A panoptic segmentation dataset and deep-learning approach for explainable scoring of tumor-infiltrating lymphocytes

Liu, S; Amgad, M; More, D; Rathore, MA; Salgado, R; Cooper, LAD

Author(s): Liu, S; Amgad, M; More, D; Rathore, MA; Salgado, R; Cooper, LAD;
Details: Publication Year 2024-06-28,Volume 10,Issue #1,Page 52
Journal Title: NPJ Breast Cancer
Publication Type: Research article
Abstract: Tumor-Infiltrating Lymphocytes (TILs) have strong prognostic and predictive value in breast cancer, but their visual assessment is subjective. To improve reproducibility, the International Immuno-oncology Working Group recently released recommendations for the computational assessment of TILs that build on visual scoring guidelines. However, existing resources do not adequately address these recommendations due to the lack of annotation datasets that enable joint, panoptic segmentation of tissue regions and cells. Moreover, existing deep-learning methods focus entirely on either tissue segmentation or cell nuclei detection, which complicates the process of TILs assessment by necessitating the use of multiple models and reconciling inconsistent predictions. We introduce PanopTILs, a region and cell-level annotation dataset containing 814,886 nuclei from 151 patients, openly accessible at: sites.google.com/view/panoptils . Using PanopTILs we developed MuTILs, a neural network optimized for assessing TILs in accordance with clinical recommendations. MuTILs is a concept bottleneck model designed to be interpretable and to encourage sensible predictions at multiple resolutions. Using a rigorous internal-external cross-validation procedure, MuTILs achieves an AUROC of 0.93 for lymphocyte detection and a DICE coefficient of 0.81 for tumor-associated stroma segmentation. Our computational score closely matched visual scores from 2 pathologists (Spearman R = 0.58-0.61, p < 0.001). Moreover, computational TILs scores had a higher prognostic value than visual scores, independent of TNM stage and patient age. In conclusion, we introduce a comprehensive open data resource and a modeling approach for detailed mapping of the breast tumor microenvironment.
Publisher: Springer Nature
Department(s): Laboratory Research
Publisher's Version: https://doi.org/10.1038/s41523-024-00663-1
Open Access at Publisher's Site: https://doi.org/10.1038/s41523-024-00663-1
Terms of Use/Rights Notice: Refer to copyright notice on published article.

Creation Date: 2024-08-06 05:29:24

Last Modified: 2024-08-06 05:31:19