OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis

2026-07-27

AI Summary

This work addresses the challenge of distribution shifts in biomedical image analysis caused by variations in imaging devices, acquisition protocols, and patient populations. To tackle this issue without requiring model retraining, the authors propose a novel multi-agent ensemble framework that enables gradient-free adaptive inference at test time. The approach introduces offline policy learning into an expert routing mechanism for the first time, integrating confidence-based temperature scaling, distribution-aware dynamic class weighting, and instance-level routing guided by prediction consistency and entropy. Evaluated across nine diverse multimodal and multitask datasets, the method consistently outperforms over thirty baseline approaches, demonstrating significant improvements in both predictive accuracy and probability calibration, thereby confirming its broad applicability and practical utility.

Abstract

Biomedical image analysis spans diverse modalities and tasks, yet real-world deployment is hindered by severe distribution shifts across scanners, protocols, and patient populations. High-performing models consequently require repeated domain-specific fine-tuning, which is a costly cycle that becomes impractical when labels are scarce or privacy constraints limit data sharing. We propose OPERA (Offline Policy-guided Expert Routing and Adaptation), a multi-agent ensemble framework that addresses this deployment bottleneck by treating expert weight assignment as an offline policy learning problem: a routing policy is learned from a small validation set without gradient updates to any expert agent, then deployed with test-time adaptation to handle distribution shift. OPERA coordinates heterogeneous specialist agents through complementary mechanisms. The expert profiling module learns selection policies offline, enabling informed allocation of expertise. Each agent undergoes confidence calibration through temperature adjustment, ensuring more reliable probabilistic outputs. OPERA also incorporates distribution aware adaptation, where class weights are dynamically adjusted at the batch level using statistics derived from unlabeled test data. Instance level routing assigns each sample to the most suitable expert by leveraging inter model agreement and predictive entropy. We evaluate OPERA on 9 datasets covering fundus photography, chest X-ray, CT, MRI, and multimodal diagnostic benchmarks, comparing against 30+ baselines across classification, segmentation, and multimodal settings. OPERA consistently improves performance and calibration quality, demonstrating that offline policy-guided expert agents coordination is a practical path to deployable biomedical AI without retraining. Code is on \href{https://github.com/HUANGLIZI/OPERA}{GitHub}.

Problem

• distribution shift
• biomedical image analysis
• domain adaptation
• label scarcity
• privacy constraints

Innovation

• offline policy learning
• expert routing
• test-time adaptation
• confidence calibration
• distribution shift