PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational Pathology
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912776997306368 |
|---|---|
| author | Liu, Fengchun Jiang, Songhan Cai, Linghan Wang, Ziyue Zhang, Yongbing |
| author_facet | Liu, Fengchun Jiang, Songhan Cai, Linghan Wang, Ziyue Zhang, Yongbing |
| contents | While Vision-Language Models (VLMs) have achieved notable progress in computational pathology (CPath), the gigapixel scale and spatial heterogeneity of Whole Slide Images (WSIs) continue to pose challenges for multimodal understanding. Existing alignment methods struggle to capture fine-grained correspondences between textual descriptions and visual cues across thousands of patches from a slide, compromising their performance on downstream tasks. In this paper, we propose PathFLIP (Pathology Fine-grained Language-Image Pretraining), a novel framework for holistic WSI interpretation. PathFLIP decomposes slide-level captions into region-level subcaptions and generates text-conditioned region embeddings to facilitate precise visual-language grounding. By harnessing Large Language Models (LLMs), PathFLIP can seamlessly follow diverse clinical instructions and adapt to varied diagnostic contexts. Furthermore, it exhibits versatile capabilities across multiple paradigms, efficiently handling slide-level classification and retrieval, fine-grained lesion localization, and instruction following. Extensive experiments demonstrate that PathFLIP outperforms existing large-scale pathological VLMs on four representative benchmarks while requiring significantly less training data, paving the way for fine-grained, instruction-aware WSI interpretation in clinical practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_17621 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational Pathology Liu, Fengchun Jiang, Songhan Cai, Linghan Wang, Ziyue Zhang, Yongbing Computer Vision and Pattern Recognition While Vision-Language Models (VLMs) have achieved notable progress in computational pathology (CPath), the gigapixel scale and spatial heterogeneity of Whole Slide Images (WSIs) continue to pose challenges for multimodal understanding. Existing alignment methods struggle to capture fine-grained correspondences between textual descriptions and visual cues across thousands of patches from a slide, compromising their performance on downstream tasks. In this paper, we propose PathFLIP (Pathology Fine-grained Language-Image Pretraining), a novel framework for holistic WSI interpretation. PathFLIP decomposes slide-level captions into region-level subcaptions and generates text-conditioned region embeddings to facilitate precise visual-language grounding. By harnessing Large Language Models (LLMs), PathFLIP can seamlessly follow diverse clinical instructions and adapt to varied diagnostic contexts. Furthermore, it exhibits versatile capabilities across multiple paradigms, efficiently handling slide-level classification and retrieval, fine-grained lesion localization, and instruction following. Extensive experiments demonstrate that PathFLIP outperforms existing large-scale pathological VLMs on four representative benchmarks while requiring significantly less training data, paving the way for fine-grained, instruction-aware WSI interpretation in clinical practice. |
| title | PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational Pathology |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.17621 |