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

• Authors: Shreyas Patil, Georgia Institute of Technology; Li Tong, Georgia Institute of Technology; Dongmei Wang, Emory University
• Journal Title: 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC)
• Volume: Volume 2020
• Publisher: IEEE | 2020-01-01, Pages 723-728
• Type of Work: Article | Post-print: After Peer Review
• Publisher DOI: http://doi.org/10.1109/COMPSAC48688.2020.0-174
• Subjects: Health Sciences, Oncology; Health Sciences, Radiology; Computer Science; Engineering, Biomedical
• Keywords: Science & Technology; Technology; Computer Science, Interdisciplinary Applications; Computer Science, Software Engineering; Computer Science; Invasive Breast Cancer; Whole-Slide-Image; Deep Learning; ROI Segmentation; CNN; Pathology; Grade

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.