Aligning Findings with Diagnosis: A Self-Consistent Reinforcement Learning Framework for Trustworthy Radiology Reporting

• URL: http://arxiv.org/abs/2601.03321v2
• Date: Mon, 12 Jan 2026 05:56:31 GMT
• Title: Aligning Findings with Diagnosis: A Self-Consistent Reinforcement Learning Framework for Trustworthy Radiology Reporting
• Authors: Kun Zhao, Siyuan Dai, Pan Wang, Jifeng Song, Hui Ji, Chenghua Lin, Liang Zhan, Haoteng Tang,
• Abstract summary: Multimodal Large Language Models (MLLMs) have shown strong potential for radiology report generation.<n>Our framework restructures generation into two distinct components: a think block for detailed findings and an answer block for structured disease labels.
• Score: 37.57009831483529
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) have shown strong potential for radiology report generation, yet their clinical translation is hindered by architectural heterogeneity and the prevalence of factual hallucinations. Standard supervised fine-tuning often fails to strictly align linguistic outputs with visual evidence, while existing reinforcement learning approaches struggle with either prohibitive computational costs or limited exploration. To address these challenges, we propose a comprehensive framework for self-consistent radiology report generation. First, we conduct a systematic evaluation to identify optimal vision encoder and LLM backbone configurations for medical imaging. Building on this foundation, we introduce a novel "Reason-then-Summarize" architecture optimized via Group Relative Policy Optimization (GRPO). This framework restructures generation into two distinct components: a think block for detailed findings and an answer block for structured disease labels. By utilizing a multi-dimensional composite reward function, we explicitly penalize logical discrepancies between the generated narrative and the final diagnosis. Extensive experiments on the MIMIC-CXR benchmark demonstrate that our method achieves state-of-the-art performance in clinical efficacy metrics and significantly reduces hallucinations compared to strong supervised baselines.

Related papers

• Structure Observation Driven Image-Text Contrastive Learning for Computed Tomography Report Generation [51.509572354327986]
  This work introduces a novel two-stage (structure- and report-learning) framework tailored for Computed Tomography Report Generation (CTRG)<n>In the first stage, a set of learnable structure-specific visual queries observe corresponding structures in a CT image. The resulting observation tokens are contrasted with structure-specific textual features extracted from the accompanying radiology report with a structure-wise image-text contrastive loss.<n>In the second stage, the visual structure queries are frozen and used to select the critical image patch embeddings depicting each anatomical structure, minimizing distractions from irrelevant areas while reducing memory consumption.
  arXiv  Detail & Related papers  (2026-03-05T07:07:07Z)
• Concept-Enhanced Multimodal RAG: Towards Interpretable and Accurate Radiology Report Generation [12.226029763256962]
  Radiology Report Generation through Vision-Language Models (VLMs) promises to reduce documentation burden, improve reporting consistency, and accelerate clinical adoption.<n>Existing research treats interpretability and accuracy as separate objectives, with concept-based explainability techniques focusing primarily on transparency.<n>We present Concept-Enhanced Multimodal RAG (CEMRAG), a unified framework that decomposes visual representations into interpretable clinical concepts.
  arXiv  Detail & Related papers  (2026-02-17T15:18:07Z)
• PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy Optimization [6.821738567680833]
  We construct PathReasoner, the first large-scale dataset of whole-slide image (WSI) reasoning.<n>PathReasoner-R1 synergizes supervised fine-tuning with reasoning-oriented reinforcement learning to instill structured chain-of-thought capabilities.<n>Experiments demonstrate that PathReasoner-R1 achieves state-of-the-art performance on both PathReasoner and public benchmarks across various image scales.
  arXiv  Detail & Related papers  (2026-01-29T12:21:16Z)
• AgentsEval: Clinically Faithful Evaluation of Medical Imaging Reports via Multi-Agent Reasoning [73.50200033931148]
  We introduce AgentsEval, a multi-agent stream reasoning framework that emulates the collaborative diagnostic workflow of radiologists.<n>By dividing the evaluation process into interpretable steps including criteria definition, evidence extraction, alignment, and consistency scoring, AgentsEval provides explicit reasoning traces and structured clinical feedback.<n> Experimental results demonstrate that AgentsEval delivers clinically aligned, semantically faithful, and interpretable evaluations that remain robust under paraphrastic, semantic, and stylistic perturbations.
  arXiv  Detail & Related papers  (2026-01-23T11:59:13Z)
• MRG-R1: Reinforcement Learning for Clinically Aligned Medical Report Generation [23.22547135801011]
  We propose a semantic-driven reinforcement learning (SRL) method for medical report generation.<n>SRL encourages clinical-correctness-guided learning beyond imitation of language style.<n>We evaluate Medical Report Generation with SRL on two datasets: IU X-Ray and MIMIC-CXR.
  arXiv  Detail & Related papers  (2025-12-18T03:57:55Z)
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
  We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
  arXiv  Detail & Related papers  (2025-12-15T10:22:43Z)
• DiA-gnostic VLVAE: Disentangled Alignment-Constrained Vision Language Variational AutoEncoder for Robust Radiology Reporting with Missing Modalities [3.5045368873011924]
  We propose the DiA-gnostic VLVAE, which achieves robust radiology reporting through Disentangled Alignment.<n>Our framework is designed to be resilient to missing modalities by disentangling shared and modality-specific features.<n>A compact LLaMA-X decoder then uses these disentangled representations to generate reports efficiently.
  arXiv  Detail & Related papers  (2025-11-08T11:08:27Z)
• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation [61.350584471060756]
  Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images.<n>We propose Self-Supervised Anatomical Consistency Learning (SS-ACL) to align generated reports with corresponding anatomical regions.<n>SS-ACL constructs a hierarchical anatomical graph inspired by the invariant top-down inclusion structure of human anatomy.
  arXiv  Detail & Related papers  (2025-09-30T08:59:06Z)
• Medical AI Consensus: A Multi-Agent Framework for Radiology Report Generation and Evaluation [0.2039123720459736]
  We introduce a multi-agent reinforcement learning framework that serves as a benchmark and evaluation environment for multimodal clinical reasoning in the radiology ecosystem.<n>The proposed framework integrates large language models (LLMs) and large vision models (LVMs) within a modular architecture composed of ten specialized agents responsible for image analysis, feature extraction, report generation, review, and evaluation.
  arXiv  Detail & Related papers  (2025-09-22T04:31:27Z)
• A Multimodal Multi-Agent Framework for Radiology Report Generation [2.1477122604204433]
  Radiology report generation (RRG) aims to automatically produce diagnostic reports from medical images.<n>We propose a multimodal multi-agent framework for RRG that aligns with the stepwise clinical reasoning workflow.
  arXiv  Detail & Related papers  (2025-05-14T20:28:04Z)
• Knowledge-Augmented Language Models Interpreting Structured Chest X-Ray Findings [44.99833362998488]
  This paper introduces CXR-TextInter, a novel framework that repurposes powerful text-centric language models for chest X-rays interpretation.<n>We augment this LLM-centric approach with an integrated medical knowledge module to enhance clinical reasoning.<n>Our work validates an alternative paradigm for medical image AI, showcasing the potential of harnessing advanced LLM capabilities.
  arXiv  Detail & Related papers  (2025-05-03T06:18:12Z)
• Cross-Modal Causal Intervention for Medical Report Generation [107.76649943399168]
  Radiology Report Generation (RRG) is essential for computer-aided diagnosis and medication guidance.<n> generating accurate lesion descriptions remains challenging due to spurious correlations from visual-linguistic biases.<n>We propose a two-stage framework named CrossModal Causal Representation Learning (CMCRL)<n> Experiments on IU-Xray and MIMIC-CXR show that our CMCRL pipeline significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-03-16T07:23:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.