AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation

Hugging Face Daily Papers Papers

Summary

AtomiMed introduces a hierarchical atomic fact-checking framework for evaluating medical report generation, decomposing clinical narratives into atomic facts and using agentic cross-verification to improve accuracy assessment beyond traditional metrics.

Traditional metrics for Medical Report Generation (MRG) predominantly rely on surface-level n-gram overlap, which fails to capture clinical factual accuracy and often overlooks catastrophic diagnostic errors. We address this fundamental limitation by proposing AtomiMed, a universal, modality-agnostic evaluation framework that decomposes complex medical narratives into a standardized, multi-level hierarchy of Atomic Clinical Facts, encompassing Disease-level entities and Attribute-level descriptors, including location, morphology, and severity. By implementing an Agentic Cross-Verification loop between ground-truth and predicted reports, AtomiMed simulates a multi-radiologist peer-review process to verify clinical consistency, thus enabling the decoupled assessment of diagnostic detection and descriptive accuracy. To facilitate standardized evaluation, we introduce MRGEvalKit, an open-source toolkit for automated hierarchical extraction, and curate OmniMRG-Bench, a comprehensive multi-modal benchmark covering X-ray, CT, MRI, and Ultrasound. Extensive experiments on multiple expert-annotated reader studies demonstrate that AtomiMed achieves significantly higher correlation with human radiologist judgment compared to traditional and model-based metrics. Our code are release at https://github.com/Venn2336/MRGEvalkit
Original Article
View Cached Full Text

Cached at: 07/02/26, 03:46 AM

Paper page - AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation

Source: https://huggingface.co/papers/2606.31292 Published on Jun 30

·

Submitted byhttps://huggingface.co/Venn2024

WANGon Jul 2

Authors:

,

,

,

,

,

,

,

,

,

Abstract

AtomiMed presents a novel evaluation framework for medical report generation that decomposes clinical narratives into atomic facts and uses an agentic cross-verification process to improve accuracy assessment beyond traditional metrics.

Traditional metrics forMedical Report Generation(MRG) predominantly rely on surface-level n-gram overlap, which fails to capture clinical factual accuracy and often overlooks catastrophic diagnostic errors. We address this fundamental limitation by proposing AtomiMed, a universal, modality-agnostic evaluation framework that decomposes complex medical narratives into a standardized, multi-level hierarchy ofAtomic Clinical Facts, encompassing Disease-level entities and Attribute-level descriptors, including location, morphology, and severity. By implementing anAgentic Cross-Verificationloop between ground-truth and predicted reports, AtomiMed simulates a multi-radiologist peer-review process to verify clinical consistency, thus enabling the decoupled assessment of diagnostic detection and descriptive accuracy. To facilitate standardized evaluation, we introduce MRGEvalKit, an open-source toolkit for automatedhierarchical extraction, and curate OmniMRG-Bench, a comprehensivemulti-modal benchmarkcovering X-ray, CT, MRI, and Ultrasound. Extensive experiments on multiple expert-annotated reader studies demonstrate that AtomiMed achieves significantly higher correlation with humanradiologist judgmentcompared to traditional and model-based metrics. Our code are release at https://github.com/Venn2336/MRGEvalkit

View arXiv pageView PDFGitHub2Add to collection

Get this paper in your agent:

hf papers read 2606\.31292

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.31292 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.31292 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.31292 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

AutoMedBench: Towards Medical AutoResearch with Agentic AI Models

Hugging Face Daily Papers

AutoMedBench is a workflow-aware benchmark for autonomous medical-AI research, evaluating agents across five stages on diverse medical imaging tasks. Stage-level scoring reveals validation as the weakest stage, highlighting the need for reliable verification in agentic workflows.

A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans

Hugging Face Daily Papers

This paper presents a modular medical imaging agent that verifies spatial relations in CT scans by decomposing tasks into parsing, localization, and geometric rules, achieving 94.1% accuracy and outperforming end-to-end vision-language models by 42.5 percentage points on a benchmark while ensuring auditable reasoning.