Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2510.21479 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918169694699520 |
|---|---|
| author | Huang, Yating Yang, Qijun Xiang, Lintao Yin, Hujun |
| author_facet | Huang, Yating Yang, Qijun Xiang, Lintao Yin, Hujun |
| contents | Accurate interpretation of histopathological images demands integration of information across spatial and semantic scales, from nuclear morphology and cellular textures to global tissue organization and disease-specific patterns. Although recent foundation models in pathology have shown strong capabilities in capturing global tissue context, their omission of cell-level feature modeling remains a key limitation for fine-grained tasks such as cancer subtype classification. To address this, we propose a dual-stream architecture that models the interplay between macroscale tissue features and aggregated cellular representations. To efficiently aggregate information from large cell sets, we propose a receptance-weighted key-value aggregation model, a recurrent transformer that captures inter-cell dependencies with linear complexity. Furthermore, we introduce a bidirectional tissue-cell interaction module to enable mutual attention between localized cellular cues and their surrounding tissue environment. Experiments on four histopathological subtype classification benchmarks show that the proposed method outperforms existing models, demonstrating the critical role of cell-level aggregation and tissue-cell interaction in fine-grained computational pathology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_21479 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ITC-RWKV: Interactive Tissue-Cell Modeling with Recurrent Key-Value Aggregation for Histopathological Subtyping Huang, Yating Yang, Qijun Xiang, Lintao Yin, Hujun Computer Vision and Pattern Recognition Accurate interpretation of histopathological images demands integration of information across spatial and semantic scales, from nuclear morphology and cellular textures to global tissue organization and disease-specific patterns. Although recent foundation models in pathology have shown strong capabilities in capturing global tissue context, their omission of cell-level feature modeling remains a key limitation for fine-grained tasks such as cancer subtype classification. To address this, we propose a dual-stream architecture that models the interplay between macroscale tissue features and aggregated cellular representations. To efficiently aggregate information from large cell sets, we propose a receptance-weighted key-value aggregation model, a recurrent transformer that captures inter-cell dependencies with linear complexity. Furthermore, we introduce a bidirectional tissue-cell interaction module to enable mutual attention between localized cellular cues and their surrounding tissue environment. Experiments on four histopathological subtype classification benchmarks show that the proposed method outperforms existing models, demonstrating the critical role of cell-level aggregation and tissue-cell interaction in fine-grained computational pathology. |
| title | ITC-RWKV: Interactive Tissue-Cell Modeling with Recurrent Key-Value Aggregation for Histopathological Subtyping |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.21479 |