GMAT: Grounded Multi-Agent Clinical Description Generation for Text Encoder in Vision-Language MIL for Whole Slide Image Classification
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_ | 1866918207877545984 |
|---|---|
| author | Quang, Ngoc Bui Lam Binh, Nam Le Nguyen Nguyen, Thanh-Huy Nguyen, Le Thien Phuc Nguyen, Quan Bagci, Ulas |
| author_facet | Quang, Ngoc Bui Lam Binh, Nam Le Nguyen Nguyen, Thanh-Huy Nguyen, Le Thien Phuc Nguyen, Quan Bagci, Ulas |
| contents | Multiple Instance Learning (MIL) is the leading approach for whole slide image (WSI) classification, enabling efficient analysis of gigapixel pathology slides. Recent work has introduced vision-language models (VLMs) into MIL pipelines to incorporate medical knowledge through text-based class descriptions rather than simple class names. However, when these methods rely on large language models (LLMs) to generate clinical descriptions or use fixed-length prompts to represent complex pathology concepts, the limited token capacity of VLMs often constrains the expressiveness and richness of the encoded class information. Additionally, descriptions generated solely by LLMs may lack domain grounding and fine-grained medical specificity, leading to suboptimal alignment with visual features. To address these challenges, we propose a vision-language MIL framework with two key contributions: (1) A grounded multi-agent description generation system that leverages curated pathology textbooks and agent specialization (e.g., morphology, spatial context) to produce accurate and diverse clinical descriptions; (2) A text encoding strategy using a list of descriptions rather than a single prompt, capturing fine-grained and complementary clinical signals for better alignment with visual features. Integrated into a VLM-MIL pipeline, our approach shows improved performance over single-prompt class baselines and achieves results comparable to state-of-the-art models, as demonstrated on renal and lung cancer datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01293 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GMAT: Grounded Multi-Agent Clinical Description Generation for Text Encoder in Vision-Language MIL for Whole Slide Image Classification Quang, Ngoc Bui Lam Binh, Nam Le Nguyen Nguyen, Thanh-Huy Nguyen, Le Thien Phuc Nguyen, Quan Bagci, Ulas Computer Vision and Pattern Recognition Artificial Intelligence Multiple Instance Learning (MIL) is the leading approach for whole slide image (WSI) classification, enabling efficient analysis of gigapixel pathology slides. Recent work has introduced vision-language models (VLMs) into MIL pipelines to incorporate medical knowledge through text-based class descriptions rather than simple class names. However, when these methods rely on large language models (LLMs) to generate clinical descriptions or use fixed-length prompts to represent complex pathology concepts, the limited token capacity of VLMs often constrains the expressiveness and richness of the encoded class information. Additionally, descriptions generated solely by LLMs may lack domain grounding and fine-grained medical specificity, leading to suboptimal alignment with visual features. To address these challenges, we propose a vision-language MIL framework with two key contributions: (1) A grounded multi-agent description generation system that leverages curated pathology textbooks and agent specialization (e.g., morphology, spatial context) to produce accurate and diverse clinical descriptions; (2) A text encoding strategy using a list of descriptions rather than a single prompt, capturing fine-grained and complementary clinical signals for better alignment with visual features. Integrated into a VLM-MIL pipeline, our approach shows improved performance over single-prompt class baselines and achieves results comparable to state-of-the-art models, as demonstrated on renal and lung cancer datasets. |
| title | GMAT: Grounded Multi-Agent Clinical Description Generation for Text Encoder in Vision-Language MIL for Whole Slide Image Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.01293 |