Generating Region of Interests for Invasive Breast Cancer in Histopathological Whole-Slide-Image

• Type of Material: Article
• Authors: Shreyas Patil, Georgia Institute of Technology; Li Tong, Georgia Institute of Technology; Dongmei Wang, Emory University
• Language: English
• Date: 2020-01-01
• Publisher: IEEE
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © Copyright 2022 IEEE - All rights reserved.
• Final Published Version (URL): http://dx.doi.org/10.1109/COMPSAC48688.2020.0-174
• Title of Journal or Parent Work: 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC)
• Volume: 2020
• Start Page: 723
• End Page: 728
• Grant/Funding Information: This work was supported in part by the scholarship from China Scholarship Council (CSC) under the Grant CSC NO. 201406010343. The content of this article is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.; The work was supported in part by grants from the National Science Foundation EAGER Award NSF1651360, Children’s Healthcare of Atlanta and Georgia Tech Partnership Grant, Giglio Breast Cancer Research Fund, Georgia Tech Petit Institute Faculty Fellow, and Carol Ann and David D. Flanagan Faculty Fellow Research Fund.
• Keywords: Science & Technology; CNN; Pathology; Deep Learning; Computer Science, Interdisciplinary Applications; Computer Science, Software Engineering; Whole-Slide-Image; Computer Science; Grade; ROI Segmentation; Technology; Invasive Breast Cancer
• Research Categories: Health Sciences, Radiology; Computer Science; Health Sciences, Oncology; Engineering, Biomedical

Abstract

The detection of the region of interests (ROIs) on Whole Slide Images (WSIs) is one of the primary steps in computer-aided cancer diagnosis and grading. Early and accurate identification of invasive cancer regions in WSI is critical in the improvement of breast cancer diagnosis and further improvements in patient survival rates. However, invasive cancer ROI segmentation is a challenging task on WSI because of the low contrast of invasive cancer cells and their high similarity in terms of appearance, to non-invasive region. In this paper, we propose a CNN based architecture for generating ROIs through segmentation. The network tackles the constraints of data-driven learning and working with very low-resolution WSI data in the detection of invasive breast cancer. Our proposed approach is based on transfer learning and the use of dilated convolutions. We propose a highly modified version of U-Net based auto-encoder, which takes as input an entire WSI with a resolution of 320x320. The network was trained on low-resolution WSI from four different data cohorts and has been tested for inter as well as intra-dataset variance. The proposed architecture shows significant improvements in terms of accuracy for the detection of invasive breast cancer regions.