Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2511.06266 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915622134218752 |
|---|---|
| author | Sekhar, Ardhendu Soni, Vasu Aske, Keshav Madnoorkar, Shivam Jeevan, Pranav Sethi, Amit |
| author_facet | Sekhar, Ardhendu Soni, Vasu Aske, Keshav Madnoorkar, Shivam Jeevan, Pranav Sethi, Amit |
| contents | Accurate survival prediction from histopathology whole-slide images (WSIs) remains challenging due to their gigapixel resolution, strong spatial heterogeneity, and complex survival distributions. We introduce a comprehensive computational pathology framework that addresses these limitations through four complementary innovations: (1) Quantile-Gated Patch Selection for dynamically identifying prognostically relevant regions, (2) Graph-Guided Clustering to group patches by spatial and morphological similarity, (3) Hierarchical Context Attention to model both local tissue interactions and global slide-level context, and (4) an Expert-Driven Mixture of Log-Logistics module that flexibly models complex survival distributions. Across large TCGA cohorts, our method achieves state-of-the-art performance, yielding time-dependent concordance indices of 0.644 on LUAD, 0.751 on KIRC, and 0.752 on BRCA, consistently outperforming both histology-only and multimodal baselines. The framework further provides improved calibration and interpretability, advancing the use of WSIs for personalized cancer prognosis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06266 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spatially-Aware Mixture of Experts with Log-Logistic Survival Modeling for Whole-Slide Images Sekhar, Ardhendu Soni, Vasu Aske, Keshav Madnoorkar, Shivam Jeevan, Pranav Sethi, Amit Computer Vision and Pattern Recognition Accurate survival prediction from histopathology whole-slide images (WSIs) remains challenging due to their gigapixel resolution, strong spatial heterogeneity, and complex survival distributions. We introduce a comprehensive computational pathology framework that addresses these limitations through four complementary innovations: (1) Quantile-Gated Patch Selection for dynamically identifying prognostically relevant regions, (2) Graph-Guided Clustering to group patches by spatial and morphological similarity, (3) Hierarchical Context Attention to model both local tissue interactions and global slide-level context, and (4) an Expert-Driven Mixture of Log-Logistics module that flexibly models complex survival distributions. Across large TCGA cohorts, our method achieves state-of-the-art performance, yielding time-dependent concordance indices of 0.644 on LUAD, 0.751 on KIRC, and 0.752 on BRCA, consistently outperforming both histology-only and multimodal baselines. The framework further provides improved calibration and interpretability, advancing the use of WSIs for personalized cancer prognosis. |
| title | Spatially-Aware Mixture of Experts with Log-Logistic Survival Modeling for Whole-Slide Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.06266 |