Dissertation/Thesis Abstract

Deep Learning for Digital Histopathology across Multiple Scales
by Hou, Le, Ph.D., State University of New York at Stony Brook, 2019, 177; 27670274
Abstract (Summary)

Histopathology is the study of tissue changes caused by diseases such as cancer. It plays a crucial role in disease diagnosis, survival analysis, and development of new treatments. Using computer vision techniques, I focus on multiple tasks for automated analysis in digital histopathology images, which are challenging because histopathology images are heterogeneous and complex, due to the large variation of hundreds of cancer types in gigapixel resolution. In this thesis, I show how histopathology image analysis tasks can be viewed in three scales: Whole Slide Image (WSI)-level, patch-level, and cellular-level, and I present my contributions in each resolution level.

WSI-level analysis such as classifying WSIs into cancer types is challenging, because conventional classification methods such as off-the-shelf deep learning models cannot be applied directly on gigapixel WSIs due to computational limitations. I contribute a patch-based deep learning method that classifies gigapixel WSIs into cancer types and subtypes with close-to-human performance. This method is useful for computer-aided diagnosis. At the patch-level, I contribute a novel method for histopathology image patch classification. On the task of identifying Tumor Infiltrating Lymphocyte (TIL) regions, the prediction result of this method correlates with the survival rate of patients. At the cellular-level, I contribute novel methods for nucleus classification and roundness regression, which are interpretable features for histopathology studies. With this method, I generated a large-scale dataset of segmented nuclei, in WSIs from a large publicly available digital histopathology image dataset, to help advance histopathology research.

Indexing (document details)
Advisor: Samaras, Dimitris
Commitee: Samaras, Dimitris, Saltz, Joel H, Nguyen, Minh Hoai, Jojic, Nebojsa
School: State University of New York at Stony Brook
Department: Computer Science
School Location: United States -- New York
Source: DAI-B 81/9(E), Dissertation Abstracts International
Source Type: DISSERTATION
Subjects: Pathology
Keywords: Deep learning, Digital pathology, Medical image analysis
Publication Number: 27670274
ISBN: 9781658470292
Copyright © 2020 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest