MAGIS: Evidence-Based Multi-Agent Reasoning for Interpretable Strabismus Clinical Decision-Making

2026-06-08

AI Summary

This study addresses the need for fine-grained and interpretable clinical decision support in diagnosing strabismus subtypes, a task hindered by the opacity of existing deep learning approaches and the hallucination tendencies of large vision-language models. To overcome these limitations, the authors propose a multi-agent reasoning framework that transforms end-to-end diagnosis into a structured pipeline. This framework integrates visual evidence from ocular alignment photographs with clinical rules through a Dual-Evidence Constrained Context (DECC) module and employs an Evidence-Based Corrective Verification (EBCV) mechanism to ensure reliable reasoning and report generation. Evaluated on a fine-grained strabismus benchmark, the method improves the weighted F1 score from 72.0% to 91.3% and substantially enhances the clinical reliability of diagnostic reports in terms of consistency, alignment, and completeness.

Abstract

Strabismus is a common ocular disorder that requires fine-grained subtype diagnosis for individualized treatment planning. However, existing deep learning methods mainly provide diagnostic predictions without transparent reasoning, while recent large vision-language models (LVLMs), although promising for joint image understanding and report generation, remain highly prone to hallucination in this evidence-sensitive and rule-driven medical task. To address these challenges, we propose MAGIS, an evidence-based Multi-AGent reasoning for Interpretable Strabismus diagnosis framework. MAGIS transforms black-box end-to-end generation into a structured diagnostic process consisting of candidate hypothesis generation, dual-evidence constrained context, evidence-based corrective verification, and report generation. Specifically, we introduce a Dual-Evidence Constrained Context (DECC) mechanism that jointly organizes visual evidence from the photograph of the nine cardinal positions of gaze and evidence-based clinical diagnostic rules into a constrained context for reliable diagnostic reasoning. We further develop an Evidence-Based Corrective Verification (EBCV) mechanism that verifies whether the current diagnostic hypothesis is supported by visual evidence, heatmap-based visual cues, and evidence-based clinical diagnostic rules. Hypothesis refinement is triggered when inconsistency is detected. Experiments on a fine-grained strabismus benchmark demonstrate that MAGIS not only significantly outperforms other state-of-the-art diagnostic systems, improving the weighted F1 score from 72.0% to 91.3%, but also substantially improves the clinical reliability (consistency, alignment, and completeness) of generated diagnostic reports. These results demonstrate that MAGIS provides an effective solution for building accurate, evidence-based, and clinically interpretable strabismus diagnosis systems.

Problem

• strabismus
• evidence-based diagnosis
• medical hallucination
• interpretable AI
• clinical decision-making

Innovation

• Multi-Agent Reasoning
• Evidence-Based Diagnosis
• Interpretable AI
• Dual-Evidence Constrained Context
• Corrective Verification