Evidence-based diagnostic reasoning with multi-agent copilot for human pathology

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Weishaupt, Luca L., Chen, Chengkuan, Williamson, Drew F. K., Chen, Richard J., Jaume, Guillaume, Ding, Tong, Chen, Bowen, Vaidya, Anurag, Le, Long Phi, Lu, Ming Y., Mahmood, Faisal
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915892943650816
author Weishaupt, Luca L.
Chen, Chengkuan
Williamson, Drew F. K.
Chen, Richard J.
Jaume, Guillaume
Ding, Tong
Chen, Bowen
Vaidya, Anurag
Le, Long Phi
Jaume, Guillaume
Lu, Ming Y.
Mahmood, Faisal
author_facet Weishaupt, Luca L.
Chen, Chengkuan
Williamson, Drew F. K.
Chen, Richard J.
Jaume, Guillaume
Ding, Tong
Chen, Bowen
Vaidya, Anurag
Le, Long Phi
Jaume, Guillaume
Lu, Ming Y.
Mahmood, Faisal
contents Pathology is experiencing rapid digital transformation driven by whole-slide imaging and artificial intelligence (AI). While deep learning-based computational pathology has achieved notable success, traditional models primarily focus on image analysis without integrating natural language instruction or rich, text-based context. Current multimodal large language models (MLLMs) in computational pathology face limitations, including insufficient training data, inadequate support and evaluation for multi-image understanding, and a lack of autonomous, diagnostic reasoning capabilities. To address these limitations, we introduce PathChat+, a new MLLM specifically designed for human pathology, trained on over 1 million diverse, pathology-specific instruction samples and nearly 5.5 million question answer turns. Extensive evaluations across diverse pathology benchmarks demonstrated that PathChat+ substantially outperforms the prior PathChat copilot, as well as both state-of-the-art (SOTA) general-purpose and other pathology-specific models. Furthermore, we present SlideSeek, a reasoning-enabled multi-agent AI system leveraging PathChat+ to autonomously evaluate gigapixel whole-slide images (WSIs) through iterative, hierarchical diagnostic reasoning, reaching high accuracy on DDxBench, a challenging open-ended differential diagnosis benchmark, while also capable of generating visually grounded, humanly-interpretable summary reports.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20964
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evidence-based diagnostic reasoning with multi-agent copilot for human pathology
Weishaupt, Luca L.
Chen, Chengkuan
Williamson, Drew F. K.
Chen, Richard J.
Jaume, Guillaume
Ding, Tong
Chen, Bowen
Vaidya, Anurag
Le, Long Phi
Jaume, Guillaume
Lu, Ming Y.
Mahmood, Faisal
Computer Vision and Pattern Recognition
Artificial Intelligence
Pathology is experiencing rapid digital transformation driven by whole-slide imaging and artificial intelligence (AI). While deep learning-based computational pathology has achieved notable success, traditional models primarily focus on image analysis without integrating natural language instruction or rich, text-based context. Current multimodal large language models (MLLMs) in computational pathology face limitations, including insufficient training data, inadequate support and evaluation for multi-image understanding, and a lack of autonomous, diagnostic reasoning capabilities. To address these limitations, we introduce PathChat+, a new MLLM specifically designed for human pathology, trained on over 1 million diverse, pathology-specific instruction samples and nearly 5.5 million question answer turns. Extensive evaluations across diverse pathology benchmarks demonstrated that PathChat+ substantially outperforms the prior PathChat copilot, as well as both state-of-the-art (SOTA) general-purpose and other pathology-specific models. Furthermore, we present SlideSeek, a reasoning-enabled multi-agent AI system leveraging PathChat+ to autonomously evaluate gigapixel whole-slide images (WSIs) through iterative, hierarchical diagnostic reasoning, reaching high accuracy on DDxBench, a challenging open-ended differential diagnosis benchmark, while also capable of generating visually grounded, humanly-interpretable summary reports.
title Evidence-based diagnostic reasoning with multi-agent copilot for human pathology
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.20964