X-PCR: A Benchmark for Cross-modality Progressive Clinical Reasoning in Ophthalmic Diagnosis

2026-04-22

AI Summary

This work addresses the lack of effective evaluation frameworks for progressive reasoning and cross-modal integration in existing medical multimodal large language models, particularly in ophthalmic diagnosis. To bridge this gap, we introduce OphthalBench—the first benchmark tailored to the complete ophthalmic diagnostic workflow—encompassing a six-stage progressive reasoning chain and six categories of multimodal fusion tasks across 52 eye diseases. Built upon 26,415 images and 177,868 expert-validated visual question-answer pairs aggregated from 51 public datasets, OphthalBench establishes a clinically grounded framework for assessing cross-modal progressive reasoning. Systematic evaluation of 21 state-of-the-art multimodal large models reveals significant deficiencies in complex diagnostic reasoning and multimodal coordination, thereby offering clear guidance for future model refinement.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Despite significant progress in Multi-modal Large Language Models (MLLMs), their clinical reasoning capacity for multi-modal diagnosis remains largely unexamined. Current benchmarks, mostly single-modality data, can't evaluate progressive reasoning and cross-modal integration essential for clinical practice. We introduce the Cross-Modality Progressive Clinical Reasoning (X-PCR) benchmark, the first comprehensive evaluation of MLLMs through a complete ophthalmology diagnostic workflow, with two reasoning tasks: 1) a six-stage progressive reasoning chain spanning image quality assessment to clinical decision-making, and 2) a cross-modality reasoning task integrating six imaging modalities. The benchmark comprises 26,415 images and 177,868 expert-verified VQA pairs curated from 51 public datasets, covering 52 ophthalmic diseases. Evaluation of 21 MLLMs reveals critical gaps in progressive reasoning and cross-modal integration. Dataset and code: https://github.com/CVI-SZU/X-PCR.

Problem

• clinical reasoning
• cross-modality
• progressive reasoning
• ophthalmic diagnosis
• multi-modal large language models

Innovation

• Cross-modality Reasoning
• Progressive Clinical Reasoning
• Multi-modal Large Language Models
• Ophthalmic Diagnosis
• Visual Question Answering