Unified Multi-Foundation-Model Slide Representation for Pan-Cancer Recognition and Text-Guided Tumor Localization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917434273824768 |
|---|---|
| author | Wang, Tianyang Su, Ziyu Akbar, Abdul Rehman Sajjad, Usama Gokhale, Lina Rabolli, Charles Chen, Wei Parwani, Anil Niazi, Muhammad Khalid Khan |
| author_facet | Wang, Tianyang Su, Ziyu Akbar, Abdul Rehman Sajjad, Usama Gokhale, Lina Rabolli, Charles Chen, Wei Parwani, Anil Niazi, Muhammad Khalid Khan |
| contents | The expanding ecosystem of pathology foundation models has produced powerful but fragmented tile-level representations, limiting their use in clinical tasks that require unified slide-level reasoning and interpretable linkage to clinically meaningful information. We present ASTRA, a pan-cancer framework that integrates heterogeneous foundation-model representations into a shared slide-level representation space and semantically grounds that space using structured pathology annotation fields, including classification category, cancer type, and anatomic site. ASTRA combines sparse mixture-of-experts contextualization, masked multi-model reconstruction, and contrastive alignment to structured pathology prompts to learn slide representations that support 4-category classification, 3-class solid tumor typing, 16-class cancer typing, and text-guided tumor localization without pixel-level supervision. Developed on a CHTN cohort of 10,359 whole-slide images (WSIs) spanning 16 tumor types, ASTRA consistently improves pan-cancer classification across four pathology foundation-model backbones, achieving up to 97.8% macro-AUC for 4-category classification, 99.7% for 3-class solid tumor typing, and 99.2% for 16-class cancer typing. For tumor localization, ASTRA achieves a mean Dice of 0.897 on an annotated in-domain CHTN subset (n = 380) spanning 16 cancer types and 0.738 on an external TCGA cohort (n = 1,686) spanning four cancer types. These results demonstrate that minimal structured pathology annotation fields derived from slide-level metadata can provide effective semantic supervision for unified slide representation learning, enabling both pan-cancer prediction and weakly supervised tumor localization within a single framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22846 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unified Multi-Foundation-Model Slide Representation for Pan-Cancer Recognition and Text-Guided Tumor Localization Wang, Tianyang Su, Ziyu Akbar, Abdul Rehman Sajjad, Usama Gokhale, Lina Rabolli, Charles Chen, Wei Parwani, Anil Niazi, Muhammad Khalid Khan Computer Vision and Pattern Recognition The expanding ecosystem of pathology foundation models has produced powerful but fragmented tile-level representations, limiting their use in clinical tasks that require unified slide-level reasoning and interpretable linkage to clinically meaningful information. We present ASTRA, a pan-cancer framework that integrates heterogeneous foundation-model representations into a shared slide-level representation space and semantically grounds that space using structured pathology annotation fields, including classification category, cancer type, and anatomic site. ASTRA combines sparse mixture-of-experts contextualization, masked multi-model reconstruction, and contrastive alignment to structured pathology prompts to learn slide representations that support 4-category classification, 3-class solid tumor typing, 16-class cancer typing, and text-guided tumor localization without pixel-level supervision. Developed on a CHTN cohort of 10,359 whole-slide images (WSIs) spanning 16 tumor types, ASTRA consistently improves pan-cancer classification across four pathology foundation-model backbones, achieving up to 97.8% macro-AUC for 4-category classification, 99.7% for 3-class solid tumor typing, and 99.2% for 16-class cancer typing. For tumor localization, ASTRA achieves a mean Dice of 0.897 on an annotated in-domain CHTN subset (n = 380) spanning 16 cancer types and 0.738 on an external TCGA cohort (n = 1,686) spanning four cancer types. These results demonstrate that minimal structured pathology annotation fields derived from slide-level metadata can provide effective semantic supervision for unified slide representation learning, enabling both pan-cancer prediction and weakly supervised tumor localization within a single framework. |
| title | Unified Multi-Foundation-Model Slide Representation for Pan-Cancer Recognition and Text-Guided Tumor Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.22846 |