Graduation Semester and Year
2022
Language
English
Document Type
Dissertation
Degree Name
Doctor of Philosophy in Computer Science
Department
Computer Science and Engineering
First Advisor
Junzhou Huang
Abstract
Digital Pathology (DP) has been recently used in replacement to traditional microscopy samples as it easy to navigate and can be analysed, processed and saved. With the invention of Digital pathology, there has been exponential increase of automated process to make the life of Doctors easier. One such automated process is Artificial Intelligence (AI) where the AI is used as an assistant to Humans and to make the analysis and guide the experts. With the advent of AI and in particular Deep Learning, research has been divided and focused to solve multiple problems in Digital Pathology. One such important application is to analyse the Whole Slide images (WSIs) of patients and predict Cancer stages for the patient. This is crucial because the WSIs becomes too many which requires Expert knowledge and time consuming job. This make a perfect application where Deep learning can be used. In this dissertation, we address the problem of identifying WSIs of patients and predict the cancer stages. We further identify several important observations to improve the performance of WSIs. We extract the granular details of the WSIs and capture the spatial relationship of granular features. We use these Graph of granualr features to further classify the cancer stages of patients. We conduct several experiments to prove our work experimentally and make conclusion that the proposed work can be used to predict cancer stages.
Keywords
Cancer staging, Whole slide image, Histology image, Segmentation
Disciplines
Computer Sciences | Physical Sciences and Mathematics
License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Recommended Citation
Raju, Ashwin, "Towards high performance cancer staging from histology images" (2022). Computer Science and Engineering Dissertations. 282.
https://mavmatrix.uta.edu/cse_dissertations/282
Comments
Degree granted by The University of Texas at Arlington