Share Email Print
cover

Proceedings Paper • new

Joint region and nucleus segmentation for characterization of tumor infiltrating lymphocytes in breast cancer
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Histologic assessment of stromal tumor infiltrating lymphocytes (sTIL) as a surrogate of the host immune response has been shown to be prognostic and potentially chemo-predictive in triple-negative and HER2-positive breast cancers. The current practice of manual assessment is prone to intra- and inter-observer variability. Furthermore, the inter-play of sTILs, tumor cells, other microenvironment mediators, their spatial relationships, quantity, and other image-based features have yet to be determined exhaustively and systemically. Towards analysis of these aspects, we developed a deep learning based method for joint region-level and nucleus-level segmentation and classification of breast cancer H&E tissue whole slide images. Our proposed method simultaneously identifies tumor, fibroblast, and lymphocyte nuclei, along with key histologic region compartments including tumor and stroma. We also show how the resultant segmentation masks can be combined with seeding approaches to yield accurate nucleus classifications. Furthermore, we outline a simple workflow for calibrating computational scores to human scores for consistency. The pipeline identifies key compartments with high accuracy (Dice= overall: 0.78, tumor: 0.83, and fibroblasts: 0.77). ROC AUC for nucleus classification is high at 0.89 (micro-average), 0.89 (lymphocytes), 0.90 (tumor), and 0.78 (fibroblasts). Spearman correlation between computational sTIL and pathologist consensus is high (R=0.73, p<0.001) and is higher than inter-pathologist correlation (R=0.66, p<0.001). Both manual and computational sTIL scores successfully stratify patients by clinical progression outcomes.

Paper Details

Date Published: 18 March 2019
PDF: 8 pages
Proc. SPIE 10956, Medical Imaging 2019: Digital Pathology, 109560M (18 March 2019); doi: 10.1117/12.2512892
Show Author Affiliations
Mohamed Amgad, Emory Univ. School of Medicine (United States)
Roche Tissue Diagnostics (United States)
Anindya Sarkar, Roche Tissue Diagnostics (United States)
Chukka Srinivas, Roche Tissue Diagnostics (United States)
Rachel Redman M.D., Roche Diagnostics Information Solutions (United States)
Simrath Ratra, Roche Tissue Diagnostics (United States)
Charles J. Bechert M.D., Roche Diagnostics Information Solutions (United States)
Benjamin C. Calhoun, Robert J, Tomsich Pathology and Laboratory Medicine Institute, Cleveland Clinic (United States)
Karen Mrazeck, Robert J, Tomsich Pathology and Laboratory Medicine Institute, Cleveland Clinic (United States)
Uday Kurkure, Roche Tissue Diagnostics (United States)
Lee A. D. Cooper, Emory Univ. School of Medicine (United States)
Winship Cancer Institute, Emory Univ. (United States)
Georgia Institute of Technology, (United States)
Michael Barnes M.D., Roche Diagnostics Information Solutions (United States)


Published in SPIE Proceedings Vol. 10956:
Medical Imaging 2019: Digital Pathology
John E. Tomaszewski; Aaron D. Ward, Editor(s)

© SPIE. Terms of Use
Back to Top