Kliknij ten link, aby zobaczyć inne rodzaje publikacji na ten temat: Non-Contrast CT (NCCT).
Artykuły w czasopismach na temat „Non-Contrast CT (NCCT)”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych artykułów w czasopismach naukowych na temat „Non-Contrast CT (NCCT)”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj artykuły w czasopismach z różnych dziedzin i twórz odpowiednie bibliografie.
1
Qazi, Shakeel, Emmad Qazi, Alexis T. Wilson, Connor McDougall, Fahad Al-Ajlan, James Evans, Henrik Gensicke i in. "Identifying Thrombus on Non-Contrast CT in Patients with Acute Ischemic Stroke". Diagnostics 11, nr 10 (16.10.2021): 1919. http://dx.doi.org/10.3390/diagnostics11101919.
Pełny tekst źródłaStreszczenie:
The hyperdense sign is a marker of thrombus in non-contrast computed tomography (NCCT) datasets. The aim of this work was to determine optimal Hounsfield unit (HU) thresholds for thrombus segmentation in thin-slice non-contrast CT (NCCT) and use these thresholds to generate 3D thrombus models. Patients with thin-slice baseline NCCT (≤2.5 mm) and MCA-M1 occlusions were included. CTA was registered to NCCT, and three regions of interest (ROIs) were placed in the NCCT, including: the thrombus, contralateral brain tissue, and contralateral patent MCA-M1 artery. Optimal HU thresholds differentiating the thrombus from non-thrombus tissue voxels were calculated using receiver operating characteristic analysis. Linear regression analysis was used to predict the optimal HU threshold for discriminating the clot only based on the average contralateral vessel HU or contralateral parenchyma HU. Three-dimensional models from 70 participants using standard (45 HU) and patient-specific thresholds were generated and compared to CTA clot characteristics. The optimal HU threshold discriminating thrombus in NCCT from other structures varied with a median of 51 (IQR: 49–55). Experts chose 3D models derived using patient-specific HU models as corresponding better to the thrombus seen in CTA in 83.8% (31/37) of cases. Patient-specific HU thresholds for segmenting the thrombus in NCCT can be derived using normal parenchyma. Thrombus segmentation using patient-specific HU thresholds is superior to conventional 45 HU thresholds.
2
Saifudin, Saifudin, i Catur Budi Saputra. "NOISE REDUCTION AT IMAGE NON CONTRAST CT-SCAN UROGRAPHY WITH USING ITERATIVE RECONSTRUCTION". SANITAS: Jurnal Teknologi dan Seni Kesehatan 12, nr 1 (14.07.2021): 15–20. http://dx.doi.org/10.36525/sanitas.2021.2.
Pełny tekst źródłaStreszczenie:
The CT Scan examination technique that in the last decade is popular in diagnosing urinary stones is NCCT Urography examination. This examination is fast and informative, but this examination has a deficiency that the resulting image has a fairly high noise. Iterative Reconstruction is a method of algorithm reconstruction on CT Scan with the basic principle of estimating data to produce reconstruction image by reducing noise. The purpose of this study was to find out the difference in noise value in the use of Iterative Reconstruction in reducing noise and improving the quality of NCCT Urography image. This research was conducted retrospectively, namely on existing image given iterative reconstruction treatment of 20%, 40%, 60%, 80% and 100%. Samples in each iterative reconstruction treatment group as many as 10 images. Image is done noise measurement by doing ROI in kidneys, ureter and VU. Data analysis is done by conducting different tests of One Way Anova using SPSS Software. The results showed that there was a significant difference in noise value after it was done Iterative Reconstruction. Noise decreased as the percentage of used Iterative Reconstruction increased in NCCT Urography image. In the use of Iterative Reconstruction percentage of 100% obtained the lowest average noise value of 9.11. The use of Iterative Reconstruction can reduce noise in NCCT Urography image by 9.386% compared to Filtered Back Projection (FBP). Iterative reconstruction is able to reduce noise and improve the image quality of NCCT Urography.
3
Naylor, Jillian, Leonid Churilov, Ziyuan Chen, Miriam Koome, Neil Rane i Bruce C. V. Campbell. "Reliability, Reproducibility and Prognostic Accuracy of the Alberta Stroke Program Early CT Score on CT Perfusion and Non-Contrast CT in Hyperacute Stroke". Cerebrovascular Diseases 44, nr 3-4 (2017): 195–202. http://dx.doi.org/10.1159/000479707.
Pełny tekst źródłaStreszczenie:
Background: Alberta Stroke Program Early CT Score (ASPECTS) assesses early ischemic change on non-contrast CT (NCCT). We hypothesised that assessing ASPECTS regions on CT Perfusion (CTP) rather than NCCT would improve inter-rater agreement and prognostic accuracy, particularly in patients presenting early after stroke onset. Methods: Ischemic stroke patients treated with intravenous alteplase from 2009 to 2014 at our institution were included in this study. Inter-rater agreement and prognostic accuracy of ASPECTS across modalities were analysed by the time between stroke onset and initial NCCT, dichotomized 1st quartile versus quartiles 2-4, referred to as epochs. ASPECTS was assessed by 2 independent raters, blinded to stroke onset time, with agreement determined by weighted kappa (κw). Prognostic accuracy for favourable outcome (modified Rankin Scale 0-2) was assessed using the receiver-operating characteristic analysis. Results: A total of 227 participants were included. There was significant time-by-CT modality interaction for ASPECTS, p < 0.0001. The inter-rater agreement of ASPECTS on NCCT significantly increased as onset to CT time increased (κw epoch 1 = 0.76 vs. κw epoch 2-4 = 0.89, p = 0.04), whereas agreement using CTP parameters was stable across epochs. Inter-rater agreement for CTP-ASPECTS was significantly higher than NCCT in early epoch: Tmax κw = 0.96, p = 0.002; cerebral blood volume (CBV) κw = 0.95, p = 0.003; cerebral blood flow (CBF) κw = 0.94, p = 0.006, with no differences in the later epochs. Prognostic accuracy of ASPECTS on NCCT in epoch 1 were (area under the ROC curves [AUC] = 0.52, 95% CI 0.48-0.56), CBV (AUC = 0.55, 95% CI 0.42-0.69, CBF (AUC = 0.58, 95% CI 0.46-0.71) and Tmax (AUC = 0.62, 95% CI 0.49-0.75), p = 0.46 between modalities. Conclusions: CTP can improve reliability when assessing the extent of ischemic changes, particularly in patients imaged early after stroke onset.
4
Mattay, Raghav R., Lane Miner, Alexander Z. Copelan, Karapet Davtyan, James E. Schmitt, Ephraim W. Church i Alexander C. Mamourian. "Unruptured Arteriovenous Malformations in the Multidetector Computed Tomography Era: Frequency of Detection and Predictable Failures". Journal of Clinical Imaging Science 12 (18.02.2022): 5. http://dx.doi.org/10.25259/jcis_200_2021.
Pełny tekst źródłaStreszczenie:
Objectives: While hemorrhage arising from ruptured arteriovenous malformations (AVMs) is usually evident on multidetector non-contrast computed tomography (NCCT), unruptured AVMs can be below the limits of detection. We performed a retrospective review of NCCT of patients with a proven diagnosis of unruptured AVM to determine if advances in CT technology have made them more apparent and what features predict their detection. Material and Methods: Twenty-five NCCTs met inclusion criteria of having angiography or MR proven AVM without hemorrhage, prior surgery, or other CNS disease. Demographic variables, clinical symptoms at presentation, abnormal CT imaging findings, attenuation of the superior sagittal sinus (SSS), and Spetzler-Martin grade of each AVM were recorded. We examined the relationship between AVM detection and SSS attenuation through Kruskal–Wallis test. Exploratory serial logistic principal components analysis was performed including demographics, symptoms, and CT features in the multivariate model. Results: About 80% of the NCCTs showed an abnormality while 20% were normal. All those with an identifiable abnormality showed hyperdensity (80%). Logistic regression models indicate that clustered associations between several CT features, primarily calcifications, hyperdensity, and vascular prominence significantly predicted Spetzler-Martin grade (likelihood ratio 7.7, P = 0.006). SSS attenuation was significantly lower in subjects with occult AVMs when compared to those with CT abnormalities (median 47 vs. 55 HU, P < 0.04). Conclusion: Abnormal hyperdensity was evident in all detectable cases (80%) and multiple CT features were predictive of a higher Spetzler-Martin AVM grade. Moreover, SSS attenuation less than 50 HU was significantly correlated with a false-negative NCCT.
5
Avsenik, Jernej, Janja Pretnar Oblak i Katarina Surlan Popovic. "Non-contrast computed tomography in the diagnosis of cerebral venous sinus thrombosis". Radiology and Oncology 50, nr 3 (1.09.2016): 263–68. http://dx.doi.org/10.1515/raon-2016-0026.
Pełny tekst źródłaStreszczenie:
Abstract Background The aim of the study was to investigate the sensitivity and specificity of non-contrast computed tomography (NCCT) in the diagnosis of cerebral venous sinus thrombosis (CVST). Methods. Screening our neurological department database, we identified 53 patients who were admitted to neurological emergency department with clinical signs of CVST. Two independent observers assessed the NCCT scans for the presence of CVST. CT venography and/or MR venography were used as a reference standard. Interobserver agreement between the two readers was assessed using Kappa statistic. Attenuation inside the cerebral venous sinuses was measured and compared between the patient and the control group. Results CVST was confirmed in 13 patients. Sensitivity and specificity of NCCT for overall presence of CVST were 100% and 83%, respectively, with Kappa value of 0.72 (a good agreement between observers). The attenuation values between CVST patients and control group were significantly different (73.4 ± 14.12 HU vs. 58.1 ± 7.58 HU; p = 0.000). The ROC analysis showed an area under the curve (AUC) of 0.916 (95% CI, 0.827 – 1.00) and an optimal cutoff value of 64 HU, leading to a sensitivity of 85% and specificity of 87%. Conclusions NCCT as a first-line investigation has a high value for diagnosis of CVST in the emergency setting. The additional measurement of the sinus attenuation may improve the diagnostic value of the examination.
6
Ma, Zhuangxuan, Liang Jin, Lukai Zhang, Yuling Yang, Yilin Tang, Pan Gao, Yingli Sun i Ming Li. "Diagnosis of Acute Aortic Syndromes on Non-Contrast CT Images with Radiomics-Based Machine Learning". Biology 12, nr 3 (21.02.2023): 337. http://dx.doi.org/10.3390/biology12030337.
Pełny tekst źródłaStreszczenie:
We aimed to detect acute aortic syndromes (AAS) on non-contrast computed tomography (NCCT) images using a radiomics-based machine learning model. A total of 325 patients who underwent aortic CT angiography (CTA) were enrolled retrospectively from 2 medical centers in China to form the internal cohort (230 patients, 60 patients with AAS) and the external testing cohort (95 patients with AAS). The internal cohort was divided into the training cohort (n = 135), validation cohort (n = 49), and internal testing cohort (n = 46). The aortic mask was manually delineated on NCCT by a radiologist. Least Absolute Shrinkage and Selection Operator regression (LASSO) was used to filter out nine feature parameters; the Support Vector Machine (SVM) model showed the best performance. In the training and validation cohorts, the SVM model had an area under the curve (AUC) of 0.993 (95% CI, 0.965–1); accuracy (ACC), 0.946 (95% CI, 0.877–1); sensitivity, 0.9 (95% CI, 0.696–1); and specificity, 0.964 (95% CI, 0.903–1). In the internal testing cohort, the SVM model had an AUC of 0.997 (95% CI, 0.992–1); ACC, 0.957 (95% CI, 0.945–0.988); sensitivity, 0.889 (95% CI, 0.888–0.889); and specificity, 0.973 (95% CI, 0.959–1). In the external testing cohort, the ACC was 0.991 (95% CI, 0.937–1). This model can detect AAS on NCCT, reducing misdiagnosis and improving examinations and prognosis.
7
GER AKARSU, Fatma, Ezgi SEZER ERYILDIZ, Özlem AYKAÇ, Zehra UYSAL KOCABAŞ i Atilla Özcan Özdemir. "ASPECTS as a clinical outcome marker for MCA infarction treated with thrombolytic therapy: Non-contrast CT versus CTA source images". Neurology Asia 27, nr 2 (czerwiec 2022): 247–53. http://dx.doi.org/10.54029/2022kmj.
Pełny tekst źródłaStreszczenie:
Background & Objective: Computed tomography angiography (CTA) in acute stroke has been widely used to demonstrate arterial occlusion. Alberta Stroke Program Early CT Score (ASPECTS) is used to detect early ischemic signs in non-contrast computed tomography (NCCT) in the middle cerebral artery region. We hypothesized that computed tomography angiography source image (CTA-SI) is superior to NCCT in predicting final infarct volume, 24 hour National Institutes of Health Stroke Scale (NIHSS) score and 90-day clinical outcome. Methods: Patients who had an acute ischemic stroke due to middle cerebral artery (MCA) occlusion and treated with tissue plasminogen activator (tPA) were retrospectively evaluated. ASPECTS was evaluated by two experienced stroke neurologists in acute NCCT, CTA-SI, and follow up imaging. The final ASPECTS was compared with the mean baseline ASPECTS of NCCT and CTA-SI. The relation of both scores with 24-hour NIHSS and clinical outcome was compared. The Modified Rankin Scale (mRS) was utilized to evaluate the 90-day outcomes. mRS score of 0-2 was considered a “good outcome”. Results: Fifty-three patients were evaluated. We observed a significant relation among CTA-SI ASPECTS and after treatment 24hr ASPECTS (y= -3.9 + 1.4 x; 95% CI, -7.6 to -0.2) (y= -26.04 + 3.5 x; CI, -41 to -10). The median baseline 24-hr NHISS was 6 (0 - 22). We found a better correlation between CTA-SI ASPECTS and 24-hr NHISS (y= 363.06 + -37.03 x; CI, -148 to 864) than between NCCT ASPECTS and 24h NHISS (y=529.80 + -62.55 x; CI, 180 - 829). Median 90 days mRS score was 2 (0 - 6). According to Deming regression analysis, the CTA-SI ASPECTS (y= 76.10 + -7.69 x; 95% CI, -36 to 188) was more consistent with the 90 day mRS compared to NCCT ASPECTS (y=149.86 + -17.67 x; 95% CI, 23 - 267) CTA-SI was superior in predicting 24hr NIHSS and day 90 mRS compared to NCCT ASPECTS. Conclusion: Prediction of CTA-SI ASPECTs is better than NCCT ASPECTs at 24hr NIHSS, 3-month mRS and final infarct size in acute ischemic stroke patients treated with tPA.
8
Schön, Felix, Hannes Wahl, Arne Grey, Pawel Krukowski, Angela Müller, Volker Puetz, Jennifer Linn i Daniel P. O. Kaiser. "Improved Visualization and Quantification of Net Water Uptake in Recent Small Subcortical Infarcts in the Thalamus Using Computed Tomography". Diagnostics 13, nr 22 (9.11.2023): 3416. http://dx.doi.org/10.3390/diagnostics13223416.
Pełny tekst źródłaStreszczenie:
Diagnosing recent small subcortical infarcts (RSSIs) via early computed tomography (CT) remains challenging. This study aimed to assess CT attenuation values (Hounsfield Units (HU)) and net water uptake (NWU) in RSSI and explore a postprocessing algorithm’s potential to enhance thalamic RSSI detection. We examined non-contrast CT (NCCT) data from patients with confirmed thalamic RSSI on diffusion-weighted magnetic resonance imaging (DW-MRI) between January 2010 and October 2017. Co-registered DW-MRI and NCCT images enabled HU and NWU quantification in the infarct area compared to unaffected contralateral tissue. Results were categorized based on symptom onset to NCCT timing. Postprocessing using window optimization and frequency-selective non-linear blending (FSNLB) was applied, with interpretations by three blinded Neuroradiologists. The study included 34 patients (median age 70 years [IQR 63–76], 14 women). RSSI exhibited significantly reduced mean CT attenuation compared to unaffected thalamus (29.6 HU (±3.1) vs. 33.3 HU (±2.6); p < 0.01). Mean NWU in the infarct area increased from 6.4% (±7.2) at 0–6 h to 16.6% (±8.7) at 24–36 h post-symptom onset. Postprocessed NCCT using these HU values improved sensitivity for RSSI detection from 32% in unprocessed CT to 41% in FSNLB-optimized CT, with specificities ranging from 86% to 95%. In conclusion, CT attenuation values and NWU are discernible in thalamic RSSI up to 36 h post-symptom onset. Postprocessing techniques, particularly window optimization and FSNLB, moderately enhance RSSI detection.
9
Toh, Tsun-Haw, Khairul Azmi Abdul Kadir, Mei-Ling Sharon Tai i Kay Sin Tan. "Acute Ischaemic Stroke Successfully Treated with Thrombolytic Therapy and Endovascular Thrombectomy with Non-Contrast Computed Tomography and Computed Tomography Angiogram Protocol". Case Reports in Neurology 12, Suppl. 1 (14.12.2020): 15–21. http://dx.doi.org/10.1159/000501820.
Pełny tekst źródłaStreszczenie:
Early endovascular thrombectomy leads to improved outcomes for patients with proximal occlusions when started within 6 h from onset of symptoms. We present a case illustrating the flow of events for a patient who underwent endovascular thrombectomy in our centre after conventional imaging – a brain non-contrast computed tomography (NCCT) and CT angiogram (CTA) – achieving a door-to-groin time of 195 min. The patient is a 65-year-old who presented with signs and symptoms of a left middle cerebral artery (MCA) territory infarct. His National Institute of Health Stroke Scale (NIHSS) score was 15 on presentation and his brain NCCT showed an Alberta Stroke Programme Early CT Score (ASPECTS) of 8. His CTA showed a left MCA distal M1 occlusion with focal calcification and stenosis of the proximal left internal carotid artery. He was subsequently thrombosed and underwent thrombectomy successfully, with a door-to-groin-puncture time of 195 min. A TICI 2b reperfusion was achieved. His NIHSS score improved to 9 over the next 2 days. For cases with straightforward NCCT and CTA with no contraindications, endovascular thrombectomy should be pursued without delay. A review of the current available literature for the usage of NCCT and CTA as well as the importance of ASPECTS scoring in patient selection for endovascular thrombectomy was included.
10
Gariani, Joanna, Victor Cuvinciuc, Delphine Courvoisier, Bernhard Krauss, Vitor Mendes Pereira, Roman Sztajzel, Karl-Olof Lovblad i Maria Isabel Vargas. "Diagnosis of acute ischemia using dual energy CT after mechanical thrombectomy". Journal of NeuroInterventional Surgery 8, nr 10 (3.11.2015): 996–1000. http://dx.doi.org/10.1136/neurintsurg-2015-011988.
Pełny tekst źródłaStreszczenie:
Background and purposeTo assess the performance of dual energy unenhanced CT in the detection of acute ischemia after mechanical thrombectomy.MethodsRetrospective study, approved by the local institutional review board, including all patients that underwent intra-arterial thrombectomy in our institution over a period of 2 years. The presence of acute ischemia and hemorrhage was evaluated by three readers. Sensitivity and specificity of the non-contrast CT weighted sum image (NCCT) and the virtual non-contrast reconstructed image (VNC) were estimated and compared using generalized estimating equations to account for the non-independence of regions in each patient.Results58 patients (27 women and 31 men; mean age 70.4 years) were included in the study, yielding 580 regions of interest. Sensitivity and specificity in detecting acute ischemia were higher for all readers when using VNC, with a significant increase in sensitivity for two readers (p<0.001 and 0.01) and a significant increase in specificity in one reader (p<0.001). Specificity in detecting hemorrhage was excellent for all readers.ConclusionsDual energy unenhanced CT VNC images were superior in the identification of acute ischemia in comparison with NCCT.
11
Ezzeddine, Mustapha A., Walter J. Koroshetz, Sam Lah, Gilberto Gonzalez i Michael H. Lev. "Hemispheric Infarct Volume Prediction by CT perfusion imaging". Stroke 32, suppl_1 (styczeń 2001): 343. http://dx.doi.org/10.1161/str.32.suppl_1.343-b.
Pełny tekst źródłaStreszczenie:
P24 Objective: The ability to predict infarct volume when evaluating acute stroke patients is difficult. Bolus contrast CT perfusion imaging (CTP) with fast helical scanning, can identify that portion of ischemic brain with vasculature that does not fill with CT contrast. We evaluated the ability of this acute CTP lesion volume to predict final infarct volume. Methods: 18 patients were selected from our acute stroke database. Inclusion criteria were a CT Angiogram within 6 hours of a major stroke-like symptoms, a follow up brain imaging study no later than 30 days and no earlier than 36 hours, no thrombolytic treatment, and a hemispheric infarct. Initial non-contrast CT (NCCT), CTP and follow-up imaging volumes were measured using image analysis software. Results: Volume of infarct as determined by follow-up brain imaging is significantly predicted by CTP volume with a p value <0.001. The slope of the regression line was 2.02 and r 2 equal to 0.660. NCCT volume also predicted follow-up infarct volume, p<0.001, slope 2.13 and r 2 0.193. Conclusion: The volume of the infarct is surprisingly well predicted by the measured volume of CTP deficit. This occurs despite the variability due to secondary vascular events, edema and spontaneous reperfusion. NCCT also predicts the infarct volume but with much greater variability than the CTP. CT perfusion is a widely available technique to predict final infarct size in the acute setting.
12
Agrawal, Basudev, i Rupesh Verma. "Correlation of Glasgow Coma Scale with Non-Contrast Computed Tomography findings in immediate post traumatic brain injury". International Journal of Research in Medical Sciences 7, nr 4 (27.03.2019): 1059. http://dx.doi.org/10.18203/2320-6012.ijrms20191077.
Pełny tekst źródłaStreszczenie:
Background: This study was undertaken to correlate Glasgow Coma Scale (GCS) score with Non-Contrast Computed Tomography (NCCT) findings in patients with acute traumatic brain injury (TBI) attending tertiary care Shree Narayana Hospital, Raipur, Chhattisgarh, India.Methods: A cross-sectional study was performed among 100 patients of acute traumatic head injury (those presenting to hospital within 24 hours of injury) over a period of six months. The patient’s GCS score was determined and NCCT Brain scan was performed in each case immediately (within 30 minutes) after presenting to casualty of the hospital. A 16 slice siemens Somatom CT scan was utilized and 5mm and 10mm sections were obtained for infratentorial and supratentorial parts respectively.Results: The age range of the patients was 0 to 76 years and male: female ratio was 2.85:1. Younger age group was more commonly involved, with 61% of cases seen in 11-40 years of age group. The most common causes of head injury were road traffic accident (RTA) (65%) and fall from height (25%). The distribution of patients in accordance with GCS was found to be 55% with mild TBI (GCS 12 to 14), 25% with moderate TBI (GCS 11 to 8) and 20% with severe TBI (GCS 7 or less).Conclusions: The presence of multiple lesions and midline shift on CT scan were accompanied with lower GCS, whereas patients having single lesion had more GCS level. There was significant correlation between GCS and NCCT findings in immediate post TBI.
13
Ali, N. Imdad, Noor Elahi Pasha i Ravishankar T.H.S. "Diagnostic Accuracy of Ultrasound and Plain X-Ray KUB (Kidney, Ureter, Bladder) Compared to Non-Contrast CT (Computed Tomography) in Patients of Ureteric Calculi". Journal of Evidence Based Medicine and Healthcare 7, nr 47 (23.11.2020): 2762–66. http://dx.doi.org/10.18410/jebmh/2020/567.
Pełny tekst źródłaStreszczenie:
BACKGROUND Imaging plays a major role in the diagnosis and management of patients with urolithiasis. Non-Contrast Computed Tomography (NCCT) is generally accepted as the gold standard, but there are concerns over higher radiation exposure from NCCT to the patient population. Our prospective study compared the diagnostic accuracy of plain X-ray KUB (Kidney, Ureter, Bladder) and USG (Ultrasonography) with NCCT in the evaluation of patients with ureteric colic. METHODS This study conducted from December 2018 to January 2020 in the Department of Urology, Vijayanagar Institute of Medical Sciences, and attached Hospital. 230 patients with ureteric colic were evaluated for ureteric calculi with x-ray KUB, USG (Ultrasonography) abdomen and pelvis and NCCT (Non-Contrast Computed Tomography) KUB region. RESULTS Out of 230 patients, 168 (73 %) were males and 62 (26.9 %) were females. Ages of the study population ranged from 18 to 55 yrs. 198 of the 230 patients were confirmed to have ureteric calculus, with lower ureteric calculus 97 (48.9 %), upper ureteric 65 (32.8 %), middle ureteric 29 (14.6 %), and multiple 7 (3.5 %). X-ray and USG (Ultrasonography) group yielded a sensitivity of 86.3 %, a specificity of 87.5 %, positive predictive value 97 %, and negative predictive value 51 %. While On NCCT (Non-Contrast Computed Tomography), a total of 192 patients (96 %) demonstrated ureterolithiasis of the 198 patients confirmed to have ureteric calculi (Table 2). X-ray and USG group yielded a sensitivity of 96.9 %, specificity of 93.6 %, positive predictive value 98.9 %, and negative predictive value 83 %. CONCLUSIONS Combination of x-ray KUB and USG, and NCCT were found to be excellent imaging modalities for the detection of ureteric calculi. X-ray KUB and USG can be used as the first investigation of choice for patients with ureteric colic and for follow up of patients after treatment. KEYWORDS Ureteric Colic, Ureterolithiasis, Ultrasonography
14
Gębka, Michał, Anna Bajer-Czajkowska, Sandra Pyza, Krzysztof Safranow, Wojciech Poncyljusz i Marcin Sawicki. "Evolution of Hypodensity on Non-Contrast CT in Correlation with Collaterals in Anterior Circulation Stroke with Successful Endovascular Reperfusion". Journal of Clinical Medicine 11, nr 2 (16.01.2022): 446. http://dx.doi.org/10.3390/jcm11020446.
Pełny tekst źródłaStreszczenie:
Introduction: The aim of the study was to assess the impact of collaterals on the evolution of hypodensity on non-contrast CT (NCCT) in anterior circulation stroke with reperfusion by mechanical thrombectomy (MT). Methods: We retrospectively included stroke patients with middle cerebral artery occlusion who were reperfused by MT in early and late time window. Artificial intelligence (AI)-based software was used to calculate of hypodensity volumes at baseline NCCT (V1) and at follow-up NCCT 24 h after MT (V2), along with the difference between the two volumes (V2-V1) and the follow-up (V2)/baseline (V1) volume ratio (V2/V1). The same software was used to classify collateral status by using a 4-point scale where the score of zero indicated no collaterals and the score of three represented contrast filling of all collaterals. The volumetric values were correlated with the collateral scores. Results: Collateral scores had significant negative correlation with V1 (p = 0.035), V2, V2− V1 and V2/V1 (p < 0.001). In cases with collateral score = 3, V2 was significantly smaller or absent compared to V1; in those with collateral score 2, V2 was slightly larger than V1, and in those with scores 1 and 0 V2 was significantly larger than V1. These relationships were observed in both early and late time windows. Conclusions: The collateral status determined the evolution of the baseline hypodensity on NCCT in patients with anterior circulation stroke who had MT reperfusion. Damage can be stable or reversible in patients with good collaterals while in those with poor collaterals tissues that initially appear normal will frequently appear as necrotic after 24 h. With good collaterals, it is stable or can be reversible while with poor collaterals, normal looking tissue frequently appears as necrotic in follow-up exam. Hence, acute hypodensity represents different states of the ischemic brain parenchyma.
15
Fitzgerald, Sean T., Shunli Wang, Daying Dai, Andrew Douglas, Ramanathan Kadirvel, Matthew J. Gounis, Juyu Chueh i in. "Platelet-rich clots as identified by Martius Scarlet Blue staining are isodense on NCCT". Journal of NeuroInterventional Surgery 11, nr 11 (5.04.2019): 1145–49. http://dx.doi.org/10.1136/neurintsurg-2018-014637.
Pełny tekst źródłaStreszczenie:
BackgroundCurrent studies on clot characterization in acute ischemic stroke focus on fibrin and red blood cell composition. Few studies have examined platelet composition in acute ischemic stroke clots. We characterize clot composition using the Martius Scarlet Blue stain and assess associations between platelet density and CT density.Materials and methodHistopathological analysis of the clots collected as part of the multi-institutional STRIP registry was performed using Martius Scarlet Blue stain and the composition of the clots was quantified using Orbit Image Analysis (www.orbit.bio) machine learning software. Prior to endovascular treatment, each patient underwent non-contrast CT (NCCT) and the CT density of each clot was measured. Correlations between clot components and clinical information were assessed using the χ2 test.ResultsEighty-five patients were included in the study. The mean platelet density of the clots was 15.7% (2.5–72.5%). There was a significant correlation between platelet-rich clots and the absence of hyperdensity on NCCT, (ρ=0.321, p=0.003*, n=85). Similarly, there was a significant inverse correlation between the percentage of platelets and the mean Hounsfield Units on NCCT (ρ=−0.243, p=0.025*, n=85).ConclusionMartius Scarlet Blue stain can identify patients who have platelet-rich clots. Platelet-rich clots are isodense on NCCT.
16
Elawadi, A. A., Safa AlMohsen, Reham AlGendy, Hosam Allazkani, Reham A. Mohamed, Hossam AlAssaf, Andrew Nisbet i Mukhtar Alshanqity. "The Effect of Contrast Agents on Dose Calculations of Volumetric Modulated Arc Radiotherapy Plans for Critical Structures". Applied Sciences 11, nr 18 (9.09.2021): 8355. http://dx.doi.org/10.3390/app11188355.
Pełny tekst źródłaStreszczenie:
Radiotherapy dose calculation requires accurate Computed Tomography (CT) imaging while tissue delineation may necessitate the use of contrast agents (CA). Acquiring these two sets is a common practice in radiotherapy. This study aims to evaluate the effect of CA on the dose calculations. Two hundred and twenty-six volumetric modulated arc therapy (VMAT) patients that had planning CT with contrast (CCT) and non-contrast CT (NCCT) of different cancer sites (e.g., brain, head, and neck (H&N), chest, abdomen, and pelvis) were evaluated. Treatment plans were recalculated using CCT, then compared to NCCT. The variation in Hounsfield units (HU) and dose distributions for critical structures and target volumes were analyzed using mean HU, mean and maximum relative dose values, D2%, D98%, and 3D gamma analysis. HU variations were statistically significant for most structures. However, this was not clinically significant as the difference in mean HU values was within 30 HU for soft tissue and 50 HU for lungs. Variation in target volumes’ D2% and D98% were insignificant for all sites except brain and nasopharynx. Dose maximum differences were within 2% for the majority of critical structures and target volumes. 3D gamma analysis results revealed that majority of plans satisfied the 2% and 2 mm criteria. CCT may be acquired for VMAT radiotherapy planning purposes instead of NCCT, since there is no clinically significant difference in dose calculations based on either image set.
17
Beaulieu, Marie-Claude, Ahmad Nehme, Francis Fortin, Fatine Karkri, Nicole Daneault, Yan Deschaintre, Laura C. Gioia i in. "Non-Contrast CT and CT-Angiogram for Late Window Ischemic Stroke Treatment Selection". Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques 47, nr 3 (13.01.2020): 309–13. http://dx.doi.org/10.1017/cjn.2020.15.
Pełny tekst źródłaStreszczenie:
ABSTRACT:Introduction:The benefit of late window endovascular treatment (EVT) for anterior circulation ischemic stroke has been demonstrated using perfusion-based neuroimaging. We evaluated whether non-contrast CT (NCCT) and CT-angiogram (CTA) alone can select late-presenting patients for EVT.Methods:We performed a retrospective comparison of all patients undergoing EVT at a single comprehensive stroke center from January 2016 to April 2017. Patients planned for EVT were divided into early (<6 hours from onset) and late (≥6 hours from onset or last time seen normal) window groups. Incidence of symptomatic hemorrhagic transformations (sHTs) at 24 hours and 3-month modified Rankin scores (mRSs) were compared.Results:During the study period, 204 (82%) patients underwent EVT in the early and 44 (18%) in the late window. Median (interquartile range) NIH Stroke Scale Score was similar between groups (early: 18 [15–23] vs. late: 17 [13–21]), as were median ASPECT scores (early: 9 [8–10] vs. late: 9 [7–9]). In the late window, 42 (95%) strokes were of unknown onset. Similar proportions of sHT occurred at 24 hours (early: 12 [6%] vs. late: 4 [9%], p = 0.43). At 3 months, the proportion of patients achieving functional independence (mRS 0–2) were comparable in the early (80/192 [42%]) and late (16/41 [39%]) windows (p = 0.76).Conclusion:NCCT- and CTA-based patient selection led to similar functional independence outcomes and low proportions of sHT in the early and late windows. In centers without access to perfusion-based neuroimaging, this pragmatic approach could be safe, particularly for strokes of unknown onset.
18
Sporns, Peter, Rene Schmidt, Jens Minnerup, Rainer Dziewas, André Kemmling, Ralf Dittrich, Tarek Zoubi i in. "Computed Tomography Perfusion Improves Diagnostic Accuracy in Acute Posterior Circulation Stroke". Cerebrovascular Diseases 41, nr 5-6 (2016): 242–47. http://dx.doi.org/10.1159/000443618.
Pełny tekst źródłaStreszczenie:
Background and Purpose: Computed tomography perfusion (CTP) has a high diagnostic value in the detection of acute ischemic stroke in the anterior circulation. However, the diagnostic value in suspected posterior circulation (PC) stroke is uncertain, and whole brain volume perfusion is not yet in widespread use. We therefore studied the additional value of whole brain volume perfusion to non-contrast CT (NCCT) and CT angiography source images (CTA-SI) for infarct detection in patients with suspected acute ischemic PC stroke. Methods: This is a retrospective review of patients with suspected stroke in the PC in a database of our stroke center (n = 3,011) who underwent NCCT, CTA and CTP within 9 h after stroke onset and CT or MRI on follow-up. Images were evaluated for signs and pc-ASPECTS locations of ischemia. Three imaging models - A (NCCT), B (NCCT + CTA-SI) and C (NCCT + CTA-SI + CTP) - were compared with regard to the misclassification rate relative to gold standard (infarction in follow-up imaging) using the McNemar's test. Results: Of 3,011 stroke patients, 267 patients had a suspected stroke in the PC and 188 patients (70.4%) evidenced a PC infarct on follow-up imaging. The sensitivity of Model C (76.6%) was higher compared with that of Model A (21.3%) and Model B (43.6%). CTP detected significantly more ischemic lesions, especially in the cerebellum, posterior cerebral artery territory and thalami. Conclusions: Our findings in a large cohort of consecutive patients show that CTP detects significantly more ischemic strokes in the PC than CTA and NCCT alone.
19
Chiang, Pi-Ling, Shih-Yen Lin, Meng-Hsiang Chen, Yueh-Sheng Chen, Cheng-Kang Wang, Min-Chen Wu, Yii-Ting Huang, Meng-Yang Lee, Yong-Sheng Chen i Wei-Che Lin. "Deep Learning-Based Automatic Detection of ASPECTS in Acute Ischemic Stroke: Improving Stroke Assessment on CT Scans". Journal of Clinical Medicine 11, nr 17 (31.08.2022): 5159. http://dx.doi.org/10.3390/jcm11175159.
Pełny tekst źródłaStreszczenie:
(1) Background: The Alberta Stroke Program Early CT Score (ASPECTS) is a standardized scoring tool used to evaluate the severity of acute ischemic stroke (AIS) on non-contrast CT (NCCT). Our aim in this study was to automate ASPECTS. (2) Methods: We utilized a total of 258 patient images with suspected AIS symptoms. Expert ASPECTS readings on NCCT were used as ground truths. A deep learning-based automatic detection (DLAD) algorithm was developed for automated ASPECTS scoring based on 168 training patient images using a convolutional neural network (CNN) architecture. An additional 90 testing patient images were used to evaluate the performance of the DLAD algorithm, which was then compared with ASPECTS readings on NCCT as performed by physicians. (3) Results: The sensitivity, specificity, and accuracy of DLAD for the prediction of ASPECTS were 65%, 82%, and 80%, respectively. These results demonstrate that the DLAD algorithm was not inferior to radiologist-read ASPECTS on NCCT. With the assistance of DLAD, the individual sensitivity of the ER physician, neurologist, and radiologist improved. (4) Conclusion: The proposed DLAD algorithm exhibits a reasonable ability for ASPECTS scoring on NCCT images in patients presenting with AIS symptoms. The DLAD algorithm could be a valuable tool to improve and accelerate the decision-making process of front-line physicians.
20
Zimmer, Sebastian, Jörn Meier, Jens Minnerup, Moritz Wildgruber, Gabriel Broocks, Jawed Nawabi, Andrea Morotti i in. "Prognostic Value of Non-Contrast CT Markers and Spot Sign for Outcome Prediction in Patients with Intracerebral Hemorrhage under Oral Anticoagulation". Journal of Clinical Medicine 9, nr 4 (10.04.2020): 1077. http://dx.doi.org/10.3390/jcm9041077.
Pełny tekst źródłaStreszczenie:
Introduction: In patients with spontaneous intracerebral hemorrhage (ICH), several non-contrast computed tomography (NCCT) markers and the spot sign (SS) in computed tomography (CT) angiography (CTA) have been established for the prediction of hematoma growth and neurological outcome. However, the prognostic value of these markers in patients under oral anticoagulation (ORAC) is unclear. We hypothesized that outcome prediction by these imaging markers may be significantly different between patients with and without ORAC. Therefore, we aimed to investigate the predictive value of NCCT markers and SS in patients with ICH under ORAC. Methods: This is a retrospective study of the database for patients with ICH at a German tertiary stroke center. Inclusion criteria were (1) patients with ICH, (2) oral anticoagulation within the therapeutic range, and (3) NCCT and CTA performed on admission within 6 h after onset of symptoms. We defined a binary outcome: modified Rankin Scale (mRS) ≤ 3 = good outcome versus mRS > 3 = poor outcome at discharge. The predictive value of each sign was assessed in uni- and multivariable logistic regression models. Results: Of 129 patients with ICH under ORAC, 76 (58.9%) presented with hypodensities within the hematoma in admission NCCT, 64 (52.7%) presented with an irregular shape of the hematoma, 60 (46.5%) presented with a swirl sign, 49 (38.0%) presented with a black hole sign, and 46 (35.7%) presented with a heterogeneous density of the hematoma. Moreover, 44 (34.1%) patients had a satellite sign, in 20 (15.5%) patients, an island sign was detected, 18 (14.0%) patients were blend-sign positive, and 14 (10.9%) patients presented with a CTA spot sign. Inter-rater agreement was very high for all included characteristics between the two readers. Multivariable logistic regression analysis identified the presence of black hole sign (odds ratio 10.59; p < 0.001), swirl sign (odds ratio 14.06; p < 0.001), and satellite sign (odds ratio 6.38; p = 0.011) as independent predictors of poor outcome. Conclusions: The distribution and prognostic value of several NCCT markers and CTA spot sign in ICH patients under ORAC is comparable to those with spontaneous ICH, even though these parameters are partly based on coagulant status. These findings suggest that a similar approach can be used for further research regarding outcome prediction in ICH patients under ORAC and those with spontaneous ICH.
21
Kuang, Hulin, Xianzhen Tan, Jie Wang, Zhe Qu, Yuxin Cai, Qiong Chen, Beom Joon Kim i Wu Qiu. "Segmenting Ischemic Penumbra and Infarct Core Simultaneously on Non-Contrast CT of Patients with Acute Ischemic Stroke Using Novel Convolutional Neural Network". Biomedicines 12, nr 3 (5.03.2024): 580. http://dx.doi.org/10.3390/biomedicines12030580.
Pełny tekst źródłaStreszczenie:
Differentiating between a salvageable Ischemic Penumbra (IP) and an irreversibly damaged Infarct Core (IC) is important for therapy decision making for acute ischemic stroke (AIS) patients. Existing methods rely on Computed Tomography Perfusion (CTP) or Diffusion-Weighted Imaging–Fluid Attenuated Inversion Recovery (DWI-FLAIR). We designed a novel Convolutional Neural Network named I2PC-Net, which relies solely on Non-Contrast Computed Tomography (NCCT) for the automatic and simultaneous segmentation of the IP and IC. In the encoder, Multi-Scale Convolution (MSC) blocks were proposed to capture effective features of ischemic lesions, and in the deep levels of the encoder, Symmetry Enhancement (SE) blocks were also designed to enhance anatomical symmetries. In the attention-based decoder, hierarchical deep supervision was introduced to address the challenge of differentiating between the IP and IC. We collected 197 NCCT scans from AIS patients to evaluate the proposed method. On the test set, I2PC-Net achieved Dice Similarity Scores of 42.76 ± 21.84%, 33.54 ± 24.13% and 65.67 ± 12.30% and lesion volume correlation coefficients of 0.95 (p < 0.001), 0.61 (p < 0.001) and 0.93 (p < 0.001) for the IP, IC and IP + IC, respectively. The results indicated that NCCT could potentially be used as a surrogate technique of CTP for the quantitative evaluation of the IP and IC.
22
Gotesman, Ryan Daniel, Naomi Niznick, Brian Dewar, Dean A. Fergusson, Risa Shorr, Michel Shamy i Dar Dowlatshahi. "Prevalence of non-contrast CT abnormalities in adults with reversible cerebral vasoconstriction syndrome: protocol for a systematic review and meta-analysis". BMJ Open 10, nr 9 (wrzesień 2020): e041776. http://dx.doi.org/10.1136/bmjopen-2020-041776.
Pełny tekst źródłaStreszczenie:
IntroductionReversible cerebral vasoconstriction syndrome (RCVS) is characterised by severe, recurrent thunderclap headaches (TCHs) and vasoconstriction of cerebral arteries that resolve within 3 months. Abnormalities on non-contrast CT (NCCT) such as ischaemic strokes, intracerebral haemorrhage and subarachnoid haemorrhages are frequently observed on brain imaging of patients with RCVS though their prevalence varies considerably between studies. The aim of this systematic review and meta-analysis is to estimate the prevalence of NCCT abnormalities seen on neuroimaging of adult patients with RCVS.Methods and analysisWe will search the Medline, Embase and the Cochrane Library databases for studies on the prevalence of NCCT abnormalities on neuroimaging of patients with RCVS. Search results will be screened for eligibility by title and abstract. Suitable studies will be fully reviewed and relevant data extracted using a data abstraction form. The studies will be assessed for methodological quality, risk of bias and heterogeneity. Prevalence estimates across studies will be pooled using a random-effects model and subgroup analysis will be performed to assess the impact of age, sex, publication year and study design on prevalence of vascular lesions. Sensitivity analysis will be used to investigate the robustness of the findings. This protocol has been devised using the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols 2015 checklist.Ethics and disseminationFormal ethics is not required as primary data will not be collected. The findings of this study will be disseminated through a peer-reviewed publication and conference presentations.Trial registration numberCRD42020190637.
23
Dissaux, Brieg, Mourad Cheddad El Aouni, Julien Ognard i Jean-Christophe Gentric. "Model-Based Iterative Reconstruction (MBIR) for ASPECT Scoring in Acute Stroke Patients Selection: Comparison to rCBV and Follow-Up Imaging". Tomography 8, nr 3 (5.05.2022): 1260–69. http://dx.doi.org/10.3390/tomography8030104.
Pełny tekst źródłaStreszczenie:
Background: To compare a model-based iterative reconstruction (MBIR) versus a hybrid iterative reconstruction (HIR) for initial and final Alberta Stroke Program Early Ct Score (ASPECT) scoring in acute ischemic stroke (AIS). We hypothesized that MBIR designed for brain computed tomography (CT) could perform better than HIR for ASPECT scoring. Methods: Among patients who had undergone CT perfusion for AIS between April 2018 and October 2019 with a follow-up imaging within 7 days, we designed a cohort of representative ASPECTS. Two readers assessed regional-cerebral-blood-volume-ASPECT (rCBV-ASPECTS) on the initial exam and final-ASPECTS on the follow-up non-contrast-CT (NCCT) in consensus. Four readers performed independently MBIR and HIR ASPECT scoring on baseline NCCT. Results: In total, 294 hemispheres from 147 participants (average age of 69.59 ± 15.63 SD) were analyzed. Overall raters’ agreement between rCBV-map and MBIR and HIR ranged from moderate to moderate (κ = 0.54 to κ = 0.57) with HIR and moderate to substantial (κ = 0.52 to κ = 0.74) with MBIR. Overall raters’ agreement between follow-up imaging and HIR/MBIR ranged from moderate to moderate (κ = 0.55 to κ = 0.59) with HIR and moderate to almost perfect (κ = 0.48 to κ = 0.82) with MBIR. Conclusions: ASPECT scoring with MBIR more closely matched with initial and final infarct extent than classical HIR NCCT reconstruction.
24
Chiramal, Justy Antony, Jacob Johnson, Jemin Webster, D. Rachel Nag, Dennis Robert, Tamaghna Ghosh, Satish Golla i in. "Artificial Intelligence-based automated CT brain interpretation to accelerate treatment for acute stroke in rural India: An interrupted time series study". PLOS Global Public Health 4, nr 7 (24.07.2024): e0003351. http://dx.doi.org/10.1371/journal.pgph.0003351.
Pełny tekst źródłaStreszczenie:
In resource-limited settings, timely treatment of acute stroke is dependent upon accurate diagnosis that draws on non-contrast computed tomography (NCCT) scans of the head. Artificial Intelligence (AI) based devices may be able to assist non-specialist physicians in NCCT interpretation, thereby enabling faster interventions for acute stroke patients in these settings. We evaluated the impact of an AI device by comparing the time to intervention (TTI) from NCCT imaging to significant intervention before (baseline) and after the deployment of AI, in patients diagnosed with stroke (ischemic or hemorrhagic) through a retrospective interrupted time series analysis at a rural hospital managed by non-specialists in India. Significant intervention was defined as thrombolysis or antiplatelet therapy in ischemic strokes, and mannitol for hemorrhagic strokes or mass effect. We also evaluated the diagnostic accuracy of the software using the teleradiologists’ reports as ground truth. Impact analysis in a total of 174 stroke patients (72 in baseline and 102 after deployment) demonstrated a significant reduction of median TTI from 80 minutes (IQR: 56·8–139·5) during baseline to 58·50 (IQR: 30·3–118.2) minutes after AI deployment (Wilcoxon rank sum test—location shift: -21·0, 95% CI: -38·0, -7·0). Diagnostic accuracy evaluation in a total of 864 NCCT scans demonstrated the sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) in detecting intracranial hemorrhage to be 0·89 (95% CI: 0·83–0·93), 0·99 (0·98–1·00), 0·96 (0·91–0·98) and 0·97 (0·96–0·98) respectively, and for infarct these were 0·84 (0·79–0·89), 0·81 (0·77–0·84), 0·58 (0·52–0·63), and 0·94 (0·92–0·96), respectively. AI-based NCCT interpretation supported faster abnormality detection with high accuracy, resulting in persons with acute stroke receiving significantly earlier treatment. Our results suggest that AI-based NCCT interpretation can potentially improve uptake of lifesaving interventions for acute stroke in resource-limited settings.
25
Choi, Jae Won, Yeon Jin Cho, Ji Young Ha, Seul Bi Lee, Seunghyun Lee, Young Hun Choi, Jung-Eun Cheon i Woo Sun Kim. "Generating synthetic contrast enhancement from non-contrast chest computed tomography using a generative adversarial network". Scientific Reports 11, nr 1 (14.10.2021). http://dx.doi.org/10.1038/s41598-021-00058-3.
Pełny tekst źródłaStreszczenie:
AbstractThis study aimed to evaluate a deep learning model for generating synthetic contrast-enhanced CT (sCECT) from non-contrast chest CT (NCCT). A deep learning model was applied to generate sCECT from NCCT. We collected three separate data sets, the development set (n = 25) for model training and tuning, test set 1 (n = 25) for technical evaluation, and test set 2 (n = 12) for clinical utility evaluation. In test set 1, image similarity metrics were calculated. In test set 2, the lesion contrast-to-noise ratio of the mediastinal lymph nodes was measured, and an observer study was conducted to compare lesion conspicuity. Comparisons were performed using the paired t-test or Wilcoxon signed-rank test. In test set 1, sCECT showed a lower mean absolute error (41.72 vs 48.74; P < .001), higher peak signal-to-noise ratio (17.44 vs 15.97; P < .001), higher multiscale structural similarity index measurement (0.84 vs 0.81; P < .001), and lower learned perceptual image patch similarity metric (0.14 vs 0.15; P < .001) than NCCT. In test set 2, the contrast-to-noise ratio of the mediastinal lymph nodes was higher in the sCECT group than in the NCCT group (6.15 ± 5.18 vs 0.74 ± 0.69; P < .001). The observer study showed for all reviewers higher lesion conspicuity in NCCT with sCECT than in NCCT alone (P ≤ .001). Synthetic CECT generated from NCCT improves the depiction of mediastinal lymph nodes.
26
Xu, Yuancheng, Stanislau Hrybouski, D. Ian Paterson, Zhiyang Li, Yulong Lan, Lin Luo, Xinping Shen i Lingyu Xu. "Comparison of epicardial adipose tissue volume quantification between ECG-gated cardiac and non-ECG-gated chest computed tomography scans". BMC Cardiovascular Disorders 22, nr 1 (13.12.2022). http://dx.doi.org/10.1186/s12872-022-02958-2.
Pełny tekst źródłaStreszczenie:
Abstract Background This study investigated accuracy and consistency of epicardial adipose tissue (EAT) quantification in non-ECG-gated chest computed tomography (CT) scans. Methods EAT volume was semi-automatically quantified using a standard Hounsfield unit threshold (− 190, − 30) in three independent cohorts: (1) Cohort 1 (N = 49): paired 120 kVp ECG-gated cardiac non-contrast CT (NCCT) and 120 kVp non-ECG-gated chest NCCT; (2) Cohort 2 (N = 34): paired 120 kVp cardiac NCCT and 100 kVp non-ECG-gated chest NCCT; (3) Cohort 3 (N = 32): paired non-ECG-gated chest NCCT and chest contrast-enhanced CT (CECT) datasets (including arterial phase and venous phase). Images were reconstructed with the slice thicknesses of 1.25 mm and 5 mm in the chest CT datasets, and 3 mm in the cardiac NCCT datasets. Results In Cohort 1, the chest NCCT-1.25 mm EAT volume was similar to the cardiac NCCT EAT volume, while chest NCCT-5 mm underestimated the EAT volume by 7.5%. In Cohort 2, 100 kVp chest NCCT-1.25 mm were 13.2% larger than 120 kVp cardiac NCCT EAT volumes. In Cohort 3, the chest arterial CECT and venous CECT dataset underestimated EAT volumes by ~ 28% and ~ 18%, relative to chest NCCT datasets. All chest CT-derived EAT volumes were similarly associated with significant coronary atherosclerosis with cardiac CT counterparts. Conclusion The 120 kVp non-ECG-gated chest NCCT-1.25 mm images produced EAT volumes comparable to cardiac NCCT. Chest CT EAT volumes derived from consistent imaging settings are excellent alternatives to the cardiac NCCT to investigate their association with coronary artery disease.
27
Morotti, Andrea, Qi Li, Valentina Mazzoleni, Jawed Nawabi, Frieder Schlunk, Federico Mazzacane, Giorgio Busto i in. "Non-contrast CT Markers of Intracerebral Hemorrhage Expansion: The influence of onset-to-CT time". International Journal of Stroke, 22.11.2022, 174749302211427. http://dx.doi.org/10.1177/17474930221142742.
Pełny tekst źródłaStreszczenie:
Background: Hematoma expansion (HE) is an appealing therapeutic target in intracerebral hemorrhage (ICH) and non-contrast computed tomography (NCCT) features are promising predictors of HE. Aims: We investigated whether onset-to-CT time influences the diagnostic performance of NCCT markers for HE. Methods: retrospective multicentre analysis of patients with primary ICH. The following NCCT markers were analyzed: hypodensities, heterogeneous density, blend sign, and irregular shape. HE was defined as growth > 6 mL and/or > 33%. We calculated the sensitivity, specificity, positive and negative predictive values (PPV and NPV) of NCCT markers for HE, stratified by onset-to-CT time (< 2 h, 2-4 h, 4-6 h, >6 h). Results: We included 1135 patients, (median age 69, 53% males) of whom 307 (27%) experienced HE. Overall hypodensities had the highest sensitivity (0.68) and blend sign the highest specificity (0.87) for HE. Hypodensities were more common and had higher sensitivity (0.80) in patients with imaging within 2 h. The same result was observed for heterogeneous density whereas irregular shape had a similar prevalence across time strata and higher sensitivity (0.79) beyond 6 h from onset. The frequency of blend sign increased with longer onset-to-CT-time whereas its specificity declined after 6 h from onset. Conclusion: the diagnostic performance of NCCT markers is influenced by imaging time. Hypodensities identified four out of five patients with HE within 2 h from onset whereas irregular shape performed better in late presenters. Our findings may improve the use of NCCT markers in future studies and trials targeting HE.
28
Nawabi, Jawed, Frieder Schlunk, Andrea Dell Orco, Sarah Elsayed, Federico Mazzacane, Dmitriy Desser, Ly Vu i in. "Non-contrast computed tomography features predict intraventricular hemorrhage growth". European Radiology, 22.05.2023. http://dx.doi.org/10.1007/s00330-023-09707-9.
Pełny tekst źródłaStreszczenie:
Abstract Objectives Non-contrast computed tomography (NCCT) markers are robust predictors of parenchymal hematoma expansion in intracerebral hemorrhage (ICH). We investigated whether NCCT features can also identify ICH patients at risk of intraventricular hemorrhage (IVH) growth. Methods Patients with acute spontaneous ICH admitted at four tertiary centers in Germany and Italy were retrospectively included from January 2017 to June 2020. NCCT markers were rated by two investigators for heterogeneous density, hypodensity, black hole sign, swirl sign, blend sign, fluid level, island sign, satellite sign, and irregular shape. ICH and IVH volumes were semi-manually segmented. IVH growth was defined as IVH expansion > 1 mL (eIVH) or any delayed IVH (dIVH) on follow-up imaging. Predictors of eIVH and dIVH were explored with multivariable logistic regression. Hypothesized moderators and mediators were independently assessed in PROCESS macro models. Results A total of 731 patients were included, of whom 185 (25.31%) suffered from IVH growth, 130 (17.78%) had eIVH, and 55 (7.52%) had dIVH. Irregular shape was significantly associated with IVH growth (OR 1.68; 95%CI [1.16–2.44]; p = 0.006). In the subgroup analysis stratified by the IVH growth type, hypodensities were significantly associated with eIVH (OR 2.06; 95%CI [1.48–2.64]; p = 0.015), whereas irregular shape (OR 2.72; 95%CI [1.91–3.53]; p = 0.016) in dIVH. The association between NCCT markers and IVH growth was not mediated by parenchymal hematoma expansion. Conclusions NCCT features identified ICH patients at a high risk of IVH growth. Our findings suggest the possibility to stratify the risk of IVH growth with baseline NCCT and might inform ongoing and future studies. Clinical relevance statement Non-contrast CT features identified ICH patients at a high risk of intraventricular hemorrhage growth with subtype-specific differences. Our findings may assist in the risk stratification of intraventricular hemorrhage growth with baseline CT and might inform ongoing and future clinical studies. Key Points • NCCT features identified ICH patients at a high risk of IVH growth with subtype-specific differences. • The effect of NCCT features was not moderated by time and location or indirectly mediated by hematoma expansion. • Our findings may assist in the risk stratification of IVH growth with baseline NCCT and might inform ongoing and future studies.
29
Wolman, Dylan N., Fasco van Ommen, Elizabeth Tong, Frans Kauw, Jan Willem Dankbaar, Edwin Bennink, Hugo W. A. M. de Jong, Lior Molvin, Max Wintermark i Jeremy J. Heit. "Non-contrast dual-energy CT virtual ischemia maps accurately estimate ischemic core size in large-vessel occlusive stroke". Scientific Reports 11, nr 1 (24.03.2021). http://dx.doi.org/10.1038/s41598-021-85143-3.
Pełny tekst źródłaStreszczenie:
AbstractDual-energy CT (DECT) material decomposition techniques may better detect edema within cerebral infarcts than conventional non-contrast CT (NCCT). This study compared if Virtual Ischemia Maps (VIM) derived from non-contrast DECT of patients with acute ischemic stroke due to large-vessel occlusion (AIS-LVO) are superior to NCCT for ischemic core estimation, compared against reference-standard DWI-MRI. Only patients whose baseline ischemic core was most likely to remain stable on follow-up MRI were included, defined as those with excellent post-thrombectomy revascularization or no perfusion mismatch. Twenty-four consecutive AIS-LVO patients with baseline non-contrast DECT, CT perfusion (CTP), and DWI-MRI were analyzed. The primary outcome measure was agreement between volumetric manually segmented VIM, NCCT, and automatically segmented CTP estimates of the ischemic core relative to manually segmented DWI volumes. Volume agreement was assessed using Bland–Altman plots and comparison of CT to DWI volume ratios. DWI volumes were better approximated by VIM than NCCT (VIM/DWI ratio 0.68 ± 0.35 vs. NCCT/DWI ratio 0.34 ± 0.35; P < 0.001) or CTP (CTP/DWI ratio 0.45 ± 0.67; P < 0.001), and VIM best correlated with DWI (rVIM = 0.90; rNCCT = 0.75; rCTP = 0.77; P < 0.001). Bland–Altman analyses indicated significantly greater agreement between DWI and VIM than NCCT core volumes (mean bias 0.60 [95%AI 0.39–0.82] vs. 0.20 [95%AI 0.11–0.30]). We conclude that DECT VIM estimates the ischemic core in AIS-LVO patients more accurately than NCCT.
30
Hablas, Lina Tarek, Alshimaa Magdy Ammar i Rehab Mohamed Elnagar. "CSF rhinorrhea: non-contrast CT, contrast-enhanced CT cisternography or combined?" Egyptian Journal of Radiology and Nuclear Medicine 53, nr 1 (6.09.2022). http://dx.doi.org/10.1186/s43055-022-00889-8.
Pełny tekst źródłaStreszczenie:
Abstract Background Radiologic diagnosis of CSF leaks is challenging. We evaluated the diagnostic value of non-contrast CT and contrast-enhanced CT cisternography in identifying the presence of CSF rhinorrhea and site of leak as well as comparing them to surgical data and/or clinical follow-up. Results Fifty patients (20 males and 30 females) were included in our study with age ranging from 19 to 67 years. 76% of cases had spontaneous CSF rhinorrhea. Cribriform plate defect was the most common site of CSF leak, accounting for about 50% of cases. The highest sensitivity, specificity, PPV and NPV for diagnosis of CSF rhinorrhea were observed with the combined NCCT and CECTC with values 87%, 100%, 100% and 67%, respectively. Conclusion Accurate surgical planning and successful dural repair requires accurate localization of the dural and osseous defects. CT cisternography which already involves pre-cisternography non-contrast images holds great sensitivity in detection of the exact defect site together with confirmation of the CSF leak.
31
"Benefit of Contrast-Enhanced PET/CT versus Non-Contrast-Enhanced PET/CT Relative to Lesion Detection, Lesion Characterization, and Diagnostic Accuracy in Patients with Cancer". Journal of the Medical Association of Thailand 103, nr 9 (15.09.2020): 904–13. http://dx.doi.org/10.35755/jmedassocthai.2020.09.10643.
Pełny tekst źródłaStreszczenie:
Objective: To investigate the benefit of contrast-enhanced PET/CT (PET/CECT) versus non-contrast-enhanced PET/CT (PET/NCCT) relative to lesion detection, characterization, and diagnostic accuracy in cancer patients. Materials and Methods: The present study was a prospective study that included patients older than 18 years with histopathologically proven cancer who underwent [F-18] fluorodeoxyglucose ([F-18]FDG) PET/CT at the Division of Nuclear Medicine, Department of Radiology, Faculty of Medicine, Siriraj Hospital between December 2014 and November 2017. PET/NCCT was performed followed by PET/CECT scan in all patients. The results of PET/NCCT, PET/CECT, and pre- and post-contrast enhanced PET/CT (PET/NCCT-CECT) for each patient were interpreted by one nuclear medicine physician and one radiologist. The sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were calculated from ROC curve analysis. Results: One hundred ten patients were included. The mean age was 52.45±17.14 years, and 52.7% were female. Lymphoma was the most common cancer diagnosis (47.3%). No significant difference was observed between PET/CT techniques for detection rate at the primary tumor site, lymph node, or distant organ. High agreement was observed between PET/CT techniques for lesion characterization. Lesion characterizations were not significantly correlated with age, gender, BMI, or FBS; however, lesion characterization was found to be significantly associated with primary tumor site, indication for PET/CT and lesion size. The following ranges were observed from all PET/CT techniques: sensitivity 81.5% to 85.3%, specificity 94.4% to 95.5%, accuracy 89.4% to 91.4%, PPV 90.4% to 92.1%, and NPV 88.9% to 91.3%. Conclusion: [F-18]FDG PET/CECT demonstrated no significant advantage over PET/NCCT for lesion detection, lesion characterization, or diagnostic accuracy in patients with cancer. The use of intravenous contrast material should be limited to select cases to reduce the risk of renal toxicity or anaphylactic reaction, and to minimize unnecessary costs. Keywords: Contrast-enhanced PET/CT, Non-contrast-enhanced PET/CT, Lesion detection, Lesion characterization, Diagnostic accuracy, Cancer, [F-18]FDG
32
McVerry, Ferghal, Krishna A. Dani, Niall J. MacDougall i Keith W. Muir. "Abstract 3417: Pixel by Pixel Comparison of CTP-Defined Infarct Core on Concurrent Non-Contrast CT". Stroke 43, suppl_1 (luty 2012). http://dx.doi.org/10.1161/str.43.suppl_1.a3417.
Pełny tekst źródłaStreszczenie:
Introduction Interobserver agreement for the presence of early ischemic changes on non-contrast CT (NCCT) in potential thrombolysis candidates can be poor even among experienced raters. CT perfusion (CTP) may demonstrate infarct core and penumbra according to proposed thresholds but the extent of correlation between CTP defined core and hypodensity on hyperacute NCCT is unclear Methods A pixel by pixel comparison between NCCT and concurrent CTP obtained <6hrs from symptom onset was performed for patients with symptomatic arterial occlusions. Segmentation was performed using time-averaged CTP raw images to compare core and normal tissue pixels for grey and white matter separately. Core was defined as relative Cerebral Blood Flow (CBF) of <45% of normal tissue. NCCT was co-registered to the baseline frames of the concurrent CTP using a rigid body transformation. Core pixels were extracted from CTP and transposed to NCCT. Hounsfield unit (HU) values in CTP-defined core and normal tissue were quantified for grey and white matter. Receiver operating characteristic (ROC) curve analysis was performed to assess the predictive value of NCCT hypodensity and CTP-defined core. Results CT and CTP were compared for 33 patients. Mean age was 72 years (SD 12), median NIHSS was 16 (IQR 11-20) and mean time from symptom onset to CTP was 191 minutes (SD 63). Area under the curve (AUC) for prediction of grey and white matter core by NCCT was 0.641 and 0.601 respectively. The most frequently occurring optimum HU cut-points were 29 and 28 for grey and white matter respectively .These cut-points were associated with low overall specificity for detecting core (Median ± IQR= 0.48, 0.32-0.59 and 0.36, 0.26-0.44) but higher sensitivity (Median ±IQR 0.79, 0.62-0.87 and 0.83, 0.73-0.89) for grey and white matter Conclusion Objectively determined hypodensity on NCCT has low sensitivity and specificity for prediction of ischemic core tissue defined by CT perfusion. Thresholds were similar for both grey and white matter. NCCT scans without established hypodensity may still have irreversibly infarcted pixels which can be detected with CTP. Prospective evaluation of the added value of CTP-defined core on decision making in acute stroke is needed.
33
Sahoo, Prasan Kumar, Sulagna Mohapatra, Ching-Yi Wu, Kuo-Lun Huang, Ting-Yu Chang i Tsong-Hai Lee. "Automatic identification of early ischemic lesions on non-contrast CT with deep learning approach". Scientific Reports 12, nr 1 (27.10.2022). http://dx.doi.org/10.1038/s41598-022-22939-x.
Pełny tekst źródłaStreszczenie:
AbstractEarly ischemic lesion on non-contrast computed tomogram (NCCT) in acute stroke can be subtle and need confirmation with magnetic resonance (MR) image for treatment decision-making. We retrospectively included the NCCT slices of 129 normal subjects and 546 ischemic stroke patients (onset < 12 h) with corresponding MR slices as reference standard from a prospective registry of Chang Gung Research Databank. In model selection, NCCT slices were preprocessed and fed into five different pre-trained convolutional neural network (CNN) models including Visual Geometry Group 16 (VGG16), Residual Networks 50, Inception-ResNet-v2, Inception-v3, and Inception-v4. In model derivation, the customized-VGG16 model could achieve an accuracy of 0.83, sensitivity 0.85, F-score 0.80, specificity 0.82, and AP 0.82 after using a tenfold cross-validation method, outperforming the pre-trained VGG16 model. In model evaluation, the customized-VGG16 model could correctly identify 53 in 58 subjects (91.37%) including 29 ischemic stroke patients and 24 normal subjects and reached the sensitivity of 86.95% in identifying ischemic NCCT slices (200/230), irrespective of supratentorial or infratentorial lesions. The customized-VGG16 CNN model can successfully identify the presence of early ischemic lesions on NCCT slices using the concept of automatic feature learning. Further study will be proceeded to detect the location of ischemic lesion.
34
Christensen, Soren, Christian Federau, Julian Maclaren, Aditya Srivatsan, Greg Albers i Maarten Lansberg. "Abstract TP64: Ischemic Stroke Lesion Identification in Non-Contrast CT Using Deep Learning". Stroke 51, Suppl_1 (luty 2020). http://dx.doi.org/10.1161/str.51.suppl_1.tp64.
Pełny tekst źródłaStreszczenie:
Background: Automatic measurement of the acute stroke lesion volume on DWI and CT-CBF has been used in recent late window trials. Despite non-contrast CT (NCCT) being the most widely used imaging modality in the acute stroke setting, quantification of acute stroke volumes on NCCT has not been employed in trials because of the difficulty outlining territory with very mild Hounsfield unit depression. Deep learning algorithms have been effective at solving many image processing tasks and may outperform human readers given enough training data. The goal of this study was to train and test a deep learning model on NCCT scans with synthetic stroke lesions and to determine the optimal model design. Methods: Training: 20 NCCT scans without acute stroke were combined with 20 DWI lesions using co-registration producing 400 non-contrast scans with lesions. The region of the NCCT that coincided with the DWI lesion was depressed by 2 Hounsfield units to simulate an acute infarct. An independent validation dataset of 100 cases was created in the same way. Two models were used: a standard “Unet” model and a symmetry-aware Unet model. The models were compared in terms of segmentation accuracy in the independent validation dataset. Results: Both the symmetry aware U-net and the standard U-net detected some part of the true lesion in 100% of the cases. The symmetry aware U-net was more sensitive, median [iqr], (45% [27-68] vs 17% [6-54], p<0.00001) but slightly less specific (98% [93-98] vs 99% [94-99], p<0.0008) than the standard U-net. Conclusion: The symmetry aware U-net shows great promise in detection of acute strokes on NCCT; lesions with Hounsfield unit depressions that are barely visible to the eye can be automatically segmented by this model. Additional training data and architectural enhancements are likely to improve the current spatial sensitivity to above 45%.
35
Shahrouki, Puja, Shingo Kihira, Elham Tavakkol, Joe X. Qiao, Achala Vagal, Pooja Khatri, Mersedeh Bahr-Hosseini i in. "Automated assessment of ischemic core on non-contrast computed tomography: a multicenter comparative analysis with CT perfusion". Journal of NeuroInterventional Surgery, 2.11.2023, jnis—2023–020954. http://dx.doi.org/10.1136/jnis-2023-020954.
Pełny tekst źródłaStreszczenie:
BackgroundApplication of machine learning (ML) algorithms has shown promising results in estimating ischemic core volumes using non-contrast CT (NCCT).ObjectiveTo assess the performance of the e-Stroke Suite software (Brainomix) in assessing ischemic core volumes on NCCT compared with CT perfusion (CTP) in patients with acute ischemic stroke.MethodsIn this retrospective multicenter study, patients with anterior circulation large vessel occlusions who underwent pretreatment NCCT and CTP, successful reperfusion (modified Thrombolysis in Cerbral Infarction ≥2b), and post-treatment MRI, were included from three stroke centers. Automated calculation of ischemic core volumes was obtained on NCCT scans using ML algorithm deployed by e-Stroke Suite and from CTP using Olea software (Olea Medical). Comparative analysis was performed between estimated core volumes on NCCT and CTP and against MRI calculated final infarct volume (FIV).ResultsA total of 111 patients were included. Estimated ischemic core volumes (mean±SD, mL) were 20.4±19.0 on NCCT and 19.9±18.6 on CTP, not significantly different (P=0.82). There was moderate (r=0.40) and significant (P<0.001) correlation between estimated core on NCCT and CTP. The mean difference between FIV and estimated core volume on NCCT and CTP was 29.9±34.6 mL and 29.6±35.0 mL, respectively (P=0.94). Correlations between FIV and estimated core volume were similar for NCCT (r=0.30, P=0.001) and CTP (r=0.36, P<0.001).ConclusionsResults show that ML-based estimated ischemic core volumes on NCCT are comparable to those obtained from concurrent CTP in magnitude and in degree of correlation with MR-assessed FIV.
36
Imarhia, Frances, Soren Christensen, Maarten G. Lansberg, Adam Wang, Jeremy J. Heit i Greg Albers. "Abstract WP103: Comparison Of Acute Infarct Lesions Between Non-contrast CT, DWI And FLAIR Using Back-to-back Imaging". Stroke 53, Suppl_1 (luty 2022). http://dx.doi.org/10.1161/str.53.suppl_1.wp103.
Pełny tekst źródłaStreszczenie:
Introduction: Size and location of the acute infarct is a major determinant of stroke outcome and eligibility for therapy. Recently, there have been efforts to train deep learning networks to detect lesions on Non-Contrast CT (NCCT) using concurrent DWI imaging as the gold standard. However, little is known about the radiological correspondence between concurrent NCCT and DWI lesion sizes. We performed an exploratory analysis comparing the stroke lesion volume on acute NCCT to that on DWI and FLAIR images performed shortly after. Methods: Population: DEFUSE 3 trial patients scanned 6-16h after last known well with DWI and NCCT <1h apart. NCCT was segmented using an algorithm detecting more than 5% depression compared to the contralateral homologous region. The DWIs and FLAIR were co-registered to NCCT and manually segmented in ITK-Snap. Results: Thirteen patients fulfilled inclusion criteria. DWI volumes were (median, [IQR]) 52 mL [39 - 102], FLAIR volumes 35 mL [18 - 66] and NCCT lesion volumes 14 mL [8 - 22]. NCCT lesions were significantly smaller than both DWI and FLAIR, p < 0.001 and p < 0.048. The Dice coefficient was 0.2 [0.1 - 0.3] for FLAIR vs NCCT and 0.3 [0.1 - 0.5] for DWI vs NCCT. Conclusion: NCCT lesion volumes were consistently smaller than both DWI and FLAIR lesions although the volumetric agreement with FLAIR lesions was better. Both FLAIR and NCCT are sensitive to influx of parenchymal water and as such may have more similar lesions than DWI imaging which is sensitive to early occurring intraparenchymal displacements. The findings suggest that the training of deep learning networks to detect early NCCT hypodensity should focus on FLAIR or expert outlines drawn directly on the NCCT rather than DWI as the gold standard.
37
Wang, Chengyan, Zhang Shi, Ming Yang, Lixiang Huang, Wenxing Fang, Li Jiang, Jing Ding i He Wang. "Deep learning-based identification of acute ischemic core and deficit from non-contrast CT and CTA". Journal of Cerebral Blood Flow & Metabolism, 8.06.2021, 0271678X2110236. http://dx.doi.org/10.1177/0271678x211023660.
Pełny tekst źródłaStreszczenie:
The accurate identification of irreversible infarction and salvageable tissue is important in planning the treatments for acute ischemic stroke (AIS) patients. Computed tomographic perfusion (CTP) can be used to evaluate the ischemic core and deficit, covering most of the territories of anterior circulation, but many community hospitals and primary stroke centers do not have the capability to perform CTP scan in emergency situation. This study aimed to identify AIS lesions from widely available non-contrast computed tomography (NCCT) and CT angiography (CTA) using deep learning. A total of 345AIS patients from our emergency department were included. A multi-scale 3D convolutional neural network (CNN) was used as the predictive model with inputs of NCCT, CTA, and CTA+ (8 s delay after CTA) images. An external cohort with 108 patients was included to further validate the generalization performance of the proposed model. Strong correlations with CTP-RAPID segmentations ( r = 0.84 for core, r = 0.83 for deficit) were observed when NCCT, CTA, and CTA+ images were all used in the model. The diagnostic decisions according to DEFUSE3 showed high accuracy when using NCCT, CTA, and CTA+ (0.90±0.04), followed by the combination of NCCT and CTA (0.87±0.04), CTA-alone (0.76±0.06), and NCCT-alone (0.53±0.09).
38
Sun, Yingli, Wei Zhao, Kaiming Kuang, Liang Jin, Pan Gao, Shaofeng Duan, Yi Xiao, Jun Liu i Ming Li. "Non-contrast and contrast enhanced computed tomography radiomics in preoperative discrimination of lung invasive and non-invasive adenocarcinoma". Frontiers in Medicine 9 (4.11.2022). http://dx.doi.org/10.3389/fmed.2022.939434.
Pełny tekst źródłaStreszczenie:
ObjectiveThis study aimed to assess the value of radiomics based on non-contrast computed tomography (NCCT) and contrast-enhanced computed tomography (CECT) images in the preoperative discrimination between lung invasive adenocarcinomas (IAC) and non-invasive adenocarcinomas (non-IAC).MethodsWe enrolled 1,185 pulmonary nodules (478 non-IACs and 707 IACs) to build and validate radiomics models. An external testing set comprising 63 pulmonary nodules was collected to verify the generalization of the models. Radiomic features were extracted from both NCCT and CECT images. The predictive performance of radiomics models in the validation and external testing sets were evaluated and compared with radiologists’ evaluations. The predictive performances of the radiomics models were also compared between three subgroups in the validation set (Group 1: solid nodules, Group 2: part-solid nodules, and Group 3: pure ground-glass nodules).ResultsThe NCCT, CECT, and combined models showed good ability to discriminate between IAC and non-IAC [respective areas under the curve (AUCs): validation set = 0.91, 0.90, and 0.91; Group 1 = 0.82, 0.79, and 0.81; Group 2 = 0.93, 0.92, and 0.93; and Group 3 = 0.90, 0.90, and 0.89]. In the external testing set, the AUC of the three models were 0.89, 0.91, and 0.89, respectively. The accuracies of these three models were comparable to those of the senior radiologist and better those that of the junior radiologist.ConclusionRadiomic models based on CT images showed good predictive performance in discriminating between lung IAC and non-IAC, especially in part solid nodule group. However, radiomics based on CECT images provided no additional value compared to NCCT images.
39
Mussmann, Bo, Peter Marshall Skov, Morten H. Lorentzen, Helene Skjøt-Arkil, Ole Graumann, Michael B. Andersen i Janni Jensen. "Ultra-low-dose emergency chest computed tomography protocols in three vendors: A technical note". Acta Radiologica Open 12, nr 3 (marzec 2023). http://dx.doi.org/10.1177/20584601231183900.
Pełny tekst źródłaStreszczenie:
Background In suspected community-acquired pneumonia (CAP), chest CT is superior to the routinely obtained radiographs (CXR), but administers higher radiation doses. However, ultra-low-dose CT (ULDCT) has shown promising results. Purpose To compare radiation dose and image quality using standard and ULDCT protocols designed for a multicenter study encompassing three CT scanner models from GE, Canon, and Siemens. Material and methods Patients with suspected CAP were referred for non-contrast standard dose chest CT (NCCT) and ULDCT. Effective radiation dose and Contrast-to-Noise Ratio (CNR) was calculated. Results Mean effective doses were GE ( n = 10) 6.93 mSv in NCCT and 0.27 mSv in ULDCT; Canon ( n = 9) 3.48 in mSv NCCT and 1.11 mSv in ULDCT; Siemens ( n = 10) 2.85 mSv in NCCT and 0.45 mSv in ULDCT. CNR was reduced by 29–39% in ULDCT. Conclusion The proposed CT protocols yielded dose reductions of 96%, 68%, and 84% using a GE, Canon, and Siemens scanner, respectively.
40
Zhai, Zhiwei, Sanne G. M. van Velzen, Nikolas Lessmann, Nils Planken, Tim Leiner i Ivana Išgum. "Learning coronary artery calcium scoring in coronary CTA from non-contrast CT using unsupervised domain adaptation". Frontiers in Cardiovascular Medicine 9 (12.09.2022). http://dx.doi.org/10.3389/fcvm.2022.981901.
Pełny tekst źródłaStreszczenie:
Deep learning methods have demonstrated the ability to perform accurate coronary artery calcium (CAC) scoring. However, these methods require large and representative training data hampering applicability to diverse CT scans showing the heart and the coronary arteries. Training methods that accurately score CAC in cross-domain settings remains challenging. To address this, we present an unsupervised domain adaptation method that learns to perform CAC scoring in coronary CT angiography (CCTA) from non-contrast CT (NCCT). To address the domain shift between NCCT (source) domain and CCTA (target) domain, feature distributions are aligned between two domains using adversarial learning. A CAC scoring convolutional neural network is divided into a feature generator that maps input images to features in the latent space and a classifier that estimates predictions from the extracted features. For adversarial learning, a discriminator is used to distinguish the features between source and target domains. Hence, the feature generator aims to extract features with aligned distributions to fool the discriminator. The network is trained with adversarial loss as the objective function and a classification loss on the source domain as a constraint for adversarial learning. In the experiments, three data sets were used. The network is trained with 1,687 labeled chest NCCT scans from the National Lung Screening Trial. Furthermore, 200 labeled cardiac NCCT scans and 200 unlabeled CCTA scans were used to train the generator and the discriminator for unsupervised domain adaptation. Finally, a data set containing 313 manually labeled CCTA scans was used for testing. Directly applying the CAC scoring network trained on NCCT to CCTA led to a sensitivity of 0.41 and an average false positive volume 140 mm3/scan. The proposed method improved the sensitivity to 0.80 and reduced average false positive volume of 20 mm3/scan. The results indicate that the unsupervised domain adaptation approach enables automatic CAC scoring in contrast enhanced CT while learning from a large and diverse set of CT scans without contrast. This may allow for better utilization of existing annotated data sets and extend the applicability of automatic CAC scoring to contrast-enhanced CT scans without the need for additional manual annotations. The code is publicly available at https://github.com/qurAI-amsterdam/CACscoringUsingDomainAdaptation.
41
Hillal, Amir, Gabriella Sultani, Birgitta Ramgren, Bo Norrving, Johan Wassélius i Teresa Ullberg. "Accuracy of automated intracerebral hemorrhage volume measurement on non-contrast computed tomography: a Swedish Stroke Register cohort study". Neuroradiology, 3.11.2022. http://dx.doi.org/10.1007/s00234-022-03075-9.
Pełny tekst źródłaStreszczenie:
Abstract Purpose Hematoma volume is the strongest predictor of patient outcome after intracerebral hemorrhage (ICH). The aim of this study was to validate novel fully automated software for quantification of ICH volume on non-contrast computed tomography (CT). Methods The population was defined from the Swedish Stroke Register (RS) and included all patients with an ICH diagnosis during 2016–2019 in Region Skåne. Hemorrhage volume on their initial head CT was measured using ABC/2 and manual segmentation (Sectra IDS7 volume measurement tool) and the automated volume quantification tool (qER–NCCT) by Qure.ai. The first 500 were examined by two independent readers. Results A total of 1649 ICH patients were included. The qER–NCCT had 97% sensitivity in identifying ICH. In total, there was excellent agreement between volumetric measurements of ICH volumes by qER–NCCT and manual segmentation by interclass correlation (ICC = 0.96), and good agreement (ICC = 0.86) between qER–NCCT and ABC/2 method. The qER–NCCT showed volume underestimation, mainly in large (> 30 ml) heterogenous hemorrhages. Interrater agreement by (ICC) was 0.996 (95% CI: 0.99–1.00) for manual segmentation. Conclusion Our study showed excellent agreement in volume quantification between the fully automated software qER–NCCT and manual segmentation of ICH on NCCT. The qER–NCCT would be an important additive tool by aiding in early diagnostics and prognostication for patients with ICH and in provide volumetry on a population-wide level. Further refinement of the software should address the underestimation of ICH volume seen in a portion of large, heterogenous, irregularly shaped ICHs.
42
Chu, Yue, Gao Ma, Xiao-Quan Xu, Shan-Shan Lu, Yue-Zhou Cao, Hai-Bin Shi, Sheng Liu i Fei-Yun Wu. "Total and regional ASPECT score for non-contrast CT, CT angiography, and CT perfusion: inter-rater agreement and its association with the final infarction in acute ischemic stroke patients". Acta Radiologica, 4.07.2021, 028418512110290. http://dx.doi.org/10.1177/02841851211029080.
Pełny tekst źródłaStreszczenie:
Background Alberta Stroke Program Early Computed Tomography Score (ASPECTS) is a grading system to assess the extent and distribution of early ischemic changes. Purpose To assess inter-rater agreement for total and regional ASPECTS on non-contrast computed tomography (NCCT) images, CT angiography source images (CTA-SI), and CT-perfusion cerebral blood volume (CTP-CBV) maps, and their association with final infarction in patients with acute ischemic stroke (AIS). Material and Methods A total of 96 consecutive patients with AIS who underwent pre-treatment NCCT and CTP were retrospectively enrolled. CTA-SI was reconstructed using the raw data of CTP. Total and regional ASPECTS were assessed on baseline NCCT, CTA-SI, and CTP-CBV, and on follow-up NCCT or diffusion-weighted imaging. Follow-up ASPECTS served as the reference standard for final infarction. Results CTP-CBV demonstrated higher concordance for total ASPECTS (interclass correlation coefficient, 0.895 vs. 0.771 vs. 0.777) and regional ASPECTS in internal capsule, lentiform, caudate nuclei, M5 and M6, compared with NCCT and CTA-SI. CTP-CBV showed a trend of stronger correlation with final ASPECTS than NCCT and CTA-SI (0.717 vs. 0.711 vs. 0.565; P > 0.05). ASPECTS in the internal capsule (ρ, 0.756 vs. 0.556; P = 0.016) and caudate nucleus (ρ, 0.717 vs. 0.476; P = 0.010) on CTP-CBV were more strongly correlated with follow-up ASPECTS than NCCT. CTP-CBV showed higher accuracy for predicting final infarction in the internal capsule (92.5% vs. 90.3% and 87.1%; P > 1.000, P = 0.125, respectively) and caudate nucleus (87.1% vs. 79.6% and 77.4%; P = 0.453, P = 0.039, respectively) than CTA-SI and NCCT. Conclusion CTP-CBV ASPECTS might be more reliable for delineating early ischemic changes and predicting final infarction.
43
Payabvash, Seyedmehdi, Mushtaq H. Qureshi, Shahram Majidi i Adnan I. Qureshi. "Abstract T P34: Residual Contrast Enhancement of Middle Cerebral Artery on Non-contrast Ct (ncct) After Endovascular Treatment in Ischemic Stroke Patients". Stroke 45, suppl_1 (luty 2014). http://dx.doi.org/10.1161/str.45.suppl_1.tp34.
Pełny tekst źródłaStreszczenie:
Background: Residual contrast enhancement of cerebral arteries is frequently visualized on follow up non-contrast CT (NCCT) after endovascular treatment in acute ischemic stroke and may represent distal microvascular no-reflow phenomenon. Objective: To evaluated the prevalence of and correlation between post- endovascular treatment residual contrast enhancement of middle cerebral artery (MCA) on follow up NCCT with clinical and imaging outcomes in patients with acute ischemic stroke. Methods: We analyzed clinical and radiographic data from all patients with acute MCA occlusion who underwent endovascular treatment at two centers over a 6-year period. The M1 segment of affected MCA was selected with free-hand region of interest on the first post-angiography NCCT; and the average attenuation was determined in Hounsfield units (HU). Bivariate correlation between the MCA contrast enhancement and clinical/imaging outcome was determined. Results: A total of 89 patients (mean age ± SD, 66.4 ± 15.5 years) with MCA occlusion were included. The median time interval between the first follow up NCCT and the time of catheterization, and the time of recanalization (if successful) were 1.7 h (interquartile range: 1.2 - 2.4), and 0.8 h (interquartile range: 0.5 - 1.6), respectively. MCA contrast enhancement with an average attenuation of >40 HU was seen in 74 of 89 patients. There was no significant correlation between the average attenuation of the affected MCA on post- endovascular treatment NCCT and post- endovascular treatment “Thrombolysis in Cerebral Infarction” (TICI) score (p=0.43), Qureshi score (p=0.61), discharge National Institutes of Health Stroke Scale (NIHSS) score (p=0.34), or 3-month modified Rankin score (p=0.51). However, the MCA contrast enhancement was inversely correlated with time interval between NCCT and catheterization (p<0.001) and angiographic recanalization (p<0.001). Conclusion: In patients with acute ischemic stroke, the residual contrast enhancement of the affected MCA on NCCT post- endovascular treatment does not correlate with status of recanalization or clinical outcome.
44
Yu, Wei, Chao Xia, Bo Tao, Yuan Xiao, Ziyang Gao, Fei Zhu, Qiannan Zhao i Su Lui. "CT hyperdense lesions after endovascular therapy in acute ischemic stroke: imaging findings and clinical significance". Cerebrovascular Diseases, 21.11.2023. http://dx.doi.org/10.1159/000535369.
Pełny tekst źródłaStreszczenie:
Background The hyperdense lesion on non-contrast CT (NCCT) is a common postoperative phenomenon in acute ischemic stroke (AIS) patients who are treated with endovascular therapy (EVT). Both contrast extravasation and hemorrhagic transformation presented hyperdense lesions on NCCT, which are sometimes difficult to distinguish them. Summary of Review Radiographic findings are important for identifying contrast extravasation and hemorrhagic transformation. We recommended a standardized follow-up protocol involving imaging and clinical evaluation as it will allow neurologists and neuroradiologists to reveal the relationships between these hyperdensities and various clinical outcomes. Key Messages Dual-energy CT and susceptibility weighted imaging are capable of distinguishing contrast extravasation and hemorrhagic transformation at an early stage after EVT. However, in institutions without access to such technology, a follow-up protocol based on NCCT is crucial
45
Emde, Julia, Romy Baumgart, Niklas Langguth, Martin Juenemann i Stefan T. Gerner. "Intravenous thrombolysis in ischemic stroke patients based on non-contrast CT in the extended time-window". Frontiers in Stroke 1 (23.11.2022). http://dx.doi.org/10.3389/fstro.2022.1026138.
Pełny tekst źródłaStreszczenie:
Purpose of reviewRecent trials provided evidence for safety and efficacy of intravenous thrombolytic therapy (IVT) in ischemic stroke patients beyond the 4.5 h time-window if ischemic penumbra is present in multimodal imaging. However, advanced imaging by either Magnet Resonance Imaging (MRI) or Computed Tomography Perfusion (CTP) is not available 24/7 at most stroke-centers. Therefore, the current review addresses the use of non-contrast CT (NCCT) to identify ischemic stroke patients suitable for IVT in the unknown or extended time-window in terms of efficacy and safety.Recent findingsThe current data on NCCT based IVT strategies in ischemic stroke patients presenting in the unknown or late time-window are relatively scarce and mainly provided by small retrospective samples. One larger registry (TRUST-CT) underlines the safety and efficacy of IVT without advanced imaging with more IVT-patients reaching an excellent outcome compared to the non-IVT treated control group. Current meta-analysis provides evidence that the rate of symptomatic intracerebral hemorrhage (sICH) is similar in the wake-up and unknown onset time-window compared to the 4.5 h time-window if patients are selected by NCCT. Results of the upcoming TWIST-trial investigating Tenecteplase (TNK) for NCCT-based IVT revealed no signals regarding an increased rate of sICH, however there was no benefit regarding functional outcomes.SummarySo far, it is not well-established whether advanced imaging is indispensable and NCCT could be sufficient to identify stroke patients in the extended window who would benefit from IVT-treatment. However, current data suggests the safety of NCCT-based IVT in the extended time-window. Therefore, unavailable advanced neuroimaging should not cause delay, or even exclusion of patients from IVT and other recanalizing therapies per se.
46
Li, Qingrun, Feng Li, Hao Liu, Yan Li, Hongri Chen, Wenrui Yang, Shaofeng Duan i Hongying Zhang. "CT-based radiomics models predict spontaneous intracerebral hemorrhage expansion and are comparable with CT angiography spot sign". Frontiers in Neurology 15 (26.02.2024). http://dx.doi.org/10.3389/fneur.2024.1332509.
Pełny tekst źródłaStreszczenie:
Background and purposeThis study aimed to investigate the efficacy of radiomics, based on non-contrast computed tomography (NCCT) and computed tomography angiography (CTA) images, in predicting early hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (SICH). Additionally, the predictive performance of these models was compared with that of the established CTA spot sign.Materials and methodsA retrospective analysis was conducted using CT images from 182 patients with SICH. Data from the patients were divided into a training set (145 cases) and a testing set (37 cases) using random stratified sampling. Two radiomics models were constructed by combining quantitative features extracted from NCCT images (the NCCT model) and CTA images (the CTA model) using a logistic regression (LR) classifier. Additionally, a univariate LR model based on the CTA spot sign (the spot sign model) was established. The predictive performance of the two radiomics models and the spot sign model was compared according to the area under the receiver operating characteristic (ROC) curve (AUC).ResultsFor the training set, the AUCs of the NCCT, CTA, and spot sign models were 0.938, 0.904, and 0.726, respectively. Both the NCCT and CTA models demonstrated superior predictive performance compared to the spot sign model (all P < 0.001), with the performance of the two radiomics models being comparable (P = 0.068). For the testing set, the AUCs of the NCCT, CTA, and spot sign models were 0.925, 0.873, and 0.720, respectively, with only the NCCT model exhibiting significantly greater predictive value than the spot sign model (P = 0.041).ConclusionRadiomics models based on NCCT and CTA images effectively predicted HE in patients with SICH. The predictive performances of the NCCT and CTA models were similar, with the NCCT model outperforming the spot sign model. These findings suggest that this approach has the potential to reduce the need for CTA examinations, thereby reducing radiation exposure and the use of contrast agents in future practice for the purpose of predicting hematoma expansion.
47
Payabvash, Seyedmehdi, Mushtaq H. Qureshi, Shayaan M. Khan, Mahnoor Khan, Shahram Majidi i Adnan I. Qureshi. "Abstract W P45: Differentiation of Contrast Extravasation From Intracranial Hemorrhage on Non-Contrast CT After Endovascular Treatment in Patients With Acute Ischemic Stroke". Stroke 45, suppl_1 (luty 2014). http://dx.doi.org/10.1161/str.45.suppl_1.wp45.
Pełny tekst źródłaStreszczenie:
Background: Distinction of intracranial hemorrhage (ICH) from contrast extravasation after endovascular treatment is crucial for guiding subsequent management in patients with ischemic stroke. We evaluated the imaging characteristics that can help differentiate these two entities on post-endovascular treatment non-contrast CT (NCCT). Methods: Clinical and neuroimaging data for all patients with acute ischemic stroke who underwent endovascular treatment at two medical centers over a 6-year period were reviewed. The first post- endovascular treatment NCCT was evaluated for presence of parenchymal hyperdense lesion(s). In patients with parenchymal hyperdensity, the lesion was selected with free hand region-of-interest on the axial slice with the highest visual contrast against parenchymal background (i.e. the lesion appears brighter). ICH was defined as a hyperdensity persisting >48 hours on serial follow up CTs or confirmed by MRI study. Results: A total of 135 patients (mean age ± SD, 66.4 ± 15.6 years) were included. The median delay between angiography and the first follow up NCCT was 1.9 hours (interquartile range, 1.3 - 2.9). Of the 135 patients, 74 (55%) patients had hyperdense lesion(s) on NCCT; of whom, 20 met the definition of ICH, and 54 were contrast extravasation, which resolved on follow up CTs. A receiver operating characteristic analysis showed that the average attenuation can differentiate ICH from contrast extravasation with an area under the curve of 0.78 (p=0.01). An average attenuation of <50 Hounsfield Units (HU) was 100% specific for contrast extravasation versus ICH - which was seen in 24/54 (44%) patients with contrast extravasation. Notably, 8/61 (13%) patients with no hyperdense lesion on first follow up CT developed late-onset ICH. Conclusion: In our series, an average attenuation of <50 HU on the axial slice with highest contrast was 100% specific for differentiating contrast extravasation from ICH among patients with hyperdensity on first post-angiography NCCT.
48
Montano, Nataly, Christina Grabarits, Radhika Avadhani, Joshua N. Goldstein, W. A. Mould, Issam A. Awad, Daniel F. Hanley i Wendy Ziai. "Abstract 76: Non-Contrast CT Markers and Pre- and Post-Surgical Hematoma Expansion in the MISTIE III Trial Surgical Cohort". Stroke 51, Suppl_1 (luty 2020). http://dx.doi.org/10.1161/str.51.suppl_1.76.
Pełny tekst źródłaStreszczenie:
Introduction: A range of findings on non-contrast CT (NCCT) have been found to predict hematoma expansion after spontaneous ICH, but it is unclear whether these findings predict peri-procedural bleeding. We explored whether any specific NCCT marker(s) predict pre- or post-surgical hematoma expansion events. Methods: NCCTs were reviewed for presence of black hole sign, blend sign, swirl sign, and island sign in the surgical cohort from the MISTIE-III trial which evaluated minimally invasive surgery plus alteplase in ICH >30 mL. Hematoma expansion was defined as any expansion ≥6 mL or 33% ICH volume increase during pre-surgical period (Model 1) from diagnostic CT (DiagCT) to 24 hours post DiagCT and from stability CT (StabCT) to 24 hours post last dose of alteplase (Model 2). Blend sign was removed from analysis due to small sample size. Multivariable logistic regression analysis was performed to identify independent predictors of pre-op and post-op hematoma expansion. Results: Of 250 surgical subjects, 5 were excluded due to poor image quality. Expansion events occurred in 82 of 234 (35.0%) subjects in the pre-op interval and in 15 of 226 (7%) in the post-op interval. None of the markers were significant for pre-op expansion, but ICH volume and time from ictus to DiagCT were statistically significant predictors. Swirl sign, ICH volume, and posterior trajectory compared to lateral trajectory were independent predictors of post-op expansion events. Expansion volume pre-op and post-op were weakly associated with presence of swirl sign; Spearmans rho=0.3 p=0.065 and rho=0.60 p=0.047, respectively. Conclusion: This is the first analysis of impact of NCCT markers on re-bleeding post minimally invasive surgery from a large clinical trial. Despite an absence of association between NCCT markers and hematoma expansion in the pre-surgical period perhaps reflecting inclusion criteria for hemorrhage stability, swirl sign was associated with post-surgical rebleeding.
49
Ostman, Cecilia, Carlos Garcia-Esperon, Thomas Lillicrap, Shinya Tomari, Elizabeth Holliday, Christopher Levi, Andrew Bivard, Mark W. Parsons i Neil J. Spratt. "Multimodal Computed Tomography Increases the Detection of Posterior Fossa Strokes Compared to Brain Non-contrast Computed Tomography". Frontiers in Neurology 11 (20.11.2020). http://dx.doi.org/10.3389/fneur.2020.588064.
Pełny tekst źródłaStreszczenie:
Aims: Multimodal computed tomography (mCT) (non-contrast CT, CT angiography, and CT perfusion) is not routinely used to assess posterior fossa strokes. We described the area under the curve (AUC) of brain NCCT, WB-CTP automated core-penumbra maps and comprehensive CTP analysis (automated core-penumbra maps and all perfusion maps) for posterior fossa strokes.Methods: We included consecutive patients with signs and symptoms of posterior fossa stroke who underwent acute mCT and follow up magnetic resonance diffusion weighted imaging (DWI). Multimodal CT images were reviewed blindly and independently by two stroke neurologists and area under the receiver operating characteristic curve (AUC) was used to compare imaging modalities.Results: From January 2014 to December 2019, 83 patients presented with symptoms suggestive of posterior fossa strokes and had complete imaging suitable for inclusion (49 posterior fossa strokes and 34 DWI negative patients). For posterior fossa strokes, comprehensive CTP analysis had an AUC of 0.68 vs. 0.62 for automated core-penumbra maps and 0.55 for NCCT. For cerebellar lesions >5 mL, the AUC was 0.87, 0.81, and 0.66, respectively.Conclusion: Comprehensive CTP analysis increases the detection of posterior fossa lesions compared to NCCT and should be implemented as part of the routine imaging assessment in posterior fossa strokes.
50
Patel, Ajay, Floris H. B. M. Schreuder, Catharina J. M. Klijn, Mathias Prokop, Bram van Ginneken, Henk A. Marquering, Yvo B. W. E. M. Roos, M. Irem Baharoglu, Frederick J. A. Meijer i Rashindra Manniesing. "Intracerebral Haemorrhage Segmentation in Non-Contrast CT". Scientific Reports 9, nr 1 (28.11.2019). http://dx.doi.org/10.1038/s41598-019-54491-6.
Pełny tekst źródłaStreszczenie:
AbstractA 3-dimensional (3D) convolutional neural network is presented for the segmentation and quantification of spontaneous intracerebral haemorrhage (ICH) in non-contrast computed tomography (NCCT). The method utilises a combination of contextual information on multiple scales for fast and fully automatic dense predictions. To handle a large class imbalance present in the data, a weight map is introduced during training. The method was evaluated on two datasets of 25 and 50 patients respectively. The reference standard consisted of manual annotations for each ICH in the dataset. Quantitative analysis showed a median Dice similarity coefficient of 0.91 [0.87–0.94] and 0.90 [0.85–0.92] for the two test datasets in comparison to the reference standards. Evaluation of a separate dataset of 5 patients for the assessment of the observer variability produced a mean Dice similarity coefficient of 0.95 ± 0.02 for the inter-observer variability and 0.97 ± 0.01 for the intra-observer variability. The average prediction time for an entire volume was 104 ± 15 seconds. The results demonstrate that the method is accurate and approaches the performance of expert manual annotation.