To see the other types of publications on this topic, follow the link: LUNG PATTERN CLASSIFICATION.
Journal articles on the topic 'LUNG PATTERN CLASSIFICATION'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'LUNG PATTERN CLASSIFICATION.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Mangayarkarasi, T., R. Chithrakkannan, and R. Karthikeyan. "PATTERN KNOWLEDGE DISCOVERY BASED LUNG CANCER CLASSIFICATION SYSTEM." CARDIOMETRY, no. 26 (March 1, 2023): 623–28. http://dx.doi.org/10.18137/cardiometry.2023.26.623628.
Full textAbstract:
An accurate detection of abnormal lung nodule detection is very important for effective treatment and surgical procedure to remove the nodules. This paper introduces an efficient deep learning model to classify lung cancer in both left and right lung. It consists of three important stages; preprocessing, lung region detection and abnormal lung nodule detection. Further, a detailed discussion about the performance of the system is given using two benchmark databases; 30 lung CT images taken from the ELCAP dataset and 130 lung CT images taken from the LIDC dataset. An algorithmic framework is first created for the purpose of segmenting left and right lung region by a morphological algorithm after removing the noise by a wiener filter. A well defined deep learning architecture is designed for effective classification or detection of abnormal lung nodule detection by semantic classification. The proposed system is validated on LIDC and ELCAP database and provides an average accuracy of 97.86%.
2
Ajin, M., and L. Mredhula. "Diagnosis Of Interstitial Lung Disease By Pattern Classification." Procedia Computer Science 115 (2017): 195–208. http://dx.doi.org/10.1016/j.procs.2017.09.126.
Full text
3
Boukansa, Sara, Zineb Benbrahim, Sanaa Gamrani, Sanae Bardai, Laila Bouguenouch, Asmae Mazti, Nadia Boutahiri, et al. "Correlation of Epidermal Growth Factor Receptor Mutation With Major Histologic Subtype of Lung Adenocarcinoma According to IASLC/ATS/ERS Classification." Cancer Control 29 (January 2022): 107327482210849. http://dx.doi.org/10.1177/10732748221084930.
Full textAbstract:
Objective Our prospective study aims to define the correlation of EGFR(epidermal growth factor receptor) mutations with major histological subtypes of lung adenocarcinoma from resected and non-resected specimens, according to the WHO 2015 classification, in Moroccan North East Population. Methods Epidermal growth factor receptor mutations of 150 primary lung adenocarcinoma were performed using Real-Time PCR or SANGER sequencing. SPSS 21 was used to assess the relationship between histological subtypes of lung adenocarcinoma and EGFR mutation status. Results 25 mutations were detected in the series of 150 lung adenocarcinomas, most of which were found in cases with papillary, acinar, patterns than without these patterns and more frequently occurred in the cases without solid pattern than with this pattern. A significant correlation was observed between EGFR mutation and acinar (P = 0,024), papillary pattern (P = 0,003) and, negative association with a solid pattern (P < 0,001). In females, EGFR mutations were significantly correlated with the acinar pattern (P = 0,02), whereas in males with the papillary pattern (P = 0,01). Association between the histologic component and exon 19 deletions and exon 21 mutations were also evaluated and, we found a significant correlation between the papillary major pattern with exon 19 mutations (P = 0,004) and, ex21 with the acinar component (P = 0,03). Conclusion An analysis of resected and non-resected lung ADC specimens in 150 Moroccan Northeast patients, revealed that acinar and papillary patterns may predict the presence of a mutation in the EGFR gene. While the solid major pattern may indicate a low mutation rate of the EGFR gene.
4
SHAMSHEYEVA, ALENA, ARCOT SOWMYA, and PETER WILSON. "SEGMENTATION OF LUNG PATTERNS IN HIGH-RESOLUTION COMPUTED TOMOGRAPHY IMAGES OF THE LUNG." International Journal of Computational Intelligence and Applications 07, no. 03 (September 2008): 265–80. http://dx.doi.org/10.1142/s1469026808002259.
Full textAbstract:
An automated method is presented for segmentation of two-dimensional HRCT images of the lung into regions of four lung patterns: normal, emphysema, honeycombing, and ground-glass opacity (GGO). Segmentation was implemented in two stages. At the first stage, pixel-wise classification of the lung area was performed using local textural features extracted by the wavelet transform. At the second stage, classification results were refined by application of knowledge-based rules. Performance of the method was compared on two sets of HRCT images: one included HRCT images with characteristic examples of lung patterns and the other consisted of unselected HRCT images that represented a model of routine operations at a general radiology practice. On the first set of images, sensitivity of the method ranged from 0.92 to 0.99, and specificity ranged from 0.96 to 0.99. On the second set of images, sensitivity and specificity were, respectively, 0.49 and 0.95 for emphysema, 0.87 and 0.55 for normal, 0.34 and 0.99 for honeycombing, and 0.57 and 0.94 for GGO. The two-stage approach allowed for simple and effective application of high-level knowledge about appearance of lung patterns on HRCT images and did not require feature and region of interest size selection for the first stage of pixel-wise lung pattern classification.
5
Subramaniam, Umashankar, M. Monica Subashini, Dhafer Almakhles, Alagar Karthick, and S. Manoharan. "An Expert System for COVID-19 Infection Tracking in Lungs Using Image Processing and Deep Learning Techniques." BioMed Research International 2021 (November 13, 2021): 1–17. http://dx.doi.org/10.1155/2021/1896762.
Full textAbstract:
The proposed method introduces algorithms for the preprocessing of normal, COVID-19, and pneumonia X-ray lung images which promote the accuracy of classification when compared with raw (unprocessed) X-ray lung images. Preprocessing of an image improves the quality of an image increasing the intersection over union scores in segmentation of lungs from the X-ray images. The authors have implemented an efficient preprocessing and classification technique for respiratory disease detection. In this proposed method, the histogram of oriented gradients (HOG) algorithm, Haar transform (Haar), and local binary pattern (LBP) algorithm were applied on lung X-ray images to extract the best features and segment the left lung and right lung. The segmentation of lungs from the X-ray can improve the accuracy of results in COVID-19 detection algorithms or any machine/deep learning techniques. The segmented lungs are validated over intersection over union scores to compare the algorithms. The preprocessed X-ray image results in better accuracy in classification for all three classes (normal/COVID-19/pneumonia) than unprocessed raw images. VGGNet, AlexNet, Resnet, and the proposed deep neural network were implemented for the classification of respiratory diseases. Among these architectures, the proposed deep neural network outperformed the other models with better classification accuracy.
6
Anthimopoulos, Marios, Stergios Christodoulidis, Lukas Ebner, Andreas Christe, and Stavroula Mougiakakou. "Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network." IEEE Transactions on Medical Imaging 35, no. 5 (May 2016): 1207–16. http://dx.doi.org/10.1109/tmi.2016.2535865.
Full text
7
Ummay Atiya, S., and N. V.K Ramesh. "Pattern classification of interstitial lung disease in high resolution clinical datasets: A systematic review." International Journal of Engineering & Technology 7, no. 2.7 (March 18, 2018): 114. http://dx.doi.org/10.14419/ijet.v7i2.7.10275.
Full textAbstract:
Automated tissues characterization helps to diagnosis the various diseases including Interstitial lung diseases (ILD). The various features and the several classifiers are used in categorize the different layers depend on the pattern presented in the image. The different types of diseases may occur in the lungs and some of the diseases happen to leave the scars. These scars can be found in the High Resolution Computed Tomography (HRCT) and have different pattern. The different diseases cause the different pattern in the images and these is classified using the efficient classifier that helps to diagnosis the diseases. In this paper, review for the many researches regarding to the classification of the different pattern from the Computed Tomography (CT) images is presented. The evaluation of the efficiency of the methods in terms of classifier and database used for the research is made. The Deep Convolution Neural Network (CNN) provides the promising classifier efficiency compared to the other researches for different pattern. In general, there are five types of pattern is classified: Healthy, ground glass, honeycomb, Fibrosis, and emphysema.
8
Raparia, Kirtee, and Rishi Raj. "Tissue Continues to Be the Issue: Role of Histopathology in the Context of Recent Updates in the Radiologic Classification of Interstitial Lung Diseases." Archives of Pathology & Laboratory Medicine 143, no. 1 (January 1, 2019): 30–33. http://dx.doi.org/10.5858/arpa.2018-0134-ra.
Full textAbstract:
Context.— High-resolution computed tomography (HRCT) imaging has an increasingly important role in clinical decision-making in patients with interstitial lung diseases. The recent Fleischner Society white paper on the diagnostic criteria for idiopathic pulmonary fibrosis highlights the advances in our understanding of HRCT imaging in interstitial lung diseases. Objective.— To discuss the evidence and recommendations outlined in the white paper as it pertains to the radiologic diagnosis of interstitial lung disease, specifically highlighting the current limitations of HRCT in confidently predicting histopathologic findings. Data Sources.— The recent Fleischner Society white paper and other studies pertaining to the role of HRCT in predicting histopathology in interstitial lung diseases are reviewed. Conclusions.— High-resolution computed tomography is highly predictive of a usual interstitial pneumonia (UIP) pattern on histopathology when the HRCT shows a typical UIP pattern on a “confident” read by the radiologist. A probable UIP pattern is also very predictive of a UIP pattern on histopathology, and histopathologic confirmation is not needed for most patients demonstrating this pattern in the appropriate clinical setting. A UIP pattern may be seen in a substantial proportion of patients with an “indeterminate UIP” pattern on HRCT and in many patients for whom the HRCT suggests an alternative diagnosis; histopathologic confirmation should be considered in patients demonstrating these patterns whenever feasible.
9
Khoiro, M., R. A. Firdaus, E. Suaebah, M. Yantidewi, and Dzulkiflih. "Segmentation Effect on Lungs X-Ray Image Classification Using Convolution Neural Network." Journal of Physics: Conference Series 2392, no. 1 (December 1, 2022): 012024. http://dx.doi.org/10.1088/1742-6596/2392/1/012024.
Full textAbstract:
Abstract The effect of segmentation on lung X-ray image classification has been analyzed in this study. The 150 lung x-ray images in this study were separated into 78 as training data, 30 as validation data, and 42 as testing in three categories: normal lungs, effusion lungs, and cancer lungs. In pre-processing, the images were modified by adaptive histogram equalization to improve image quality and increase image contrast. The segmentation aims to mark the image by contouring the lung area obtained from the thresholding and some morphological manipulation processes such as filling holes, area openings, and labelling. Image classification uses Convolutional Neural Network (CNN) with five convolution layers, an Adam optimizer, and 30 epochs. The segmentation effect is analyzed by comparing the classification performance of the segmented and unsegmented images. In the study, the unsegmented X-ray image dataset classification reached an overall accuracy of 59.52% in the network testing process. The segmented X-ray image dataset obtained greater accuracy, 73.81%. It indicated that the segmentation process could improve network performance because the input pattern of the segmented image is easier to classify. Furthermore, the segmentation technique in the study can be one of the alternatives to developing image classification technologies, especially for medical image diagnosis. Segmentation Effect on Lungs X-Ray Image Classification Using Convolution Neural Network.
10
Vasconcelos, Verónica, João Barroso, Luis Marques, and José Silvestre Silva. "Enhanced Classification of Interstitial Lung Disease Patterns in HRCT Images Using Differential Lacunarity." BioMed Research International 2015 (2015): 1–9. http://dx.doi.org/10.1155/2015/672520.
Full textAbstract:
The analysis and interpretation of high-resolution computed tomography (HRCT) images of the chest in the presence of interstitial lung disease (ILD) is a time-consuming task which requires experience. In this paper, a computer-aided diagnosis (CAD) scheme is proposed to assist radiologists in the differentiation of lung patterns associated with ILD and healthy lung parenchyma. Regions of interest were described by a set of texture attributes extracted using differential lacunarity (DLac) and classical methods of statistical texture analysis. The proposed strategy to compute DLac allowed a multiscale texture analysis, while maintaining sensitivity to small details. Support Vector Machines were employed to distinguish between lung patterns. Training and model selection were performed over a stratified 10-fold cross-validation (CV). Dimensional reduction was made based on stepwise regression (F-test,pvalue < 0.01) during CV. An accuracy of 95.8 ± 2.2% in the differentiation of normal lung pattern from ILD patterns and an overall accuracy of 94.5 ± 2.1% in a multiclass scenario revealed the potential of the proposed CAD in clinical practice. Experimental results showed that the performance of the CAD was improved by combining multiscale DLac with classical statistical texture analysis.
11
Hung, Jung-Jyh, Yi-Chen Yeh, Wen-Juei Jeng, Kou-Juey Wu, Biing-Shiun Huang, Yu-Chung Wu, Teh-Ying Chou, and Wen-Hu Hsu. "Predictive Value of the International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society Classification of Lung Adenocarcinoma in Tumor Recurrence and Patient Survival." Journal of Clinical Oncology 32, no. 22 (August 1, 2014): 2357–64. http://dx.doi.org/10.1200/jco.2013.50.1049.
Full textAbstract:
Purpose This study investigated the pattern of recurrence of lung adenocarcinoma and the predictive value of histologic classification in resected lung adenocarcinoma using the new International Association for the Study of Lung Cancer (IASLC)/American Thoracic Society (ATS)/European Respiratory Society (ERS) classification system. Patients and Methods Histologic classification of 573 patients undergoing resection for lung adenocarcinoma was determined according to the IASLC/ATS/ERS classification system, and the percentage of each histologic component (lepidic, acinar, papillary, micropapillary, and solid) was recorded. The pattern of recurrence of those components and their predictive value were investigated. Results The predominant histologic pattern was significantly associated with sex (P < .01), invasive tumor size (P < .01), T status (P < .01), N status (P < .01), TNM stage (P < .01), and visceral pleural invasion (P < .01). The percentage of recurrence was significantly higher in micropapillary- and solid-predominant adenocarcinomas (P < .01). Micropapillary- and solid-predominant adenocarcinomas had a significantly higher possibility of developing initial extrathoracic-only recurrence than other types (P < .01). The predominant pattern group (micropapillary or solid v lepidic, acinar, or papillary) was a significant prognostic factor in overall survival (OS; P < .01), probability of freedom from recurrence (P < .01), and disease-specific survival (P < .01) in multivariable analysis. For patients receiving adjuvant chemotherapy, solid-predominant adenocarcinoma was a significant predictor for poor OS (P = .04). Conclusion In lung adenocarcinoma, the IASLC/ATS/ERS classification system has significant prognostic and predictive value regarding death and recurrence. Solid-predominant adenocarcinoma was also a significant predictor in patients undergoing adjuvant chemotherapy. Prognostic and predictive information is important for stratifying patients for aggressive adjuvant chemoradiotherapy.
12
Hamdan, Hussein, and Umar Alqasemi. "Classification of Lungs Images for Detecting Nodules using Machine Learning." Signal & Image Processing : An International Journal 13, no. 6 (December 30, 2022): 01–09. http://dx.doi.org/10.5121/sipij.2022.13601.
Full textAbstract:
Lung nodules are tiny lumps of tissue that are common in the lungs. The nodule may be benign or malignant; malignant nodules are cancerous and can grow rapidly. For a long time, X-ray images of the chest have been utilized to diagnose lung cancer. We developed in this paper a computer aid diagnosis system (CAD) to atomically classify a set of lung x-ray images into normal and abnormal (with nodule and no-nodule) cases. We used 180 images in this work, the images are in full size no filtering or segmenting process were applied, 75 of them are for normal cases and the other 105 are for abnormal cases, at the same time 120 of the images have been used to train the classifier and 60 for testing. Our classifiers were fed with a variety of features, including LBP (local binary pattern) and statistical features. And a classifier was able to identify cases with nodule from cases without nodule with an accuracy (ACC) of 86.7%.
13
Correa, Malena, Mirko Zimic, Franklin Barrientos, Ronald Barrientos, Avid Román-Gonzalez, Mónica J. Pajuelo, Cynthia Anticona, et al. "Automatic classification of pediatric pneumonia based on lung ultrasound pattern recognition." PLOS ONE 13, no. 12 (December 5, 2018): e0206410. http://dx.doi.org/10.1371/journal.pone.0206410.
Full text
14
Nezamabadi, Kasra, Zeinab Naseri, Hamid Abrishami Moghaddam, Mohammadreza Modarresi, Neda Pak, and Mehrzad Mahdizade. "Lung HRCT pattern classification for cystic fibrosis using convolutional neural network." Signal, Image and Video Processing 13, no. 6 (April 11, 2019): 1225–32. http://dx.doi.org/10.1007/s11760-019-01447-y.
Full text
15
Mao, Keming, and Zhuofu Deng. "Lung Nodule Image Classification Based on Local Difference Pattern and Combined Classifier." Computational and Mathematical Methods in Medicine 2016 (2016): 1–7. http://dx.doi.org/10.1155/2016/1091279.
Full textAbstract:
This paper proposes a novel lung nodule classification method for low-dose CT images. The method includes two stages. First, Local Difference Pattern (LDP) is proposed to encode the feature representation, which is extracted by comparing intensity difference along circular regions centered at the lung nodule. Then, the single-center classifier is trained based on LDP. Due to the diversity of feature distribution for different class, the training images are further clustered into multiple cores and the multicenter classifier is constructed. The two classifiers are combined to make the final decision. Experimental results on public dataset show the superior performance of LDP and the combined classifier.
16
Petersen, Iver, and Simone Petersen. "Towards a Genetic-Based Classification of Human Lung Cancer." Analytical Cellular Pathology 22, no. 3 (2001): 111–21. http://dx.doi.org/10.1155/2001/374304.
Full textAbstract:
Lung cancer is a highly aggressive neoplasm which is reflected by a multitude of genetic aberrations being detectable on the chromosomal and molecular level. In order to understand this seemingly genetic chaos, we performed Comparative Genomic Hybridisation (CGH) in a large collective of human lung carcinomas investigating different tumor entities as well as multiple individual tumour specimens of single patients. Despite the considerable genetic instability being reflected by the well known morphological heterogeneity of lung cancer the comparison of different tumour groups using custom made computer software revealed recurrent aberration patterns and highlighted chromosomal imbalances that were significantly associated with morphological histotypes and biological phenotypes. Specifically we identified imbalances in NSCLC being associated with metastasis formation which are typically present in SCLC thus explaining why the latter is such an aggressive neoplasm characterized by widespread tumor dissemination. Based on the genetic data a new model for the development of SCLC is presented. It suggests that SCLC evolving from the same stem cell as NSCLC should be differentiated into primary and secondary tumors. Primary SCLC corresponding to the classical type evolved directly from an epithelial precursor cell. In contrast, secondary SCLC correlating with the combined SCLC develops via an NSCLC intermediate. In addition, we established libraries of differentially expressed genes from different human lung cancer types to identify new candidate genes for several of the chromosomal subregions identified by CGH. In this review, we summarise the status of our results aiming at a refined classification of lung cancer based on the pattern of genetic aberrations.
17
Rajalingam, Bavaharan, Ethirajan Narayanan, Praveen Nirmalan, Kamalanthan Muthukrishnan, Vivek Sundaram, Saravanan Kumaravelu, Mukundhan Gopalan, et al. "Pattern recognition of high-resolution computer tomography (HRCT) chest to guide clinical management in patients with mild to moderate COVID-19." Indian Journal of Radiology and Imaging 31, S 01 (January 2021): S110—S118. http://dx.doi.org/10.4103/ijri.ijri_774_20.
Full textAbstract:
Abstract Aim: To describe the distribution of lung patterns determined by High Resolution Computed Tomography (HRCT) in COVID patients with mild and moderate lung involvement and outcomes after early identification and management with steroids and anticoagulants. Material and Methods: A cross sectional study of COVID-19 patients with mild and moderate lung involvement presenting at 5 healthcare centres in Trichy district of South TamilNadu in India. Patients underwent HRCT to assess patterns and severity of lung involvement, Inflammatory markers (LDH/Ferritin) and D-Dimer assay and clinical correlation with signs and symptoms. Patients were assessed for oxygen, steroid and anticoagulant therapy, clinical recovery or progression on follow up and details on mortality were collected. The RSNA, Fleischer Society guidelines and CORADS score was used for radiological reporting. New potential classification of patterns of percentage of lung parenchyma involvement in Covid patients is being suggested. Results: The study included 7,340 patients with suspected COVID and 3,963 (53.9%) patients had lung involvement based on HRCT. RT PCR was positive in 74.1% of the CT Positive cases. Crazy Pavement pattern was predominant (n = 2022, 51.0%) and Ground Glass Opacity (GGO) was found in 1,941 (49.0%) patients in the study. Severe lung involvement was more common in the Crazy Pavement pattern. Patients with GGO in moderate lung involvement were significantly more likely to recover faster compared to Crazy Pavement pattern (P value <0.001). Conclusion: HRCT chest and assessment of lung patterns can help triage patients to home quarantine and hospital admission. Early initiation of steroids and anticoagulants based on lung patterns can prevent progression to more severe stages and aid early recovery. HRCT can play a major role to triage and guide management especially as RT PCR testing and results are delayed for the benefit of patients and in a social cause to decrease the spread of the virus
18
Yan, Jian-Jun, Rui Guo, Yi-Qin Wang, Guo-Ping Liu, Hai-Xia Yan, Chun-Ming Xia, and Xiaojing Shen. "Objective Auscultation of TCM Based on Wavelet Packet Fractal Dimension and Support Vector Machine." Evidence-Based Complementary and Alternative Medicine 2014 (2014): 1–11. http://dx.doi.org/10.1155/2014/502348.
Full textAbstract:
This study was conducted to illustrate that auscultation features based on the fractal dimension combined with wavelet packet transform (WPT) were conducive to the identification the pattern of syndromes of Traditional Chinese Medicine (TCM). The WPT and the fractal dimension were employed to extract features of auscultation signals of 137 patients with lung Qi-deficient pattern, 49 patients with lung Yin-deficient pattern, and 43 healthy subjects. With these features, the classification model was constructed based on multiclass support vector machine (SVM). When all auscultation signals were trained by SVM to decide the patterns of TCM syndromes, the overall recognition rate of model was 79.49%; when male and female auscultation signals were trained, respectively, to decide the patterns, the overall recognition rate of model reached 86.05%. The results showed that the methods proposed in this paper were effective to analyze auscultation signals, and the performance of model can be greatly improved when the distinction of gender was considered.
19
Huang, Sheng, Feifei Lee, Ran Miao, Qin Si, Chaowen Lu, and Qiu Chen. "A deep convolutional neural network architecture for interstitial lung disease pattern classification." Medical & Biological Engineering & Computing 58, no. 4 (January 22, 2020): 725–37. http://dx.doi.org/10.1007/s11517-019-02111-w.
Full text
20
Devdatt Kawathekar, Ishan, and Anu Shaju Areeckal. "Performance analysis of texture characterization techniques for lung nodule classification." Journal of Physics: Conference Series 2161, no. 1 (January 1, 2022): 012045. http://dx.doi.org/10.1088/1742-6596/2161/1/012045.
Full textAbstract:
Abstract Lung cancer ranks very high on a global index for cancer-related casualties. With early detection of lung cancer, the rate of survival increases to 80-90%. The standard method for diagnosing lung cancer from Computed Tomography (CT) scans is by manual annotation and detection of the cancerous regions, which is a tedious task for radiologists. This paper proposes a machine learning approach for multi-class classification of the lung nodules into solid, semi-solid, and Ground Glass Object texture classes. We employ feature extraction techniques, such as gray-level co-occurrence matrix, Gabor filters, and local binary pattern, and validate the performance on the LNDb dataset. The best performing classifier displays an accuracy of 94% and an F1-score of 0.92. The proposed approach was compared with related work using the same dataset. The results are promising, and the proposed method can be used to diagnose lung cancer accurately.
21
Prasad, Mithun, Arcot Sowmya, and Peter Wilson. "Multi-level classification of emphysema in HRCT lung images." Pattern Analysis and Applications 12, no. 1 (November 6, 2007): 9–20. http://dx.doi.org/10.1007/s10044-007-0093-7.
Full text
22
Saleh, Abdulrazak Yahya, Chee Ka Chin, Vanessa Penshie, and Hamada Rasheed Hassan Al-Absi. "Lung cancer medical images classification using hybrid CNN-SVM." International Journal of Advances in Intelligent Informatics 7, no. 2 (July 30, 2021): 151. http://dx.doi.org/10.26555/ijain.v7i2.317.
Full textAbstract:
Lung cancer is one of the leading causes of death worldwide. Early detection of this disease increases the chances of survival. Computer-Aided Detection (CAD) has been used to process CT images of the lung to determine whether an image has traces of cancer. This paper presents an image classification method based on the hybrid Convolutional Neural Network (CNN) algorithm and Support Vector Machine (SVM). This algorithm is capable of automatically classifying and analyzing each lung image to check if there is any presence of cancer cells or not. CNN is easier to train and has fewer parameters compared to a fully connected network with the same number of hidden units. Moreover, SVM has been utilized to eliminate useless information that affects accuracy negatively. In recent years, Convolutional Neural Networks (CNNs) have achieved excellent performance in many computer visions tasks. In this study, the performance of this algorithm is evaluated, and the results indicated that our proposed CNN-SVM algorithm has been succeed in classifying lung images with 97.91% accuracy. This has shown the method's merit and its ability to classify lung cancer in CT images accurately.
23
Santana Peralta, J., R. A. Alvarez Santana, D. Garcia, L. Perez, T. Polanco Mora, L. Concepción Sanchez, I. Paulino, et al. "AB1555 CORRELATION BETWEEN HIGH RESOLUTION CHEST TOMOGRAPHY AND CAPILLAROSCOPIC FINDINGS IN SYSTEMIC SCLEROSIS." Annals of the Rheumatic Diseases 82, Suppl 1 (May 30, 2023): 2011.2–2012. http://dx.doi.org/10.1136/annrheumdis-2023-eular.4674.
Full textAbstract:
BackgroundSystemic sclerosis (SSc) is a chronic autoimmune multisystemic disease characterized by fibrosis and vasculopathy.[1]Mortality in patients with systemic sclerosis who present with interstitial lung disease can be up to 3x healthy population.[2]It is estimated that 70-90% have interstitial lung disease.[3]High resolution computed tomography (HRCT) of chest is recognized as a sensitive imaging method for evaluating pulmonary involvement.[4,5]Presentation patterns are also described: NSIP (non specific interstitial pneumonia), UIP (usual interstitial pneumonia), COP (cryptogenic organizing pneumonia), LIP (Lymphocytic interstitial pneumonitis). Capillaroscopy allows the study of the microcirculation. Changes are classified into “early,” “active,” and “late” scleroderma patterns.[6]ObjectivesTo relate between high resolution chest tomography and capillaroscopic findings in Systemic sclerosis.MethodsDescriptive, observational, cross-sectional study. Capillaroscopy with Optilia CapiScope 2.0/5.0MP and lung ultrasound with Siemmens Acuson X150 were performed in patients with SSc in the outpatient clinic of the rheumatology service from August-November 2021. Inclusion criteria: > 18 years old, meet criteria for classification of SSc according to ACR/EULAR 2013. Exclusion criteria: history of pre-existing lung disease.Results22 patients met inclusion criteria. 80% were female. Diffuse SSc 81.8% (18), limited SSc 18.2% (4). Mean age 54±17 years, disease duration 58.1% (13) >5 years and 40.9% (9) < 5 years, mean diagnosis 15.3±9.2 years, mean mRSS 19.4 + 13.2 mRSS Mild: 22.7% (5), moderate 18.2% (4), severe 27.3% (6), terminal 31.8% (7). ANA+ 45.5% (10), Topo IA 18.2% (4). Treatment: RTX 77.3% (17), Ca+ antagonists 68.2% (15), Bosentan 36.4% (8), MMF 36.4% (8), Colchicine 31.8% (7), Sildenafil 27.3% (6). Capillaroscopy: normal pattern 59% (13), early scleroderma pattern 9.1% (2), active scleroderma pattern 4.5% (1), late scleroderma pattern 22.7% (5), nonspecific abnormalities 4.5% (1). TACAR: 54.5% (12) normal, pathological findings 45.4% (10): NSIP pattern 80% (8), UIP 20% (2). TACAR/Capillaroscopy correlation: UIP pattern and early scleroderma pattern 4.5% (1) rp=.112, NSIP pattern and active scleroderma pattern 4.5% (1) rp=.769, NSIP pattern and normal capillaroscopy 4.5% (1) rp=. 518, NSIP pattern and late scleroderma pattern 27.2% (6) rp=1, normal TACAR and capillaroscopy with nonspecific abnormalities 4.5% (1) rp=1, UIP pattern and early pattern 4.5% (1) rp=.622, normal TACAR and normal capillaroscopy 27.2% (6).ConclusionWe found in this study that capillaroscopic findings of active and late patterns correlated with greater pulmonary involvement. It is recommended to follow patients with early patterns and the existence or not of interstitial pattern and to evaluate response to medication.References[1]Morrisroe K, Stevens W, Sahhar J. The clinical and economic burden of systemic sclerosis related interstitial lung disease. Rheumatology. 2019;0(1):1-11.[2]Volkmann E, Tashkin D, Sim M, Kim G, Goldin J, Clements P. Determining progression of scleroderma-related interstitial lung disease. Journal of Scleroderma and Related Disorders. 2018;4(1):62-70.[3]Simeón-Aznar C, Fonollosa-Plá V, et al. Registry of the Spanish Network forSystemic Sclerosis. Medicine. 2015;94(43):e1728.[4]Hussein, K., Shaaban, L. and Mohamed, E., 2016. Correlation of high resolution CT patterns with pulmonary function tests in patients with interstitial lung diseases. Egyptian Journal of Chest Diseases and Tuberculosis, 65(3), pp.681- 688.[5]Chung JH, Walker CM, Hobbs S. Imaging Features of Systemic Sclerosis- Associated Interstitial Lung Disease. J Vis Exp. 2020[6]Man, M., Dantes, E., Domokos Hancu, B., Bondor, C., Ruscovan, A., Parau, A., Motoc, N. and Marc, M., 2019. Correlation between Transthoracic Lung Ultrasound Score and HRCT Features in Patients with Interstitial Lung Diseases. Journal of Clinical Medicine, 8(8), p.1199.Acknowledgements:NIL.Disclosure of InterestsNone Declared.
24
Wang, Liang, Xing Wang, Miao Huang, Shi Yan, Shaolei Li, Chao Lv, Nan Wu, and Yue Yang. "High-risk-pattern lung adenocarcinoma with epidermal growth factor receptor mutation is associated with distant metastasis risk and may benefit from adjuvant targeted therapy." Interactive CardioVascular and Thoracic Surgery 33, no. 3 (April 21, 2021): 395–401. http://dx.doi.org/10.1093/icvts/ivab099.
Full textAbstract:
Abstract OBJECTIVES This study aimed to evaluate the value of the high-risk-pattern histology (micropapillary and solid components) for predicting distant metastasis in lung adenocarcinoma and to determine the survival benefit with adjuvant targeted therapy for resected non-small cell lung cancer with high-risk-pattern histology. METHODS Patients receiving surgery for non-small cell lung cancer were included in this retrospective study. Histological classification was performed according to 2015 World Health Organization classification. Tumours with micropapillary and solid components were defined as high-risk-pattern tumours. Univariable and multivariable Cox regression analyses were used for survival analysis. Adjuvant targeted therapy was alternative for patients with epidermal growth factor receptor (EGFR)-mutation and refusing adjuvant chemotherapy, and outcome was evaluated between 2 groups. RESULTS The 514 patients (78 in high-risk group and 436 in low-risk group) were followed up for a median of 64 months. High-risk-pattern adenocarcinoma was significantly more common in male patients (P < 0.001) and in smokers (P < 0.001). Among patients with EGFR mutation (n = 164), the high-risk pattern was significantly associated with distant metastasis (P = 0.028) including brain metastasis (P = 0.022). In the 42 patients with high-risk pattern plus EGFR mutation, survival was significantly better after treatment with adjuvant targeted therapy than with chemotherapy (5-year overall survival: 56.4 ± 2.6 vs 44.7 ± 3.7 months, P = 0.011; 5-year disease-free survival: 54.0 ± 3.3 vs 41.9 ± 4.5 months, P = 0.006). CONCLUSIONS High-risk pattern is associated with distant metastasis in non-small cell lung cancer after surgery. Adjuvant targeted therapy may be superior to chemotherapy for treatment of patients with high-risk pattern and EGFR mutation.
25
Bortoluzzi, Eduarda M., Paige H. Schmidt, Rachel E. Brown, Makenna Jensen, Madeline R. Mancke, Robert L. Larson, Phillip A. Lancaster, and Brad J. White. "Image Classification and Automated Machine Learning to Classify Lung Pathologies in Deceased Feedlot Cattle." Veterinary Sciences 10, no. 2 (February 3, 2023): 113. http://dx.doi.org/10.3390/vetsci10020113.
Full textAbstract:
Bovine respiratory disease (BRD) and acute interstitial pneumonia (AIP) are the main reported respiratory syndromes (RSs) causing significant morbidity and mortality in feedlot cattle. Recently, bronchopneumonia with an interstitial pattern (BIP) was described as a concerning emerging feedlot lung disease. Necropsies are imperative to assist lung disease diagnosis and pinpoint feedlot management sectors that require improvement. However, necropsies can be logistically challenging due to location and veterinarians’ time constraints. Technology advances allow image collection for veterinarians’ asynchronous evaluation, thereby reducing challenges. This study’s goal was to develop image classification models using machine learning to determine RS diagnostic accuracy in right lateral necropsied feedlot cattle lungs. Unaltered and cropped lung images were labeled using gross and histopathology diagnoses generating four datasets: unaltered lung images labeled with gross diagnoses, unaltered lung images labeled with histopathological diagnoses, cropped images labeled with gross diagnoses, and cropped images labeled with histopathological diagnoses. Datasets were exported to create image classification models, and a best trial was selected for each model based on accuracy. Gross diagnoses accuracies ranged from 39 to 41% for unaltered and cropped images. Labeling images with histopathology diagnoses did not improve average accuracies; 34–38% for unaltered and cropped images. Moderately high sensitivities were attained for BIP (60–100%) and BRD (20–69%) compared to AIP (0–23%). The models developed still require fine-tuning; however, they are the first step towards assisting veterinarians’ lung diseases diagnostics in field necropsies.
26
Warth, Arne, Thomas Muley, Michael Meister, Albrecht Stenzinger, Michael Thomas, Peter Schirmacher, Philipp A. Schnabel, Jan Budczies, Hans Hoffmann, and Wilko Weichert. "The Novel Histologic International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society Classification System of Lung Adenocarcinoma Is a Stage-Independent Predictor of Survival." Journal of Clinical Oncology 30, no. 13 (May 1, 2012): 1438–46. http://dx.doi.org/10.1200/jco.2011.37.2185.
Full textAbstract:
Purpose Our aim was to analyze and validate the prognostic impact of the novel International Association for the Study of Lung Cancer (IASLC)/American Thoracic Society (ATS)/European Respiratory Society (ERS) proposal for an architectural classification of invasive pulmonary adenocarcinomas (ADCs) across all tumor stages. Patients and Methods The architectural pattern of a large cohort of 500 patients with resected ADCs (stages I to IV) was retrospectively analyzed in 5% increments and classified according to their predominant architecture (lepidic, acinar, solid, papillary, or micropapillary), as proposed by the IASLC/ATS/ERS. Subsequently, histomorphologic data were correlated with clinical data, adjuvant therapy, and patient outcome. Results Overall survival differed significantly between lepidic (78.5 months), acinar (67.3 months), solid (58.1 months), papillary (48.9 months), and micropapillary (44.9 months) predominant ADCs (P = .007). When patterns were lumped into groups, this resulted in even more pronounced differences in survival (pattern group 1, 78.5 months; group 2, 67.3 months; group 3, 57.2 months; P = .001). Comparable differences were observed for overall, disease-specific, and disease-free survival. Pattern and pattern groups were stage- and therapy-independent prognosticators for all three survival parameters. Survival differences according to patterns were influenced by adjuvant chemoradiotherapy; in particular, solid-predominant tumors had an improved prognosis with adjuvant radiotherapy. The predominant pattern was tightly linked to the risk of developing nodal metastases (P < .001). Conclusion Besides all recent molecular progress, architectural grading of pulmonary ADCs according to the novel IASLC/ATS/ERS scheme is a rapid, straightforward, and efficient discriminator for patient prognosis and may support patient stratification for adjuvant chemoradiotherapy. It should be part of an integrated clinical, morphologic, and molecular subtyping to further improve ADC treatment.
27
Travis, William D., Elisabeth Brambilla, and Gregory J. Riely. "New Pathologic Classification of Lung Cancer: Relevance for Clinical Practice and Clinical Trials." Journal of Clinical Oncology 31, no. 8 (March 10, 2013): 992–1001. http://dx.doi.org/10.1200/jco.2012.46.9270.
Full textAbstract:
We summarize significant changes in pathologic classification of lung cancer resulting from the 2011 International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society (IASLC/ATS/ERS) lung adenocarcinoma classification. The classification was developed by an international core panel of experts representing IASLC, ATS, and ERS with oncologists/pulmonologists, pathologists, radiologists, molecular biologists, and thoracic surgeons. Because 70% of patients with lung cancer present with advanced stages, a new approach to small biopsies and cytology with specific terminology and criteria focused on the need for distinguishing squamous cell carcinoma from adenocarcinoma and on molecular testing for EGFR mutations and ALK rearrangement. Tumors previously classified as non–small-cell carcinoma, not otherwise specified, because of the lack of clear squamous or adenocarcinoma morphology should be classified further by using a limited immunohistochemical workup to preserve tissue for molecular testing. The terms “bronchioloalveolar carcinoma” and “mixed subtype adenocarcinoma” have been discontinued. For resected adenocarcinomas, new concepts of adenocarcinoma in situ and minimally invasive adenocarcinoma define patients who, if they undergo complete resection, will have 100% disease-free survival. Invasive adenocarcinomas are now classified by predominant pattern after using comprehensive histologic subtyping with lepidic, acinar, papillary, and solid patterns; micropapillary is added as a new histologic subtype with poor prognosis. Former mucinous bronchioloalveolar carcinomas are now called “invasive mucinous adenocarcinoma.” Because the lung cancer field is now rapidly evolving with new advances occurring on a frequent basis, particularly in the molecular arena, this classification provides a much needed standard for pathologic diagnosis not only for patient care but also for clinical trials and TNM classification.
28
Onozato, Maristela L., Veronica E. Klepeis, Yukako Yagi, and Mari Mino-Kenudson. "A Role of Three-Dimensional (3D)-Reconstruction in the Classification of Lung Adenocarcinoma." Analytical Cellular Pathology 35, no. 2 (2012): 79–84. http://dx.doi.org/10.1155/2012/684751.
Full textAbstract:
Background: Three-dimensional (3D)-reconstruction from paraffin embedded sections has been considered laborious and time-consuming. However, the high-resolution images of large object areas and different fields of view obtained by 3D-reconstruction make one wonder whether it can add a new insight into lung adenocarcinoma, the most frequent histology type of lung cancer characterized by its morphological heterogeneity.Objective: In this work, we tested whether an automated tissue sectioning machine and slide scanning system could generate precise 3D-reconstruction of microanatomy of the lung and help us better understand and define histologic subtypes of lung adenocarcinoma.Methods: Four formalin-fixed human lung adenocarcinoma resections were studied. Paraffin embedded tissues were sectioned with Kurabo-Automated tissue sectioning machine and serial sections were automatically stained and scanned with a Whole Slide Imaging system. The resulting stacks of images were 3D reconstructed by Pannoramic Viewer software.Results: Two of the four specimens contained islands of tumor cells detached in alveolar spaces that had not been described in any of the existing adenocarcinoma classifications. 3D-reconstruction revealed the details of spatial distribution and structural interaction of the tumor that could hardly be observed by 2D light microscopy studies. The islands of tumor cells extended into a deeper aspect of the tissue, and were interconnected with each other and with the main tumor with a solid pattern that was surrounded by the islands. The finding raises the question whether the islands of tumor cells should be classified into a solid pattern in the current classification.Conclusion: The combination of new technologies enabled us to build an effective 3D-reconstruction of resected lung adenocarcinomas. 3D-reconstruction may help us refine the classification of lung adenocarcinoma by adding detailed spatial/structural information to 2D light microscopy evaluation.
29
Asai, Nobuhiro, Eisuke Katsuda, Rie Hamanaka, Kenshi Kosaka, Ayako Matsubara, Masaki Nishimura, Hiroyuki Tanaka, et al. "The ATS/ERS/JRS/ALAT Statement “IPF by HRCT” could Predict Acute Exacerbation of Interstitial Lung Disease in Non-small Cell Lung Cancer." Tumori Journal 103, no. 1 (October 22, 2016): 60–65. http://dx.doi.org/10.5301/tj.5000574.
Full textAbstract:
Introduction Patients with non-small cell lung cancer (NSCLC) and interstitial lung disease (ILD) are at high risk of acute exacerbation of ILD (AE-ILD) when treated with systemic chemotherapy. Standard treatment for NSCLC complicated by ILD has not been established. Purpose and methods To examine whether the type of ILD categorized by the official ATS/ERS/JRS/ALAT statement as “idiopathic pulmonary fibrosis (IPF) by high-resolution computed tomography (HRCT)” could predict chemotherapy-induced AE-ILD in NSCLC patients with ILD, we retrospectively reviewed all patients with NSCLC complicated by ILD who had received chemotherapy at our institute from January 2007 until December 2013. Patients’ characteristics, pathology and clinical staging of lung cancer, chemotherapy, type of ILD and AE-ILD during chemotherapy were evaluated. ILD was classified according to the statement as follows: usual interstitial pneumonia (UIP), possible UIP, and inconsistent with a UIP pattern. Results A total of 46 patients had pre-existing ILD and received chemotherapy. The mean age was 73 years (range 46-83 years). Fifteen (32.6%) of 46 patients with ILD developed chemotherapy-induced AE-ILD, which was seen more frequently in patients with ILD with a UIP pattern or possible UIP pattern than in patients with a pattern inconsistent with UIP (80% versus 9.7%, p<0.001). Multivariate analyses including age, sex, performance status and radiographic patterns of ILD showed that the presence of a UIP or possible UIP pattern was an independent risk factor for chemotherapy-induced AE-ILD. Conclusions ILD with a UIP pattern or possible UIP pattern by the classification could be a risk factor for AE-ILD in NSCLC patients with ILD.
30
Et al., Dr S. Gnanavel. "Identification and Classification of Lung Nodules Using Neural Networks." Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 6 (April 5, 2021): 1956–61. http://dx.doi.org/10.17762/turcomat.v12i6.4799.
Full textAbstract:
Lung cancer is a serious health concern, which is also one of the major types of cancer that has a profound impact on the overall cancer mortality rates. The detection of lung cancer nodules is quite a challenge as the major challenge is the structure of the cancer nodules; here the cells are imbricated with each other. The prediction and classification of lung cancer is done by applying digital image processing techniques to the acquired input images of the nodules. This methodology also aids early detection which in turns reduces the criticality of the condition and provides scope for early intervention and treatment. The prediction methodology involves extracting several features of the lung cancer cell and then applying pattern-based prediction techniques. In recent times, owing to the fact that the time and execution parameters are very important aspects to detect the abnormality of the fast-spreading cancer cells, digital image processing techniques are being widely deployed. The fundamental factors of this research are the quality of image assessment and the precision of feature extraction. Following our proposed methodology, a clear picture of the region of interest is obtained which acts as a basis for the feature extraction process. Here an overall evaluation of the digital image processing techniques used by previous scholars for the finding and classification of lung cancer nodules have also been emphasised.
31
Chang, Chia-Ching, Min-Shu Hsieh, Mong-Wei Lin, Yi-Hsuan Lee, Yi-Jing Hsiao, Kang-Yi Su, Te-Jen Su, Sung-Liang Yu, and Jin-Shing Chen. "Novel Genetic Prognostic Signature for Lung Adenocarcinoma Identified by Differences in Gene Expression Profiles of Low- and High-Grade Histological Subtypes." Biomolecules 12, no. 2 (January 19, 2022): 160. http://dx.doi.org/10.3390/biom12020160.
Full textAbstract:
The 2021 WHO classification proposed a pattern-based grading system for early-stage invasive non-mucinous lung adenocarcinoma. Lung adenocarcinomas with high-grade patterns have poorer outcomes than those with lepidic-predominant patterns. This study aimed to establish genetic prognostic signatures by comparing differences in gene expression profiles between low- and high-grade adenocarcinomas. Twenty-six (9 low- and 17 high-grade adenocarcinomas) patients with histologically “near-pure” patterns (predominant pattern comprising >70% of tumor areas) were selected retrospectively. Using RNA sequencing, gene expression profiles between the low- and high-grade groups were analyzed, and genes with significantly different expression levels between these two groups were selected for genetic prognostic signatures. In total, 196 significant candidate genes (164 upregulated and 32 upregulated in the high- and low-grade groups, respectively) were identified. After intersection with The Cancer Genome Atlas–Lung Adenocarcinoma prognostic genes, three genes, exonuclease 1 (EXO1), family with sequence similarity 83, member A (FAM83A), and disks large-associated protein 5 (DLGAP5), were identified as prognostic gene signatures. Two independent cohorts were used for validation, and the areas under the time-dependent receiver operating characteristic were 0.784 and 0.703 in the GSE31210 and GSE30219 cohorts, respectively. Our result showed the feasibility and accuracy of this novel three-gene prognostic signature for predicting the clinical outcomes of lung adenocarcinoma.
32
Schultz, Kenia, Luiz Carlos D'Aquino, Maria Raquel Soares, Andrea Gimenez, and Carlos Alberto de Castro Pereira. "Lung volumes and airway resistance in patients with a possible restrictive pattern on spirometry." Jornal Brasileiro de Pneumologia 42, no. 5 (October 2016): 341–47. http://dx.doi.org/10.1590/s1806-37562016000000091.
Full textAbstract:
ABSTRACT Objective: Many patients with proportional reductions in FVC and FEV1 on spirometry show no reduction in TLC. The aim of this study was to evaluate the role that measuring lung volumes and airway resistance plays in the correct classification of patients with a possible restrictive pattern on spirometry. Methods: This was a prospective study involving adults with reduced FVC and FEV1, as well as an FEV1/FV(C) ratio within the predicted range. Restrictive lung disease (RLD) was characterized by TLC below the 5th percentile, as determined by plethysmography. Obstructive lung disease (OLD) was characterized by high specific airway resistance, significant changes in post-bronchodilator FEV1, or an FEF25-75% < 50% of predicted, together with a high RV/TLC ratio. Nonspecific lung disease (NLD) was characterized by TLC within the predicted range and no obstruction. Combined lung disease (CLD) was characterized by reduced TLC and findings indicative of airflow obstruction. Clinical diagnoses were based on clinical suspicion, a respiratory questionnaire, and the review of tests of interest. Results: We included 300 patients in the study, of whom 108 (36%) were diagnosed with RLD. In addition, 120 (40%) and 72 (24%) were diagnosed with OLD/CLD and NLD, respectively. Among the latter, 24 (33%) were clinically diagnosed with OLD. In this sample, 151 patients (50.3%) were obese, and obesity was associated with all patterns of lung disease. Conclusions: Measuring lung volumes and airway resistance is often necessary in order to provide an appropriate characterization of the pattern of lung disease in patients presenting with a spirometry pattern suggestive of restriction. Airflow obstruction is common in such cases.
33
Refaee, Turkey, Benjamin Bondue, Gaetan Van Simaeys, Guangyao Wu, Chenggong Yan, Henry Woodruff, Serge Goldman, and Philippe Lambin. "A Handcrafted Radiomics-Based Model for the Diagnosis of Usual Interstitial Pneumonia in Patients with Idiopathic Pulmonary Fibrosis." Journal of Personalized Medicine 12, no. 3 (February 28, 2022): 373. http://dx.doi.org/10.3390/jpm12030373.
Full textAbstract:
The most common idiopathic interstitial lung disease (ILD) is idiopathic pulmonary fibrosis (IPF). It can be identified by the presence of usual interstitial pneumonia (UIP) via high-resolution computed tomography (HRCT) or with the use of a lung biopsy. We hypothesized that a CT-based approach using handcrafted radiomics might be able to identify IPF patients with a radiological or histological UIP pattern from those with an ILD or normal lungs. A total of 328 patients from one center and two databases participated in this study. Each participant had their lungs automatically contoured and sectorized. The best radiomic features were selected for the random forest classifier and performance was assessed using the area under the receiver operator characteristics curve (AUC). A significant difference in the volume of the trachea was seen between a normal state, IPF, and non-IPF ILD. Between normal and fibrotic lungs, the AUC of the classification model was 1.0 in validation. When classifying between IPF with a typical HRCT UIP pattern and non-IPF ILD the AUC was 0.96 in validation. When classifying between IPF with UIP (radiological or biopsy-proved) and non-IPF ILD, an AUC of 0.66 was achieved in the testing dataset. Classification between normal, IPF/UIP, and other ILDs using radiomics could help discriminate between different types of ILDs via HRCT, which are hardly recognizable with visual assessments. Radiomic features could become a valuable tool for computer-aided decision-making in imaging, and reduce the need for unnecessary biopsies.
34
Pan, Xiaoxi, Hanyun Zhang, Anca-Ioana Grapa, Khalid AbdulJabbar, Shan E. Ahmed Raza, HO KWAN ALVIN CHEUNG, Takahiro Karasaki, et al. "Abstract 5055: Precise segmentation of growth patterns in TRACERx lung adenocarcinoma." Cancer Research 82, no. 12_Supplement (June 15, 2022): 5055. http://dx.doi.org/10.1158/1538-7445.am2022-5055.
Full textAbstract:
Abstract Histologic growth patterns are associated with patient prognosis, thus recognized as an important part of the WHO classification in lung adenocarcinoma (Travis et al. 2015, Moreira et al., 2020). The wide spectrum of growth patterns proves challenging for reproducible and quantitative scoring. Currently, scoring is based on manual identification of the predominant pattern and percentages of patterns in routine diagnostic slides. The lack of an automated method also limits our ability to investigate the immune microenvironment of growth patterns. To overcome the above challenges, we present a deep learning method, Pyramid Stream Networks, to precisely segment growth patterns at pixel level. Unlike existing methods, the proposed method captures different spatial scales of the histology information by novel attention strategies at different learning stages. This problem-oriented design yields precise boundaries for each pattern, enabling the investigation of growth pattern heterogeneity, and the relationship with tumor microenvironment components. Experiments were conducted on 49 haematoxylin and eosin whole slide images (WSIs) from TRACERx 100 cohort (AbdulJabbar et al., 2020). Each WSI was sparsely annotated by 3 senior pathologists. A total of 2968 annotated patches were split into 5 folds for cross validation. We compared our method with two state-of-the-art methods applied in semantic segmentation, attention U-net (Oktay et al. 2018) and DeepLabV3+ (Chen et al. 2018). When evaluated at patch level, our method outperformed the better comparison method, DeepLabV3+, by 3.43% and 2.99% in pixel-wise Dice and overall precision (OP) (Dice: 60.34% vs. 56,91%, OP: 65.43% vs. 62.44%). When applied to WSIs, the model correctly predicted the predominant pattern for 38 out of 49 samples, achieving an accuracy of 77.55%. Interestingly, in the 11 discordant cases, 10 showed high intra-tumor heterogeneity of growth patterns, measured by Shannon diversity, highlighting the impact of intra-tumor heterogeneity on growth pattern assessment. Additionally, we combined the identified growth patterns with lymphocytic distribution measured in (AbdulJabbar et al., 2020) and revealed a significantly increased immune infiltration in proximity to the solid pattern as compared to others, which is in line with previous findings (Tavernari et al., 2021). In summary, by leveraging image-analysis and artificial intelligence techniques, we propose a new method for precise growth pattern segmentation from routine histology samples of lung adenocarcinoma. It provides quantitative and reproducible scores of growth patterns, which can be developed into a decision support system for pathologists and clinicians. Furthermore, through pattern-specific spatial mapping, it enables future studies of intra-tumor heterogeneity, such as the preferential infiltration of lymphocyte subsets adjacent to diverse growth patterns. Citation Format: Xiaoxi Pan, Hanyun Zhang, Anca-Ioana Grapa, Khalid AbdulJabbar, Shan E. Ahmed Raza, HO KWAN ALVIN CHEUNG, Takahiro Karasaki, John Le Quesne, David A. Moore, Charles Swanton, Yinyin Yuan. Precise segmentation of growth patterns in TRACERx lung adenocarcinoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 5055.
35
Khan, Muhammad Attique, Venkatesan Rajinikanth, Suresh Chandra Satapathy, David Taniar, Jnyana Ranjan Mohanty, Usman Tariq, and Robertas Damaševičius. "VGG19 Network Assisted Joint Segmentation and Classification of Lung Nodules in CT Images." Diagnostics 11, no. 12 (November 26, 2021): 2208. http://dx.doi.org/10.3390/diagnostics11122208.
Full textAbstract:
Pulmonary nodule is one of the lung diseases and its early diagnosis and treatment are essential to cure the patient. This paper introduces a deep learning framework to support the automated detection of lung nodules in computed tomography (CT) images. The proposed framework employs VGG-SegNet supported nodule mining and pre-trained DL-based classification to support automated lung nodule detection. The classification of lung CT images is implemented using the attained deep features, and then these features are serially concatenated with the handcrafted features, such as the Grey Level Co-Occurrence Matrix (GLCM), Local-Binary-Pattern (LBP) and Pyramid Histogram of Oriented Gradients (PHOG) to enhance the disease detection accuracy. The images used for experiments are collected from the LIDC-IDRI and Lung-PET-CT-Dx datasets. The experimental results attained show that the VGG19 architecture with concatenated deep and handcrafted features can achieve an accuracy of 97.83% with the SVM-RBF classifier.
36
Kesuma, Lucky Indra, and Rudiansyah Rudiansyah. "Classification of Covid-19 Diseases Through Lung CT-Scan Image Using the ResNet-50 Architecture." Computer Engineering and Applications Journal 12, no. 1 (February 1, 2023): 11–30. http://dx.doi.org/10.18495/comengapp.v12i1.425.
Full textAbstract:
Covid-19 is a respiratory tract disease caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). The Covid-19 disease was first reported in Wuhan, China, in December 2019. The SARS-CoV-2 virus is primarily transmitted through human contact, and the World Health Organization has proclaimed a global pandemic (WHO). Symptoms of Covid-19 can range from asymptomatic to mild and severe. One way to diagnose Covid-19 disease can be done by examining lung abnormalities on the results of a Computed Tomography Scan (CT-Scan) of the lungs. However, determining the diagnostic results requires high accuracy and a long time. For this reason, an automated system is needed to make it easier for medical personnel to diagnose Covid-19 disease quickly and accurately. One of the automated systems with computer assistance in detecting abnormalities in CT-Scan images of the lungs is to perform pattern recognition
37
Schmid, Hans-Rudolf, Doris Schmitter, Philippe Blum, Mark Miller, and Dieter Vonderschmitt. "Lung tumor cells: A multivariate approach to cell classification using two-dimensional protein pattern." Electrophoresis 16, no. 1 (1995): 1961–68. http://dx.doi.org/10.1002/elps.11501601322.
Full text
38
Feng, Po-Hao, Tzu-Tao Chen, Yin-Tzu Lin, Shang-Yu Chiang, and Chung-Ming Lo. "Classification of lung cancer subtypes based on autofluorescence bronchoscopic pattern recognition: A preliminary study." Computer Methods and Programs in Biomedicine 163 (September 2018): 33–38. http://dx.doi.org/10.1016/j.cmpb.2018.05.016.
Full text
39
Subasree, S., N. P. Gopalan, and N. K. Sakthivel. "EMOPS: an enhanced multi-objective pswarm based classifier for poorly understood cancer patterns." International Journal of Engineering & Technology 7, no. 2 (May 8, 2018): 7. http://dx.doi.org/10.14419/ijet.v7i2.27.12102.
Full textAbstract:
Microarray based Cancer Pattern Classification is one of the popular techniques in Bioinformatics Research. This Research Work is noticed that for studying the expression levels through the Gene Expression profiling experiments, thousands of Genes have to be simultaneously studied to understand the patterns of the Gene Expression or Cancer Pattern. This research work proposed an efficient Cancer Pattern Clas-sifier called An Enhanced Multi-Objective Pswarm (EMOPS) and it is studied thoroughly in terms of Memory Utilization, Execution Time (Processing Time), Sensitivity, Specificity, Classification Accuracy and FScore. The results were compared with the recently proposed classifiers namely Hybrid Ant Bee Algorithm (HABA), Kernelized Fuzzy Rough Set Based Semi Supervised Support Vector Machine (KFRS-S3VM) and Multi-objective Particle Swarm Optimization (MPSO). For analyzing the performances of the proposed model, this work considered a few cancer patterns namely Bladder, Breast, Colon, Endometrial, Kidney, Leukemia, Lung, Melanoma, Mom-Hodgkin, Pancreatic, Prostate and Thyroid. From our experimental results, it was noticed that the proposed model outperforms the identified three classifiers in terms of Memory Utilization, Execution Time (Processing Time), Sensitivity, Specificity, Classification Accuracy and FScore. To improve the performance of the system further in term of Processing Time, the proposed model Enhanced Multi-Objective Pswarm (EMOPS) is implemented under Parallel Framework and evaluated. That is the model is tested with Two, Four, Eight and Sixteen Parallel Processors and from the results, it is established that the Processing Time decreases considerably which will improve the performance of the Proposed Model.
40
Irsyad, Hafiz, and Dina Mariana. "Klasifikasi Pneumonia pada Chest X-Ray Paru-paru dengan Ekstraksi Fitur Local Binary Pattern Menggunakan Support Vector Machine." Jurnal Ilmiah Betrik 12, no. 1 (April 8, 2021): 54–62. http://dx.doi.org/10.36050/betrik.v12i1.294.
Full textAbstract:
Pneumonia is a type of lung disease caused by bacteria, viruses, fungi, or parasites. One way to find out pneumonia is by X-ray or x-ray. X-ray results will be analyzed by experts in the field to find out whether there is pneumonia or not. This study aims to classify the x-ray results whether there is pneumonia or normal. The method used for the classification of Support Vector Machine (SVM) and Local Binary Pattern (LBP) feature extraction. Stages carried out in the image before the classification are Cropping and Resize, then feature extraction using Local Binary Pattern and in classification using Support Vector Machine produces the best accuracy of 65.63%.
Keywords : Pneumonia, Chest X-Ray, LBP, SVM
41
Nishio, Mizuho, Mari Nishio, Naoe Jimbo, and Kazuaki Nakane. "Homology-Based Image Processing for Automatic Classification of Histopathological Images of Lung Tissue." Cancers 13, no. 6 (March 10, 2021): 1192. http://dx.doi.org/10.3390/cancers13061192.
Full textAbstract:
The purpose of this study was to develop a computer-aided diagnosis (CAD) system for automatic classification of histopathological images of lung tissues. Two datasets (private and public datasets) were obtained and used for developing and validating CAD. The private dataset consists of 94 histopathological images that were obtained for the following five categories: normal, emphysema, atypical adenomatous hyperplasia, lepidic pattern of adenocarcinoma, and invasive adenocarcinoma. The public dataset consists of 15,000 histopathological images that were obtained for the following three categories: lung adenocarcinoma, lung squamous cell carcinoma, and benign lung tissue. These images were automatically classified using machine learning and two types of image feature extraction: conventional texture analysis (TA) and homology-based image processing (HI). Multiscale analysis was used in the image feature extraction, after which automatic classification was performed using the image features and eight machine learning algorithms. The multicategory accuracy of our CAD system was evaluated in the two datasets. In both the public and private datasets, the CAD system with HI was better than that with TA. It was possible to build an accurate CAD system for lung tissues. HI was more useful for the CAD systems than TA.
42
Deepa, V., and P. Mohamed Fathimal. "Deep-ShrimpNet fostered Lung Cancer Classification from CT Images." International Journal of Image, Graphics and Signal Processing 15, no. 4 (August 8, 2023): 59–68. http://dx.doi.org/10.5815/ijigsp.2023.04.05.
Full text
43
Wang, Zhoufeng, Minjie Xu, Hua Chen, Kehui Xie, Minyang Su, Qiye He, Zhixi Su, Rui Liu, and Weimin Li. "Abstract 6202: Plasma cell-free DNA fragmentation patterns combined with tumor mutation detection in diagnosis of lung cancer." Cancer Research 82, no. 12_Supplement (June 15, 2022): 6202. http://dx.doi.org/10.1158/1538-7445.am2022-6202.
Full textAbstract:
Abstract Background: Lung cancer is one of the deadliest types of cancer in China. Its 5-year survival rates at early stages are significantly higher than advanced stages. LDCT has been adopted for lung cancer screening in high-risk individuals; however, debate regarding its accuracy is still ongoing. Mutation detection on cell free DNA (cfDNA) has traditionally been used to monitor DNA molecular changes derived from lung cancer cells in blood, while recently fragmentation pattern profiling of cfDNA has been shown as a promising alternative for early cancer detection. We aimed to combine mutation detection and fragmentation pattern analysis on cfDNA to develop a non-invasive assay to screen early lung cancer. Methods: Candidate DNA mutations were curated from literature and public databases, including COSMIC and TCGA. DNA fragmentation markers were collected from literature and whole genome sequencing (WGS) datasets. A panel of 407 primers covering selected mutation and fragmentation markers was developed to distinguish lung adenocarcinoma (ADC) plasma and normal plasma. We enrolled a total of 122 plasma samples (64 normal, 58 ADC) for this study. 49 normal samples and 44 ADC samples were used to construct a mutation-based classification model and a fragmentation-based classification model separately. The tuning parameters and features were determined by inner 4-fold cross validation. For the mutation-based model, baseline was set using normal samples in training set. Maximum allele frequency was calculated for each sample in test data (15 normal, 14 ADC), which was filtered by the background baseline. For the fragmentation-based model, we used the DELFI fragment score to construct fragmentation profiles, which was the ratio between short fragments (100-150bp) and long fragments (151-220bp). After optimization, the two models were integrated by Logistic Regression to create a combined model, which was validated by 4-fold nested cross validation. Results: ADC and normal plasma were sequenced by the aforementioned panel at an average depth of 2,000X to ensure the reliability of model construction and classification results. In classifying normal and ADC plasma, the mutation model alone is only modestly accurate as it produced an AUC of 0.69. But the fragmentation model demonstrated significantly higher accuracy, achieving AUC of 0.85. Furthermore, the combined model performed better than either model along, achieving an elevated AUC of 0.87. Conclusions: We demonstrate that DNA mutation and fragmentation pattern of cfDNA can classify lung cancer and normal plasmas separately, but fragmentation pattern are more accurate than mutation in this task. Combining the two models further improved prediction accuracy, suggesting they complement each other. Although this is a pilot study of limited cases, it demonstrated the potential of combining markers for accurate lung ADC detection in plasma. Citation Format: Zhoufeng Wang, Minjie Xu, Hua Chen, Kehui Xie, Minyang Su, Qiye He, Zhixi Su, Rui Liu, Weimin Li. Plasma cell-free DNA fragmentation patterns combined with tumor mutation detection in diagnosis of lung cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 6202.
44
Satter, Khaled Bin, Paul MH Tran, Lynn KH Tran, John Nechtman, Nikhil Patel, Bruno Santos, Diane Hopkins, Nagla Abdel Karim, Jin-Xiong She, and Sharad B. Purohit. "Abstract 3496: Transcriptomic classification of lung adenocarcinoma identifies a novel subgroup with a poor survival prognosis." Cancer Research 82, no. 12_Supplement (June 15, 2022): 3496. http://dx.doi.org/10.1158/1538-7445.am2022-3496.
Full textAbstract:
Abstract Lung adenocarcinoma is one-half of all lung cancer and the third deadliest cancer in the world. The traditional classification of lung adenocarcinoma involves invasiveness, growth pattern, presence of mucin, and other histological features. However, this classification provides limited prognostic predictability. Molecular profiles based The Cancer genome Atlas lung adenocarcinoma cohort classified the tumors into the terminal respiratory unit (TRU), proximal proliferative (PP), and proximal infiltrative (PI) based on unsupervised classification, which did not address clinical applicability to the classification. Here, we developed an unsupervised classification with Density-based UMAP (DBU), which identified four transcriptomic profiles for lung adenocarcinoma (Transcriptomic profile, TP1-TP4). We identified a gene signature with 299 genes to develop a supervised classifier, called Ensemble Transcriptomic classifier (ETC), to identify these four subgroups within the total cohort. All TP1 is PI. TP2 is 49.0% TFU and 45.0% PP. TP3 is 76.2% PI and 23.8% PP. TP4 is 54.5% TFU and 45.5% PI. TP1 is characterized by neuroendocrine-like features and clusters with large cell neuroendocrine tumors in cluster analysis. TP3 is squamous-like enriched with cell cycle and DNA repair high and worse prognosis and groups with squamous cell carcinoma in cluster analysis. TP2 has high immune cell infiltration, and TP4 showed low mutational burden and low immune cell infiltration. We validated these subgroups identified in the TCGA cohort in a microarray meta-dataset with DBU, ETC. This classification showed four subgroups in lung adenocarcinoma, which shows potential clinical actionable findings. Citation Format: Khaled Bin Satter, Paul MH Tran, Lynn KH Tran, John Nechtman, Nikhil Patel, Bruno Santos, Diane Hopkins, Nagla Abdel Karim, Jin-Xiong She, Sharad B. Purohit. Transcriptomic classification of lung adenocarcinoma identifies a novel subgroup with a poor survival prognosis [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 3496.
45
Davri, Athena, Effrosyni Birbas, Theofilos Kanavos, Georgios Ntritsos, Nikolaos Giannakeas, Alexandros T. Tzallas, and Anna Batistatou. "Deep Learning for Lung Cancer Diagnosis, Prognosis and Prediction Using Histological and Cytological Images: A Systematic Review." Cancers 15, no. 15 (August 5, 2023): 3981. http://dx.doi.org/10.3390/cancers15153981.
Full textAbstract:
Lung cancer is one of the deadliest cancers worldwide, with a high incidence rate, especially in tobacco smokers. Lung cancer accurate diagnosis is based on distinct histological patterns combined with molecular data for personalized treatment. Precise lung cancer classification from a single H&E slide can be challenging for a pathologist, requiring most of the time additional histochemical and special immunohistochemical stains for the final pathology report. According to WHO, small biopsy and cytology specimens are the available materials for about 70% of lung cancer patients with advanced-stage unresectable disease. Thus, the limited available diagnostic material necessitates its optimal management and processing for the completion of diagnosis and predictive testing according to the published guidelines. During the new era of Digital Pathology, Deep Learning offers the potential for lung cancer interpretation to assist pathologists’ routine practice. Herein, we systematically review the current Artificial Intelligence-based approaches using histological and cytological images of lung cancer. Most of the published literature centered on the distinction between lung adenocarcinoma, lung squamous cell carcinoma, and small cell lung carcinoma, reflecting the realistic pathologist’s routine. Furthermore, several studies developed algorithms for lung adenocarcinoma predominant architectural pattern determination, prognosis prediction, mutational status characterization, and PD-L1 expression status estimation.
46
Travis, William D., Kavita Garg, Wilbur A. Franklin, Ignacio I. Wistuba, Bradley Sabloff, Masayuki Noguchi, Ryutaro Kakinuma, et al. "Evolving Concepts in the Pathology and Computed Tomography Imaging of Lung Adenocarcinoma and Bronchioloalveolar Carcinoma." Journal of Clinical Oncology 23, no. 14 (May 10, 2005): 3279–87. http://dx.doi.org/10.1200/jco.2005.15.776.
Full textAbstract:
Purpose To review recent advances in pathology and computed tomography (CT) of lung adenocarcinoma and bronchioloalveolar carcinoma (BAC). Methods A pathology/CT review panel of pathologists and radiologists met during a November 2004 International Association for the Study of Lung Cancer/American Society of Clinical Oncology consensus workshop in New York. The purpose was to determine if existing data was sufficient to propose modification of criteria for adenocarcinoma and BAC as newly published in the 2004 WHO Classification of Lung Tumors, and to address the pathologic/radiologic concept of diffuse/multicentric BAC. Results Solitary small, peripheral BACs have an excellent prognosis. Most lung adenocarcinomas with a BAC pattern are not pure BAC, but rather adenocarcinoma, mixed subtype with invasive patterns. This applies to tumors presenting with a diffuse/multinodular as well as solitary nodule pattern. The percent of BAC versus invasive components in lung adenocarcinomas appears to be prognostically important. However, a consensus definition of “minimally invasive” BAC with a favorable prognosis could not be achieved. While recognition of a BAC component is possible, the diagnosis of BAC with exclusion of invasive adenocarcinoma cannot be made by small biopsy or cytology specimens. Conclusion There is a need to work toward a mutual understanding and consensus between pathologists, clinicians, and researchers with the use of the term BAC versus adenocarcinoma. Future studies should make some attempt to quantitate these components and/or other features such as size of scar, size of invasive component, or pattern of invasion. Hopefully, this work will allow definition of a category of adenocarcinoma, mixed subtype with predominant BAC/minimal invasion and a favorable prognosis.
47
Satoory, Luma J., Hussain S. Hasan, and Ali M. Hasan. "An Automated System for the Classification of COVID-19, Suspected COVID-19 and Healthy Lung CT Images based on Local Binary Pattern and Deep Learning Features." NeuroQuantology 20, no. 5 (May 11, 2022): 436–43. http://dx.doi.org/10.14704/nq.2022.20.5.nq22192.
Full textAbstract:
Because of the inadequate capacity and a substantial surge of probable COVID-19 cases, several health systems around worldwide have collapsed. As a result, the requirement for a rapid, effective, and precise way to reduce radiologists' workload in diagnosing suspected instances has arisen. The goal of the present study is to develop a novel system to automatically diagnose and classify lung CT scans into three categories: suspected covid-19, covid-19, and healthy lung scans. Before feature extraction using convolutional neural network (CNN) and Local Binary Pattern (LBP) approaches, the CT scans are first pre-processed through implementing a set of algorithms. Lastly, with the use of the support vector machine (SVM) model, such features are divided into three groups. The maximum accuracy attained in classifying a dataset of 351 CT scans of the lungs was 98.22%. The outcomes of the experiments show that merging the extracted features increases the effectiveness of lung classification CT scans.
48
Manfredi, A., C. Vacchi, G. Della Casa, S. Cerri, G. DI Cecco, F. Coppi, F. Luppi, C. Salvarani, and M. Sebastiani. "AB0426 FIBROSING INTERSTITIAL LUNG DISEASE IN PRIMARY SJOGREN SYNDROME." Annals of the Rheumatic Diseases 79, Suppl 1 (June 2020): 1512.3–1512. http://dx.doi.org/10.1136/annrheumdis-2020-eular.5769.
Full textAbstract:
Background:Interstitial lung disease (ILD) represents the most frequent pulmonary manifestation of primary Sjogren’s syndrome (pSS), with a prevalence ranging between 6-70% in different retrospectives studies. Non-specific interstitial pneumonia (NSIP) is recognized as the most common ILD disorder, followed by organizing pneumonia (OP), usual interstitial pneumonia (UIP) and lymphocytic interstitial pneumonia (LIP), specifically associated with pSS but less frequent.Objectives:To investigate the prevalence of fibrosing patterns in a monocentric cohort of pSS patients evaluated for lung involvement in a cross-sectional study.Methods:In a cross-sectional study all patients fulfilling ACR/EULAR classification criteria for pSS and with a known diagnosis of ILD were enrolled; the other patients were carefully investigated for signs or symptoms suggestive for ILD (including the search for velcro crackles with a digital device); when suspect, patients underwent to high resolution computed tomography (HRCT). An expert radiologist re-evaluated all HRCT for classifying the ILD pattern as: UIP, fibrotic NSIP, fibrotic OP, NSIP, OP, LIP, indeterminate.Results:One hundred and eighty-five pSS patients were enrolled; among them 34 showed ILD (18.4%) with the following features: M/F 3/31, median age 57 (range 24-80), median FVC 90% (39-127%), median DLCO 49% (20-84%). Patients were classified in two groups according to radiologic classification: the group 1 (18 pts 52,9%) included UIP (13 patients, 38.2%), fibrotic NSIP (4, 11.8%), fibrotic OP (1 2.9%); the group 2 (16 pts, 47.1%) included NSIP (6, 17.6%), OP (4, 11.8%), indeterminate (4, 11.8%), LIP (2, 5.9%). No significant differences were observed between the two groups with the exception of anti-SSB positivity more frequently detected in non-fibrosing pattern (p0,043).Conclusion:Despite previous observations, our data suggest a high prevalence of fibrosing ILD pattern in pSS patients. We participate at a multidisciplinary team with expert pulmonologists and radiologists and some patients of our cohort firstly referred to pulmonologist for appearance of ILD before the diagnosis of pSS, contributing to the possible selection of more severe lung disease. However, these data suggest first of all that pSS should always be considered in differential diagnosis of fibrosing ILD; moreover, since fibrosing ILD is thought to have a worse response to immunosuppressive drugs, the role of new possible therapeutic strategies such as anti-fibrotic could represent an important field of interest.Disclosure of Interests:None declared
49
Nascimento, Ellen Caroline Toledo do, Bruno Guedes Baldi, Marcio Valente Yamada Sawamura, and Marisa Dolhnikoff. "Morphologic Aspects of Interstitial Pneumonia With Autoimmune Features." Archives of Pathology & Laboratory Medicine 142, no. 9 (September 1, 2018): 1080–89. http://dx.doi.org/10.5858/arpa.2017-0528-ra.
Full textAbstract:
Context.— Interstitial lung disease, a common complication observed in several connective tissue diseases, causes significant morbidity and mortality. Similar to individuals with connective tissue diseases, a significant subgroup of patients with clinical and serologic characteristics suggestive of autoimmunity but without confirmed specific connective tissue disease presents with associated interstitial lung disease. These patients have been classified using different controversial nomenclatures, such as undifferentiated connective tissue disease–associated interstitial lung disease, lung-dominant connective tissue disease, and autoimmune featured interstitial lung disease. The need for a better understanding and standardization of this entity, interstitial lung disease with autoimmune features, and the need for an adequate management protocol for patients resulted in the introduction of a new terminology in 2015: interstitial pneumonia with autoimmune features. This new classification requires a better comprehension of its diagnostic impact and the influence of its morphologic aspects on the prognosis of patients. Objective.— To review the diagnostic criteria for interstitial pneumonia with autoimmune features, with an emphasis on morphologic aspects. Data Sources.— The review is based on the available literature, and on pathologic, radiologic, and clinical experience. Conclusions.— The interstitial pneumonia with autoimmune features classification seems to identify a distinct subgroup of patients with different prognoses. Studies show that nonspecific interstitial pneumonia and usual interstitial pneumonia are the most prevalent morphologic patterns and show discrepant results on the impact of the usual interstitial pneumonia pattern on survival. Prospective investigations are necessary to better define this subgroup and to determine the prognosis and appropriate clinical management of these patients.
50
Karasaki, Takahiro, David A. Moore, Selvaraju Veeriah, Cristina Naceur-Lombardelli, Antonia Toncheva, Maise Al Bakir, Thomas B. Watkins, et al. "Abstract 6091: Evolutionary characterisation of lung adenocarcinoma pathological subtypes in TRACERx." Cancer Research 82, no. 12_Supplement (June 15, 2022): 6091. http://dx.doi.org/10.1158/1538-7445.am2022-6091.
Full textAbstract:
Abstract Background: Lung adenocarcinoma (LUAD) is a morphologically and genetically diverse disease. The prognostic impact of LUAD histological patterns have been described, such as solid growth pattern and poor outcomes, though their underlying biology is poorly understood. Furthermore, the genomic characteristics and evolutionary constraints in relation to the inter- and intra- tumoral variance of histological patterns in primary and metastatic disease are unknown. Methods: Pathological classification of 246 patients with LUAD from the TRACERx 421 cohort was performed at the whole tumor (diagnostic samples) and multi-regional sample level (matched for tumor whole exome sequencing and RNA sequencing). Circulating tumor DNA (ctDNA) data was also integrated to determine the relationship between pathological subtypes and ctDNA detection. Results: Chromosomal instability, characterized by fraction of the genome affected by subclonal copy number alterations was significantly correlated with proportion of high-grade patterns, namely solid, cribriform and micropapillary (Spearman’s Rho 0.27, p<0.001). Analysis of somatic copy number alterations (SCNAs) and driver mutation profiles showed that specific SCNAs were associated with a predominant growth pattern, such as 3q arm gains in predominantly cribriform and solid pattern tumors. Multiregional analysis of tumors with mixed patterns showed higher grade regions to be associated with a higher frequency of LOH and expression of proliferation-related pathway genes, suggesting intra-tumoral sequential evolution from low to high grade growth patterns. No recurrent subclonal mutations or SCNAs were found to associate with progression from low to high grade patterns. The growth pattern in metastatic tumors tended to show similar or a higher-grade pattern compared with primary tumor regions harboring metastasizing clones (seeding regions). The growth pattern of the seeding regions in the primary tumor was not necessarily higher grade compared with their non-seeding counterparts. Finally, the proportion of solid pattern in the primary tumor and the presence of necrosis were found to be strongly associated with pre-operative ctDNA detection, while histological ‘spread through air spaces’ (STAS) was identified in 92% (12/13) of pre-operative ctDNA-negative tumors that subsequently were associated with recurrence. Patients with both pre-operative detectable ctDNA and STAS had a particularly poor prognosis. Conclusion: These data reveal insights into the association between morphological and molecular heterogeneity in LUAD, describe key features of tumor evolutionary tendencies and demonstrate the utility of detailed tumor morphological assessment integrated with molecular characterization and ctDNA detection. Citation Format: Takahiro Karasaki, David A. Moore, Selvaraju Veeriah, Cristina Naceur-Lombardelli, Antonia Toncheva, Maise Al Bakir, Thomas B. Watkins, Oriol Pich, Alexander M. Frankell, Emilia Lim, Mark S. Hill, Kristiana Grigoriadis, Carlos Martinez-Ruiz, James R. Black, Clare Puttick, Dhruva Biswas, Ariana Huebner, Michelle Dietzen, Emma Colliver, Claudia Lee, Nnenna Kanu, Sadegh Mohammad Saghafinia, Francisco Gimeno Valiente, Christopher Abbosh, Crispin T. Hiley, Simone Zaccaria, Nicolai J. Birkbak, Allan Hackshaw, TRACERx Consortium, Teresa Marafioti, Roberto Salgado, John Le Quesne, Andrew G. Nicholson, Nicholas McGranahan, Charles Swanton, Mariam Jamal-Hanjani. Evolutionary characterisation of lung adenocarcinoma pathological subtypes in TRACERx [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 6091.