Дисертації з теми "Breast Tumors Classification"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-19 дисертацій для дослідження на тему "Breast Tumors Classification".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Chaudhury, Baishali. "The Use of Textural Kinetic Habitats to Mine Diagnostic Information from DCE MR Images of Breast Tumors." Scholar Commons, 2015. http://scholarcommons.usf.edu/etd/5663.
Повний текст джерелаGuo, Qi. "Computerised texture and shape analysis for classification of breast tumours in digital mammograms." Thesis, University of Reading, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.501358.
Повний текст джерелаPurvis, Nina Louise. "Classification of breast malignancy using optimised advanced diffusion-weighted imaging, and, Surgical planning for breast tumour resection using MR-guided focused ultrasound." Thesis, University of Hull, 2016. http://hydra.hull.ac.uk/resources/hull:15193.
Повний текст джерелаSundqvist, Martina. "Stability and selection of the number of groups in unsupervised clustering : application to the classification of triple negative breast cancers." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASM026.
Повний текст джерелаIn this thesis, I treat the topic of classifying Triple Negative Breast Cancer (TNBC) tumors from a statistical point of view. After proposing a classification of TNBC based on proteins, I mainly focus on the use of cluster stability for selecting the number of groups in unsupervised clustering. Indeed, this is the method generally employed when classifying TNBC. The aim of this method is to obtain a classification that is robust, that is, easily replicable on similar data. This is measured by its sensibility to small changes, such as subsamplig of the dataset.Despite the popularity of this method, little is still known about how or when it works. For this reason, I propose two important methodological contributions, increasing the usability and interpretability of this method: (1) an R-package, clustRstab, that easily enables to estimate the stability of a clustering in different parameter settings. This package is accompanied by a simulation and an application study investigating when and how this method works. (2) A Modified version of the Adjusted Rand Index (ARI), a popular score for cluster comparisons which is a crucial step for estimating the stability of a clustering. I correct this score by basing it on a multinomial distribution hypothesis which enables it to take into account dependence between clusterings and conduct statistical inference. This Modified ARI (M ARI) is implemented in the R package texttt{aricode}.These two methods are then applied to a large cohort of TNBC tumors and the results are discussed in relation to earlier classification results of TNBC
Neudert, Marcus, Christian Fischer, Burkhard Krempien, Markus J. Seibel, and Frieder Bauss. "A Rapid Histological Score for the Semiquantitative Assessment of Bone Metastases in Experimental Models of Breast Cancer." Karger, 2008. https://tud.qucosa.de/id/qucosa%3A27606.
Повний текст джерелаHintergrund: Mit Hilfe eines etablierten Tiermodells zur Erzeugung lokalisationsspezifischer Knochenmetastasen in der Nacktratte wurde ein semiquantitatives histologisches Graduierungssystem zur schnellen Bewertung osteolytischer Knochenmetastasen entwickelt. Das Graduierungssystem liefert hinsichtlich der Metastasenlokalisation, deren Ausmaß und Infiltrationsmuster wertvolle Zusatzinformationen zu den konventionellen histologischen Untersuchungsmethoden. Damit kann beispielsweise auch die pharmakologische Wirkung von Bisphosphonaten auf die Knochenmetastasierung beurteilt werden. Material und Methoden: Männlichen Nacktratten (n = 12 pro Gruppe) wurden Zellen der humanen Brustkrebszellinie MDA-MB-231 in die Oberschenkelarterie inokuliert. Ab dem Auftreten radiologisch erkennbarer Osteolysen 18 Tage nach Inokulation erhielten die Tiere bis zum Studienende (Tag 30) täglich entweder eine subkutane Applikation einer Phosphat-Puffer-Lösung (Kontrollgruppe) oder Ibandronat (IBN, 10 µg P/kg; Behandlungsgruppe). Konventionelle Röntgenaufnahmen wurden an den Tagen 18 und 30 nach Tumorinokulation angefertigt und die Osteolysenflächen mittels Computerauswertung bestimmt. Nach Studienende wurde der Metastasenbefall in beiden Tibiae sowohl konventionell histologisch als auch mittels des neuen Graduierungssystems ausgewertet. Ergebnisse: Die Metastasenfläche korrelierte mit der kummulativen Punktsumme des Graduierungssystems sowohl in der Kontrollgruppe (r = 0,762; p < 0,001) als auch in der Ibandronat- Gruppe (r = 0,951; p < 0,001). Ebenso war die Osteolysenfläche eng mit der Punktesumme in beiden Gruppen korreliert (r = 0,845 und 0,854; p < 0,001). Schlussfolgerung: Die signifikante Reduktion von Knochenmark- und Kortikalisbefall durch IBN deuten auf eine gute lokale Kontrolle des Metastasenwachstums hin.
Dieser Beitrag ist mit Zustimmung des Rechteinhabers aufgrund einer (DFG-geförderten) Allianz- bzw. Nationallizenz frei zugänglich.
Albuquerque, Andreia de, Sepp Kaul, Georg Breier, Petra Krabisch, and Nikos Fersis. "Multimarker Analysis of Circulating Tumor Cells in Peripheral Blood of Metastatic Breast Cancer Patients: A Step Forward in Personalized Medicine." Karger, 2012. https://tud.qucosa.de/id/qucosa%3A27718.
Повний текст джерелаZiel: Entwicklung eines immunomagnetischen Verfahrens zur Isolierung zirkulierender Tumorzellen (CTCs) in Kombination mit einer molekularen Multimarkeranalyse für die hochspezifische Identifizierung maligner Zellen. Patientinnen und Methoden: Peripheres Blut (PB) von 32 Patientinnen mit metastasiertem Mammakarzinom und von 42 gesunden Kontrollen wurde für die immunomagnetische Tumorzellanreicherung mit den Antikörpern BM7 und VU1D9 genutzt. Eine Real-Time Reverse Transkription Polymerase-Kettenreaktion (RT-PCR)-Methodik mit den Markern KRT19, SCGB2A2, MUC1, EPCAM, BIRC5 und ERBB2 wurde für den CTC-Nachweis und die Tumorzellcharakterisierung entwickelt. Ergebnisse: Für die einzelnen Marker wurden die folgenden Positivitätsraten ermittelt: 46,9% für KRT19, 25,0% für SCGB2A2, 28,1% für MUC1, 28,1% für EPCAM, 21,9% für BIRC5 und 15,6% für ERBB2. Nach der Bestimmung individualisierter Cut-off-Werte ergab sich für den kombinierten Multimarkernachweis eine Sensitivität und Spezifität von 56,3% bzw. 100%. Bemerkenswert war der Befund, dass 27,0% der HER2-tumornegativen Patientinnen ERBB2-mRNA-positive CTCs aufwiesen. Schlussfolgerung: Die hier beschriebene Methodik bestimmt CTCs mit hoher Spezifität. Die molekulare Multimarkeranalyse liefert wertvolle Real-Time-Informationen für personalisierte Behandlungsmodalitäten.
Dieser Beitrag ist mit Zustimmung des Rechteinhabers aufgrund einer (DFG-geförderten) Allianz- bzw. Nationallizenz frei zugänglich.
Makdissi, Fabiana Baroni Alves. "Influência do microambiente no prognóstico do câncer da mama." Universidade de São Paulo, 2014. http://www.teses.usp.br/teses/disponiveis/5/5155/tde-01042014-112230/.
Повний текст джерелаIntroduction: Luminal breast cancer subtypes A and B (HER2 negative) may present a variable prognosis, depending on tumor proliferation index, evaluated by Ki67 expression. Malignant cells and adjacent stromal cells (fibroblasts and immune response cells) may interact by both cell contact and secreted factors and influence tumor behavior. It was shown that stromal cells may enhance breast cancer cells proliferation. Objective: Our aim was to evaluate stromal cells gene expression profile in luminal A and luminal B tumors and to evaluate whether selected transcripts expressed in stromal cells may be associated with prognosis in breast cancer. Material/ Methods and Results: Hormone receptor positive tumor samples from 11 post menopausal patients were analyzed, all of them Her2 negative. Ki67 expression <= 10% (luminal A) was observed in five and Ki67 >= 30% (luminal B) in six samples. Stromal cells were microdissected for RNA extraction, which was hybridized in Agilent G485-1A GE 8x60K microarray platform. After normalization, 50% of the genes with the highest variance were selected for further analysis by two class unpaired SAM (TMEV software) and accepting FDR 14,1%, 35 sequences, including 16 known genes, were found differentially expressed between stromal cells from luminal A vs luminal B breast cancer samples, all of them more expressed in luminal B. Among biological functions enriched in genes found differentially expressed were positive regulation of immune system process, including genes as: ZAP70 (zeta-chain (TCR) associated protein kinase 70kDa); CD38 (CD38 molecule); UBASH3A (ubiquitin associated and SH3 domain containing A); PLA2G7 (phospholipase A2, group VII (platelet-activating factor acetylhydrolase, plasma); NCR3 (natural cytotoxicity triggering receptor 3). Our next step was evaluate whether expression of selected genes was associated with prognosis in another group of patients. Tumor samples from 89 patients with at least 5 years of follow up, all of them estrogen receptor positive and HER2 negative, were selected. Tissue microarray was prepared with stromal tumor compartment from paraffin embedded tumor samples. Fibroblasts were characterized for the expression of 3 fibroblasts markers (alfa-SMA, alpha smooth muscel actin; S100A4 and CAV1, caveolin 1), and ZAP70. Correlation of expression of these markers with prognostic variables was determined. Expression of alfa-SMA, S100A4 and CAV1 was detected in fibroblasts from all tumor samples in different proportions, however no differential expression was observed between luminal A and B tumors. Neither difference was detected on the expression of these proteins in relation with histological grade, lymph node involvement and clinical stage. Conclusion: A differential expression of 16 genes involved in immune process was found, all of them more expressed in fibroblasts from luminal B as compared with luminal A tumors
Seifert, Michael, Khalil Abou-El-Ardat, Betty Friedrich, Barbara Klink, and Andreas Deutsch. "Autoregressive Higher-Order Hidden Markov Models: Exploiting Local Chromosomal Dependencies in the Analysis of Tumor Expression Profiles." Public Library of Science, 2014. https://tud.qucosa.de/id/qucosa%3A28671.
Повний текст джерелаKennedy, Brian Michael Kennedy. "Leveraging Multimodal Tumor mRNA Expression Data from Colon Cancer: Prospective Observational Studies for Hypothesis Generating and Predictive Modeling." The Ohio State University, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=osu1498742562364379.
Повний текст джерелаHabla, Christiane. "Der Einfluss von Relaxin auf das Wachstum von Mammakarzinomen." Doctoral thesis, Universitätsbibliothek Leipzig, 2010. http://nbn-resolving.de/urn:nbn:de:bsz:15-qucosa-37922.
Повний текст джерелаNataša, Prvulović Bunović. "Дигитална мамографија и томосинтеза у детекцији и радиолошкој БИ РАДС категоризацији туморских лезија дојке". Phd thesis, Univerzitet u Novom Sadu, Medicinski fakultet u Novom Sadu, 2015. http://www.cris.uns.ac.rs/record.jsf?recordId=92756&source=NDLTD&language=en.
Повний текст джерелаCilj ove studije je da se uporedi dijagnostička značajnost 2D i 2D+3D mamografije u detektovanju tumora dojke. Ispitivali smo 864 dojki u 740 pacijentkinja. Studija je sprovedena u toku rutinskog rada u Centru za imidžing dijagnostiku Institutu za onkologiju Vojvodine. 2D + 3D mamografija su načinjene pojedinačno ili u istom aktu snimanja kao kombo opcija na Selenia Dimensions aparatu proizvođača firme Holodžik. Radiološki izvešataji su klasifikovani u kategorije 1-5 prema ACR BI RADS-u. Patohistološka verifikacija je vršena u svih suspektnih promena ili u toku njihovog praćenja . Sve pacijentkinje sa urednim nalazom ili mamografski uočenih benignih promena su radiološki praćene najkraće tokom 2 godine. Uočeno je 103 maligne lezije u dojkama klasifikovanih kao BI RADS 4, 5 na digitalnoj mamografiji i u 22 dojke čije su promene klasifikovane kao BI RADS 1-3, tokom praćenja ili pregleda dojki pomoću drugih modaliteta. Na 2D + 3D mamografiji malignite je potvrđen u 125 dojke od kojih je 118 klasifikovano kao BI RADS 4,5 i u 7 dojki čuje su promene kategorisane u BIRADS 1-3. Postoji statistički značajna razlika u distribuciji malignih nalaza u odnosu na podgrupe Studija je pokazala 20% lažno negativnih nalaza na 2D, a 5,6% na 2D + 3D modalitetu pregleda dojki. Osetljivost u otkrivanju raka u ovoj studiji iznosi 82,4% na 2D i 94,4% na 2D+3D metodi pregleda, dok je specifičnost 90,5% i 92,0%, respektivno. PPV je veća za 2D + 3D tehniku pregleda , iznosi 66,7%, kao i negativna prediktivna vrednost koja iznosi 99,0%. U 172 slučaja (19, 9%) nalazi 2D mamografije se ne uočavaju na 3D tehnici pregleda i smatraju se posledicom strukturne ili anatomske „buke“. Većina ne -stalnih nalaza (85%) je klasifikovano kao fokalna asimetrija. U ovoj studiji 500 dojki je klasifikovano prema ACR strukturi u masne (ACR 1) ili difuzne fibro-glandularne (ACR 2), a preostalih 264 je bilo heterodenzno (ACR 3) i značajno denzno (ACR 4). Statistički značajna razlika nije pokazana prilikom distribucije malignih nalaza u poređenju sa podgrupama dojki načinjenim prema njihovoj gustini - skladu sa pravilima ACR-a. Ukupna tačnost testa iznosi 89,4% za 2D i 92,4% za 2D + 3D mamografiju. Prediktivne vrednosti dobijene za 2D + 3D mamografiju su bolje od onih koje se odnose samo na 2D mamografiju, što je rezultat njene veće osetljivosti i šire mogućnosti karakterizacije promena. Varijabilnost u interpretaciji nalaza među dva radiologa je je niska, pokazano je slaganje u interšpretavciji evaluiranih mamograma u 94.1% slučajeva.
The aim of this study was to compare diagnostic importance of 2D and 2D+3D diagnostic mammography in breast tumor detection. We evaluated 864 breasts in 740 patients. Study was performed in Diagnostic Imaging Center at Oncology Institute of Vojvodina. 2D+3D mammography were performed during single procedure or via combo option at Selenia Dimensions unit, Hologic, BE. Radiological findings were classified in categories 1-5 according to ACR BIRADS. Pathohistologic verification was obtained in all suspicious findings or after follow up studies. All other patients with mammographic normal findings or benign findings were fallowed up during 2 years period or longer. We detected malignant lesions in 103 breasts classified as BIRADS 4,5 at digital mammography, and in 22 breasts classified as BIRADS 1-3 after followed up or diagnosed by other imaging modalities. At 2D+3D mammography malignancy was confirmed in 125 breasts, 118 classified as BIRADS 4,5 and in 7 breasts classified as BIRADS 1-3. There is statistically significant difference (p<0.001) in distribution of malignant findings compared to the subgroups classified according to 2D mammography. There was 20% false negative findings on 2D, and 5.6% on 2D+3D modality. Sensitivity in cancer detection in this study is 82.4% and 94.4% for 2D and 2D+3D mammography, while specificity is 90.5% and 92.0%, respectively. PPV is higher for 2D+3D technique (66.7%), as well as negative predictive value (99.0%). In 172 cases (19, 9%) 2D mammography findings did not persist on 3D mammography and were considered as structural or anatomical noise. The majority of the non-persistent findings (85%) were classified as asymmetric focal density. In this study 500 breast were classified according to ACR as fatty (ACR 1) or scattered fibroglandular densities (ACR 2), and the remaining 264 had heterogeneously (ACR 3) and extremely dense breasts (ACR 4). Statistically significant difference (p<0.001) was not shown in distribution of malignant findings compared to the subgroups of density structure according to ACR. Overall accuracy of the test was 89.4% and 92.4% for 2D and 2D+3D mammography, respectively. Predictive values obtained in 2D+ 3D mammography are better than those for 2D mammography alone, as a result of its higher sensitivity and better possibility of lesion characterization. Interobserver variability is low, there is an agreement between two radiologist between two radiologic interpretations in 94.1% cases.
McGarry, Gregory John. "Model-based mammographic image analysis." Thesis, Queensland University of Technology, 2002.
Знайти повний текст джерелаLiebscher, Steffi. "Die Bedeutung von VEGF-C und NRP-2 für die Strahlenresistenz im Prostatakarzinom." Doctoral thesis, Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2017. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-222372.
Повний текст джерелаBackground In addition to radical prostatectomy, radiotherapy is a standard therapy for the treatment of prostate tumours and leads to good results for local tumour control and survival. However, as with the resection, the risk of recurrence for advanced tumours is relatively high compared to tumours in earlier stages. Therefore, there is a high urgency to improve radiotherapy especially for advanced stages. One approach is the combination of irradiation with molecular therapies. The aim is to block certain target proteins to increase the radiosensitivity of the prostate carcinoma cells. A potential target could be the blockade of the VEGF-C/NRP-2/Akt signalling pathway (VEGF-C – vascular endothelial growth factor C; NRP-2 – neuropilin 2; Akt – protein kinase B). In prostate cancer the concentrations of VEGF-C and NRP-2 are increased compared to normal prostate cells. Studies have shown that both proteins have a progressive effect on tumourigenesis. In preliminary work Muders et al. (2009) also showed the activation of Akt via the VEGF-C/NRP-2 axis and a resistance to H2O2 induced oxidative stress. Akt also has a protective effect against irradiation in various tumour entities. It is assumed that this also applies to prostate carcinoma cells. Aim of the study Within the framework of this thesis, it was investigated whether and via which mechanism VEGF-C, NRP-2, and Akt affect the radioresistance in prostate carcinoma cell lines. Methods In vitro and in vivo experiments were performed in the human prostate carcinoma cell lines PC-3, DU145, LNCaP, as well as in PC-3 xenografts. The influence of VEGF-C and NRP-2 on the radioresistance was examined in vitro after knock down of the corresponding genes using siRNA or after supplementation with human recombinant VEGF-C in colony formation assays. In order to determine the influence of VEGF-C and NRP-2 on possible cell survival mechanisms, the autophagic flux was examined after the blockade of autophagy with bafilomycin A1 using western blot, the DNA double strand break repair by quantification of the γH2AX foci, and the cell cycle distribution by flow cytometry. The signal transduction of VEGF-C via Akt as well as, as a further possibility, the signal transduction via ERK1/2 were tested after siRNA transfection with and without irradiation using western blot. Further experiments on Akt were performed in vitro and in vivo with the PI3K/Akt inhibitor nelfinavir in PC-3 cells. The in vitro effect of nelfinavir on radioresistance was tested using a colony formation assay after treatment of the cells with 10 μM nelfinavir. In vivo, the effect of nelfinavir without and in combination with irradiation in PC-3 xenografts was investigated in nude mice. For the determination of the tumour growth time, the mice were treated with 80 mg nelfinavir/kg body weight 30 times within 6 weeks. In a further experiment, the local tumour control was determined with simultaneous fractionated irradiation with total doses of 30 to 120 Gy and a follow-up time of 180 days. Results The investigations on radioresistance via the VEGF-C/NRP-2/Akt signalling pathway showed that in the three prostate carcinoma cell lines PC-3, DU145, and LNCaP VEGF-C significantly mediates radioresistance. For NRP-2 however, it was found that, depending on the cell line, it either leads to radioresistance (DU145) or radiosensitization (PC-3). Further, it was shown that in PC-3 and DU145 VEGF-C does not mediate radioresistance via Akt or ERK1/2. The experiments on radioresistance mediating mechanisms revealed that VEGF-C promotes autophagy in untreated PC-3 cells, but NRP-2 does not. Under irradiation, an effect of VEGF-C and NRP-2 on autophagy could not be detected reproducibly. A further experiment has shown that in PC-3 autophagy has no influence on the clonogenic survival after irradiation. In addition, it was found that VEGF-C does not affect the DNA double strand break repair in PC-3. Furthermore, it was shown that a reduction in the VEGF-C content leads to a G2/M arrest in PC-3. However, no effect could be observed in DU145. In studies regarding the influence of Akt on radioresistance independent of VEGF-C and NRP-2, nelfinavir inhibited Akt phosphorylation at Ser473 and minimally affected the clonogenic survival of PC-3 cells. In PC-3 xenografts, nelfinavir did not lead to any tumour growth delay and did not have a radiosensitizing effect in vitro or in vivo. Conclusion In the experiments, it was shown that VEGF-C mediates radioresistance in prostate cancer cells. This finding could serve as a research approach for the development of a combined therapy of a VEGF-C blockade and irradiation. A potential mechanism by which VEGF-C mediates radioresistance is the reverse of the G2/M arrest, depending on the cell line. NRP-2 acts differently in the mediation of radioresistance or radiosensitivity, depending on the cell line. On this, further investigations should be carried out with regard to possible interactions within other signalling pathways with a radiosensitizing influence. Within the investigated signalling pathway, it was further shown that VEGF-C does not mediate radioresistance via Akt. The present work contains the first study examining the effect of nelfinavir in combination with irradiation on prostate cancer cell survival in vitro as well as on growth time and local tumour control in vivo. Herein no radiosensitizing effects of nelfinavir could be detected. Since nelfinavir radiosensitizes cells of other tumour entities and is also known to interfere with a series of signalling pathways that promote or inhibit cell survival, it should be clarified whether tumour cells with a particular genetic profile are more responsive to treatment with nelfinavir
Davis, Shakti K. "Ultrawideband radar-based detection and classification of breast tumors." 2006. http://www.library.wisc.edu/databases/connect/dissertations.html.
Повний текст джерелаRodrigues, Miguel Ângelo Borlão. "Classifying Breast Tumors using Medical Microwave Radar Imaging." Master's thesis, 2021. http://hdl.handle.net/10362/126696.
Повний текст джерелаA Imagem Médica por Microondas (do inglês, MMI) tem sido estudada nos últimos anos de forma a desenvolver técnicas de deteção do cancro da mama nas primeiras fases de desenvolvimento. Em particular, os sistemas de imagem de radar por microondas em banda ultralarga (do inglês UWB) podem detetar e classificar os tumores como benignos ou malignos, uma vez que esta técnica produz informação sobre o tamanho e a forma dos tumores. Neste estudo, utilizámos esta tecnologia para classificar os tumores. A dissertação tem dois objetivos principais. Primeiro, produzir fantomas de tumores mamários e utilizá-los em simulações de MMI em 2D que recriam as condições de um sistema de imagem de radar por microondas UWB. Os fantomas numéricos de tumores mamários produzidos possuem morfologias semelhantes a tumores reais, uma vez que são feitos a partir de segmentações de exames de ressonância magnética da mama. Em segundo lugar, as reflexões dos sinais de microondas UWB produzidos pelas simulações de MMI foram utilizados para classificar tumores de acordo com o seu tamanho e histologia, o que é relevante para avaliar o potencial dos sistemas de imagem de radar por microondas UWB como um método alternativo e fiável para a classificação de tumores mamários no campo da MMI. Os Algo-ritmos de Classificação utilizados neste trabalho foram a Pseudo Linear Discriminant Analysis (Pseudo-LDA), Pseudo Quadratic Discriminant Analysis (pseudo-QDA), e a K-Nearest Neighbors (KNN), jun-tamente com um algoritmo de extração de features - Análise de Componentes Principais (do inglês PCA).
Liao, Chi-Jou, and 廖綺柔. "Using Convolutional Neural Network Auto-encoder in Breast Tumors Classification and Detection Compare with Traditional Ultrasound BIRADS." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/tfz345.
Повний текст джерелаSu, Yu-Cheng, and 蘇育成. "Improvement in Ultrasound Breast Tumor Images Classification by A Support Vector Machine with Outliers Detection." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/59507762821199926008.
Повний текст джерела長庚大學
資訊管理研究所
94
According to the statistics from the Department of Health, breast cancer is still on the top-5 list of the cause of death. Hence, regular health check and set up of a computer-aided diagnosis system is of great urgency. Owing to the shape of a benign tumor is quite different from a malignant tumor and is relatively stable that comparing with conventional features like texture, so it is not affected with different type of scanners. In this thesis, we classify a tumor according to its shape feature. The result shows that the classification result is good and the accuracy is 89.05%. Furthermore, we use a support vector machine (SVM) as the classifier. A traditional SVM is sensitive to the outlier in the samples. It affects the location of the decision hyper-plane and decreases the accuracy. Hence, we propose an effective method to solve this problem and will improve the performance of the SVM. The experiment shows that the proposed method successfully reduces the influence of the outliers and promotes the classification accuracy of a SVM form 89.05% to 91.43%.
Peralta, Inês Leão Saldanha Rios. "Tumores mamários em cadelas: fatores de prognóstico." Master's thesis, 2018. http://hdl.handle.net/10400.26/24488.
Повний текст джерелаCanine mammary tumors (TMC) are considered the most frequent neoplasia in female dogs. Different studies indicate that about 50% of bitches with breast tumors have benign breast tumors, and 50% have malignant tumors. The clinical evolution of malignant tumors varies widely, with disease-free time and survival time ranging from a few months to several years. The main risk factors associated with CMD are age, breed, exposure to gonad hormones or analogues, age of ovariohysterectomy and obesity. The tumor-nodes-metastasis (TNM) classification, the clinical stage and histological classification, the histological grade of Nottingham's malignancy, the type of surgery and serum and tissue biomarkers are currently considered the most important prognostic factors. In recent years, serum and tissue biomarkers have been increasingly studied as they may contribute decisively to the approach to TMC. The most studied tissue markers are the sex hormone receptors- estrogen and progesterone receptors; the expression of human epidermal growth factor receptor 2 (HER-2 / neu); the breast cancer susceptibility gene 1 (BRCA1); p53 and E-cadherin. Serum markers that may have utility or prognostic value are carcinoembryonic antigen (CA15-3), Interleukin 8 and 10, TK1, lactate dehydrogenase (LDH), Mamoblobin B, mucin 1 (MUC1), and CAN SINE (single intercalated nuclear elements) sequences. There are also some studies on proliferation markers – argyrophilic nucleolar organizer region (AgNOR), proliferating cell nuclear antigen (PCNA) and Ki-67; the COX-2 enzyme; the kinase dependent cycle inhibitors - p16, p21 and p27; the TP53 gene; and the carcinoembryonic antigen (CEA) glycoprotein. This subject is of high relevance due to the high incidence of this type of tumor in dogs, and the clinical implications it may present. In addition, bitch mammary tumors have also been used as spontaneous biological models of mammary tumors in humans. The present study is a review of existing prognostic factors, taking into account the documented utility of these as a prognostic factor, since they have an influence on the treatment of neoplasia.
Müller, Franziska. "Hochauflösende Ultraschallverfahren und Doppler-Sonographie zur Mammadiagnostik bei der Hündin: High-resolution and Doppler methods in sonography of the mammary gland of the bitch." Doctoral thesis, 2009. https://ul.qucosa.de/id/qucosa%3A11014.
Повний текст джерелаIn 53 bitches that underwent surgery because of tumors of the mammary gland at the Department of small animal medicine of the University of Leipzig we carried out a preoperative ultrasonographic examination of the mammary gland. Furthermore eight pregnant and one lactating bitch were examined the same way. We aimed to find out, whether high-resolution ultrasound helps differentiate benign from malignant tumors. Also we wanted to evaluate criteria established for that purpose in human medicine. Use of colour-coded duplex sonography, resistance index and pulsatility index for this question are reassessed too. The total number of mammary complexes examined for this study is 114. A GE Logiq™ 9 with a 14 MHz linear array transducer was used for all examinations. Seventy of the 114 sites of mammary tissue underwent a colour-coded duplex sonography after the B scan. Blood vessels were detectet in 70 of the tumors. In 47 of these sites the PW-Doppler was used to gain flow patterns to achieve resistance- and pulsatility-index. The images were analysed retrospectively. In B scan images lesions were judged by 12 parameters. Additional information about number, diameter and distribution of vessels within a tumor was taken from the images of colour-coded duplex sonography. The excised complexes were evaluated pathohistologically. Only descriptive statistical analysis was possible because the resulting groups were very small after being sorted according to WHO-classification. Therefore the complexes of mammary glands were subsumpted into two groups – „malignant“ and „benign“ tumours. An irregular contour of the tumor (32 of 61 malignant, 4 of 48 benign tumors), signal enhancement (36/61 malignant, 9/48 benign tumors) or total shadowing (8/61 malignant, 0/48 benign tumors) behind the tumor, calcification (20/61 malignant, 6/48 benign tumors) and irregular vessel diameters (25/61 malignant, 12/48 benign tumors) are signs of malignancy. Tumors that miss a clearly detactable borderline (15/61 malignant, 36/48 benign tumors) and tumors with no signal alteration behind the tumor (17/61 malignant, 39/48 benign tumors) are benign more often. The combination of parameters reduces the number of adequate tumors and rises significance. A tumor showing an irregular contour and calcification (13/61 malignant, 1/48 benign tumors) is more likely to be malignant as well as a tumor of medium echodensity showing signal enhancement (21/61 malignant, 6/48 benign tumors). Tumors of medium echodensity without signal alteration behind the lesion (13/61 malignant, 33/48 benign tumors) and tumors with diffusely distributed vessels of regular diameter (3/36 malignant, 14/29 benign tumors) are more likely to be benign. It could be shown that high-resolution B scan parameters can help differentiate between malignant and benign tumors of the mammary gland, especially if they are used in combination with each other. Parameters from colour-coded duplex sonography can increase predicting value of B scan examinations too but there is no use of analysing resistance index or pulsatility index. One of the criteria established in human medicine ist the contour of a tumor. This parameter is of diagnostic use in mammary tumours of the bitch too. It is not possible to clearly predict the character of a tumor of the mammary gland of a bitch by only a few parameters based on a sonogram but sonographic examination can be helpful for assessing prognosis sometimes.