GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration

TL;DR

This paper introduces GSCo, a collaborative framework combining a generalist foundation model and specialist models to improve medical image analysis, demonstrating superior performance across diverse datasets and out-of-domain tasks.

Contribution

The work develops MedDr, the largest open-source GFM for medicine, and proposes a novel collaborative inference mechanism, advancing generalizable AI in medical applications.

Findings

MedDr outperforms state-of-the-art GFMs on multiple datasets.

GSCo surpasses both GFMs and specialists in out-of-domain diagnosis.

The collaborative approach enhances accuracy and generalization in medical AI.

Abstract

Generalist foundation models (GFMs) are renowned for their exceptional capability and flexibility in effectively generalizing across diverse tasks and modalities. In the field of medicine, while GFMs exhibit superior generalizability based on their extensive intrinsic knowledge as well as proficiency in instruction following and in-context learning, specialist models excel in precision due to their domain knowledge. In this work, for the first time, we explore the synergy between the GFM and specialist models, to enable precise medical image analysis on a broader scope. Specifically, we propose a cooperative framework, Generalist-Specialist Collaboration (GSCo), which consists of two stages, namely the construction of GFM and specialists, and collaborative inference on downstream tasks. In the construction stage, we develop MedDr, the largest open-source GFM tailored for medicine, showcasing exceptional instruction-following and in-context learning capabilities. Meanwhile, a series of lightweight specialists are crafted for downstream tasks with low computational cost. In the collaborative inference stage, we introduce two cooperative mechanisms, Mixture-of-Expert Diagnosis and Retrieval-Augmented Diagnosis, to harvest the generalist's in-context learning abilities alongside the specialists' domain expertise. For a comprehensive evaluation, we curate a large-scale benchmark featuring 28 datasets and about 250,000 images. Extensive results demonstrate that MedDr consistently outperforms state-of-the-art GFMs on downstream datasets. Furthermore, GSCo exceeds both GFMs and specialists across all out-of-domain disease diagnosis datasets. These findings indicate a significant paradigm shift in the application of GFMs, transitioning from separate models for specific tasks to a collaborative approach between GFMs and specialists, thereby advancing the frontiers of generalizable AI in medicine.