Dense, high-resolution mapping of cells and tissues from pathology images for the interpretable prediction of molecular phenotypes in cancer
Diao, J. A.; Chui, W. F.; Wang, J. K.; Mitchell, R. N.; Rao, S. K.; Resnick, M. B.; Lahiri, A.; Maheshwari, C.; Glass, B.; Mountain, V.; Kerner, J. K.; Montalto, M. C.; Khosla, A.; Wapinski, I. N.; Beck, A. H.; Taylor-Weiner, A.; Elliott, H.
Show abstract
While computational methods have made substantial progress in improving the accuracy and throughput of pathology workflows for diagnostic, prognostic, and genomic prediction, lack of interpretability remains a significant barrier to clinical integration. In this study, we present a novel approach for predicting clinically-relevant molecular phenotypes from histopathology whole-slide images (WSIs) using human-interpretable image features (HIFs). Our method leverages >1.6 million annotations from board-certified pathologists across >5,700 WSIs to train deep learning models for high-resolution tissue classification and cell detection across entire WSIs in five cancer types. Combining cell- and tissue-type models enables computation of 607 HIFs that comprehensively capture specific and biologically-relevant characteristics of multiple tumors. We demonstrate that these HIFs correlate with well-known markers of the tumor microenvironment (TME) and can predict diverse molecular signatures, including immune checkpoint protein expression and homologous recombination deficiency (HRD). Our HIF-based approach provides a novel, quantitative, and interpretable window into the composition and spatial architecture of the TME.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Pan-cancer classification of single cells in the tumour microenvironment 97%
- Single-Cell RNA Sequencing Reveals the Effects of Chemotherapy on Human Pancreatic Adenocarcinoma and its Tumor Microenvironment 97%
- Spatial domain analysis predicts risk of colorectal cancer recurrence and infers associated tumor microenvironment networks 97%
Similar papers in this journal
- PanIN and CAF Transitions in Pancreatic Carcinogenesis Revealed with Spatial Data Integration 95%
- Integrative, high-resolution analysis of single cell gene expression across experimental conditions with PARAFAC2-RISE 94%
- Automated assignment of cell identity from single-cell multiplexed imaging and proteomic data 94%
Similar papers in this journal
- Predicting the Tumor Microenvironment Composition and Immunotherapy Response in Non-Small Cell Lung Cancer from Digital Histopathology Images 97%
- Generalizing AI-driven Assessment of Immunohistochemistry across Immunostains and Cancer Types: A Universal Immunohistochemistry Analyzer 96%
- Single-Cell Spatial Proteomics Analyses of Head and Neck Squamous Cell Carcinoma Reveal Tumor Heterogeneity and Immune Architectures Associated with Clinical Outcome 95%
Similar papers in this journal
- An Omic and Multidimensional Spatial Atlas from Serial Biopsies of an Evolving Metastatic Breast Cancer 97%
- Determination of permissive and restraining cancer-associated fibroblast (DeCAF) subtypes 97%
- Cell states and neighborhoods in distinct clinical stages of primary and metastatic esophageal adenocarcinoma 96%
Similar papers in this journal
- Generative Adversarial Networks Accurately Reconstruct Pan-Cancer Histology from Pathologic, Genomic, and Radiographic Latent Features 97%
- Biologically relevant integration of transcriptomics profiles from cancer cell lines, patient-derived xenografts and clinical tumors using deep learning 97%
- Charting the transcriptomic landscape of primary and metastatic cancers in relation to their origin and target normal tissues 96%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.