Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Metastasis detection and localization in lypmh nodes by using convolutional neural networks
Date
2016
Author
Öner, Mustafa Ümit
Metadata
Show full item record
Item Usage Stats
89
views
0
downloads
Cite This
Breast cancer digital histopathology is a new application area of deep learning. Breast cancer was the leading cause of cancer death among women with 15.1% death rate among all cancer deaths in the world in 2012. Insufficient number of pathologists is one of the key factors in that situation. There were 5.7 pathologists per 100.000 people in USA in 2013 and this value was 1.56 in Turkey in 2011. It is possible to increase the number of slide analysis made by the pathologists within the same period by developing deep learning based systems to assist them. In this thesis, a convolutional neural networks based system is introduced. This system accepts the whole slide images of lymph node excisions from breast cancer patients as input and detects and localizes metastasis regions on these images automatically. In this system, performance values of 0.9259 and 0.8669 for slide-based evaluation and 0.5349 and 0.4060 values for the lesion based evaluation are achieved on CAMELYON16 training and test sets, respectively.
Subject Keywords
Neural networks (Computer science).
,
Artificial intelligence.
,
Machine learning.
,
Breast
,
Metastasis.
URI
http://etd.lib.metu.edu.tr/upload/12620460/index.pdf
https://hdl.handle.net/11511/25950
Collections
Graduate School of Natural and Applied Sciences, Thesis
Suggestions
OpenMETU
Core
Quality Enhancement of Computed Tomography Images of Porous Media Using Convolutional Neural Networks
Yıldırım, Ertuğrul Umut; Uğur, Ömür; Glatz, Guenther; Department of Scientific Computing (2022-2-11)
Computed tomography has been widely used in clinical and industrial applications as a non-destructive visualization technology. The quality of computed tomography scans has a strong effect on the accuracy of the estimated physical properties of the investigated sample. X-ray exposure time is a crucial factor for scan quality. Ideally, long exposure time scans, yielding large signal-to-noise ratios, are available if physical properties are to be delineated. However, especially in micro-computed tomography ap...
Comparison of GST Isoenzyme Expression in Normal and Neoplastic Breast Tissue: Correlation with Clinical and Prognostic Factors
OĞUZTÜZÜN, SERPİL; İşcan, Mesude; ÖZHAVZALI, MÜZEYYEN; Sak, Serpil Dizbay (2009-01-01)
Glutathione S-transferases in breast tissue play an important role in the susceptibility to the mutagenic effects of chemical carcinogens and in the response of breast tumors to chemotherapy. In this study the immunohistochemical staining characteristics of glutathione S-transferase isoenzymes (alpha, mu, pi, and theta) were investigated in invasive duct carcinomas and in normal breast tissue of 43 patients. The relationships between the expression of the GST isoenzymes and some clinicopathological features...
ANDROID BASED PORTABLE CELL COUNTING SYSTEM FOR LABEL FREE QUANTIFICATION OF DEP MANIPULATED CANCER CELLS
Aslan, Mahmut Kamil; Külah, Haluk (2017-06-22)
This paper presents a portable system integrating microfluidic dielectrophoresis (DEP) channel with a CMOS imager for label and lens free detection, and real-time counting of MCF-7 breast cancer cells. The DEP device is designed for trapping the MCF-7 that can simultaneously be imaged using a CMOS sensor. An android application is employed in order to record raw CMOS images. Cells are detected and counted using inbuilt image processing operations of the same application. Average counting accuracy of the sys...
Magnetohydrodynamic flow imaging of ionic solutions using electrical current injection and MR phase measurements
Eroglu, Hasan H.; Sadighi, Mehdi; Eyüboğlu, Behçet Murat (Elsevier BV, 2019-06-01)
In this study, a method is proposed to image magnetohydrodynamic (MHD) flow of ionic solutions, which is caused by externally injected electrical current to an imaging media, during MRI scans. A multi-physics (MP) model is created by using the electrical current, laminar flow, and MR equations. The conventional spoiled gradient echo MRI pulse sequence with bipolar flow encoding gradients is utilized to encode the MHD flow. Using the MP model and the MRI pulse sequence, relationship between the MHD flow rela...
AUTOMATIC SEGMENTATION OF NUCLEI IN HISTOPATHOLOGY IMAGES USING ENCODING-DECODING CONVOLUTIONAL NEURAL NETWORKS
Mercadier, Deniz Sayin; Beşbınar, Beril; Frossard, Pascal (2019-01-01)
Accurate and fast segmentation of nuclei in histopathological images plays a crucial role in cancer research for detection and grading, as well as personal treatment. Despite the important efforts, current algorithms are still suboptimal in terms of speed, adaptivity and generalizability. Popular Deep Convolutional Neural Networks (DCNNs) have recently been utilized for nuclei segmentation, outperforming traditional approaches that exploit color and texture features in combination with shallow classifiers o...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
M. Ü. Öner, “Metastasis detection and localization in lypmh nodes by using convolutional neural networks,” M.S. - Master of Science, Middle East Technical University, 2016.