NeuroSymb-MRG: Differentiable Abductive Reasoning with Active Uncertainty Minimization for Radiology Report Generation

TL;DR

NeuroSymb-MRG is a novel framework that combines neuro-symbolic abductive reasoning with active uncertainty minimization to generate more accurate and clinically grounded radiology reports.

Contribution

It introduces a unified, differentiable reasoning system that enhances factual consistency and clinical relevance in automated radiology report generation.

Findings

Improves factual consistency over baseline methods.

Achieves higher standard language metrics.

Incorporates clinician-in-the-loop for refinement.

Abstract

Automatic generation of radiology reports seeks to reduce clinician workload while improving documentation consistency. Existing methods that adopt encoder-decoder or retrieval-augmented pipelines achieve progress in fluency but remain vulnerable to visual-linguistic biases, factual inconsistency, and lack of explicit multi-hop clinical reasoning. We present NeuroSymb-MRG, a unified framework that integrates NeuroSymbolic abductive reasoning with active uncertainty minimization to produce structured, clinically grounded reports. The system maps image features to probabilistic clinical concepts, composes differentiable logic-based reasoning chains, decodes those chains into templated clauses, and refines the textual output via retrieval and constrained language-model editing. An active sampling loop driven by rule-level uncertainty and diversity guides clinician-in-the-loop adjudication and promptbook refinement. Experiments on standard benchmarks demonstrate consistent improvements in factual consistency and standard language metrics compared to representative baselines.