Spatial proteomics guided by H&E-based AI reveals recurrence-risk niches in triple-negative breast cancer

2026-08-04

AI Summary

This study addresses the lack of spatially resolved molecular interpretation in AI models that predict recurrence risk from H&E images of triple-negative breast cancer. The authors propose an innovative framework that leverages a prognosis-oriented deep learning risk heatmap as an experimental guide to direct laser-capture microdissection and spatial proteomics, thereby enabling precise correlation between morphologically defined high- and low-risk regions and their local molecular states. Evaluated on 156 patients, the model achieved an AUC and C-index of 0.77. Proteomic analysis revealed enrichment of mitotic pathways in high-risk areas and immune-related pathways in low-risk regions. A 13-protein composite signature was identified, which, when combined with H&E-based scoring, improved the C-index from 0.679 to 0.739 and demonstrated robust prognostic value in an independent validation cohort, advancing multiscale, biologically informed biomarker discovery.

Abstract

Deep learning models can predict cancer recurrence from H&E stained slides, but the localized molecular states underlying these predictions remain largely obscured. Here, we developed an outcome informed spatial pathology framework in TNBC that integrates AI generated recurrence risk heatmaps with mass spectrometry based spatial proteomics. In a cohort of 156 patients, distribution based aggregation of high scoring patches achieved an AUC of 0.77 and a C-index of 0.77 in an independent test cohort. Bulk proteomics associated high image derived risk with cell cycle and genome maintenance programs and low risk with immune activation. High and low risk patches coexisted within the same tumor compartment and displayed distinct nuclear and architectural features, revealing intratumoral heterogeneity beyond tissue compartment identity. We then used the heatmaps as coordinate level guides to physically isolate and profile 46 AI defined tumor regions from two recurrence patients. Spatial proteomic profiling revealed a concordant molecular contrast across both patients: mitotic programs were enriched in high risk regions and immune and antigen presentation programs in low risk regions. A 13 protein composite derived from these spatial contrasts showed a trend toward poorer recurrence-free survival with increasing scores in an expanded cohort, while the corresponding transcript based composite stratified recurrence free survival in the independent METABRIC TNBC cohort. Integrating the protein composite with the H&E derived risk score improved the out of bag C-index from 0.679 to 0.739 and enhanced time dependent discrimination at 3 and 5 years. Together, these findings define a new role for outcome trained AI models as spatially explicit experimental guides that connect prognostic morphology with localized molecular states and advance biologically grounded, multiscale biomarker discovery in TNBC.

Problem

• spatial proteomics
• triple-negative breast cancer
• cancer recurrence
• intratumoral heterogeneity
• AI-guided pathology

Innovation

• spatial proteomics
• AI-guided pathology
• intratumoral heterogeneity
• recurrence risk prediction
• multiscale biomarker