Towards Autonomous and Auditable Medical Imaging Model Development

2026-07-11

AI Summary

This work addresses the challenges in automated medical imaging model development—namely modality-specific constraints, stringent validation requirements, and auditability concerns—by introducing AMID, a multi-agent framework that uniquely integrates data-conditioned task planning with a verification-guided two-stage optimization mechanism. Leveraging a large language model–driven multi-agent system, AMID enables autonomous cross-modal modeling, parallel exploration, and automatic validation of predictive outputs. Evaluated across 20 diverse cross-modal medical imaging tasks, AMID substantially outperforms general-purpose maximum likelihood estimation (MLE) approaches and achieves performance on par with or superior to expert-crafted state-of-the-art solutions in multiple tasks.

Abstract

Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by coupling planning, code execution, debugging, and empirical feedback. Translating this capability to medical imaging remains difficult because each task imposes modality-specific experimentation and strict requirements for validation protocols and prediction artifacts. Here we introduce AMID, an autonomous multi-agent framework for medical imaging model development. AMID first proposes Data-Conditioned Method Planning, which refines coarse task-level search spaces into executable, parallelizable method lanes grounded in task-specific data analysis and runnable medical-imaging resources. It then develops Verification-Guided Two-Stage Optimization, moving from broad early exploration of diverse method lanes to selective exploitation of promising candidates while enforcing strict verification of validation protocols, metric computation, and prediction artifacts throughout the optimization. Across 20 medical imaging challenge tasks spanning diverse modalities and prediction types, AMID outperformed evaluated general-purpose MLE systems and, on several tasks, approached or matched strong human-designed challenge solutions. These results suggest that AMID can turn task-specific medical imaging model development from bespoke manual engineering into an agentic workflow for producing high-performing and auditable model artifacts across heterogeneous tasks.

Problem

• autonomous
• auditable
• medical imaging
• model development
• validation protocols

Innovation

• Autonomous Medical Imaging
• Multi-Agent Framework
• Data-Conditioned Method Planning
• Verification-Guided Optimization
• Auditable Model Development