Date of Submission
Summer 8-20-2019
Degree Type
Thesis
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
Committee Chair/First Advisor
Dr. Mingon Kang
Track
Big Data
Chair
Dr. Dan Chia-Tien Lo
Committee Member
Dr. Chih-Cheng Hung
Committee Member
Dr. Junggab Son
Abstract
Automatic histopathological Whole Slide Image (WSI) analysis for cancer classification has been highlighted along with the advancements in microscopic imaging techniques. However, manual examination and diagnosis with WSIs is time-consuming and tiresome. Recently, deep convolutional neural networks have succeeded in histopathological image analysis. In this paper, we propose a novel cancer texture-based deep neural network (CAT-Net) that learns scalable texture features from histopathological WSIs. The innovation of CAT-Net is twofold: (1) capturing invariant spatial patterns by dilated convolutional layers and (2) Reducing model complexity while improving performance. Moreover, CAT-Net can provide discriminative texture patterns formed on cancerous regions of histopathological images compared to normal regions. The proposed method outperformed the current state-of-the-art benchmark methods on accuracy, precision, recall, and F1 score.
Included in
Applied Statistics Commons, Artificial Intelligence and Robotics Commons, Bioinformatics Commons, Numerical Analysis and Scientific Computing Commons, Software Engineering Commons, Statistical Models Commons, Theory and Algorithms Commons