Toward Clinically Acceptable Chest X-ray Report Generation: A Qualitative Retrospective Pilot Study of CXRMate-2

• URL: http://arxiv.org/abs/2604.18967v1
• Date: Tue, 21 Apr 2026 01:30:51 GMT
• Title: Toward Clinically Acceptable Chest X-ray Report Generation: A Qualitative Retrospective Pilot Study of CXRMate-2
• Abstract summary: State-of-the-art CXRMate-2 integrates structured conditioning and reinforcement learning with a composite reward for semantic alignment with radiologist reports.<n>To compare CXRMate-2 against radiologist reporting, we conduct a blinded, qualitative retrospective evaluation.<n> Generated reports were deemed acceptable (defined as preferred or rated equally to radiologist reports) in 45% of ratings, with no statistically significant difference in preference rates.<n>These results suggest a credible pathway to clinically acceptable CXR RRG.
• Score: 10.139968076056071
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Chest X-ray (CXR) radiology report generation (RRG) models have shown rapid progress, yet their clinical utility remains uncertain due to limited evaluation by radiologists. We present CXRMate-2, a state-of-the-art CXR RRG model that integrates structured multimodal conditioning and reinforcement learning with a composite reward for semantic alignment with radiologist reports. Across the MIMIC-CXR, CheXpert Plus, and ReXgradient datasets, CXRMate-2 achieves statistically significant improvements over strong benchmarks, including gains of 11.2% and 24.4% in GREEN and RadGraph-XL, respectively, on MIMIC-CXR relative to MedGemma 1.5 (4B). To directly compare CXRMate-2 against radiologist reporting, we conduct a blinded, randomised qualitative retrospective evaluation. Three consultant radiologists compare generated and radiologist reports across 120 studies from the MIMIC-CXR test set. Generated reports were deemed acceptable (defined as preferred or rated equally to radiologist reports) in 45% of ratings, with no statistically significant difference in preference rates between radiologist reports and acceptable generated reports for seven of the eight analysed findings. Preference for radiologist reports was driven primarily by higher recall, while generated reports were often preferred for readability. Together, these results suggest a credible pathway to clinically acceptable CXR RRG. Improvements in recall, alongside better detection of subtle findings (e.g., pulmonary congestion), are likely sufficient to achieve non-inferiority to radiologist reporting. With these targeted advances, CXR RRG systems may be ready for prospective evaluation in assistive roles within radiologist-led workflows.

Related papers

• A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation [48.23500302185585]
  We present CheXOne, a reasoning-enabled vision-language model for CXR interpretation.<n>CheXOne jointly generates diagnostic predictions and explicit, clinically grounded reasoning traces.<n>We show that CheXOne-drafted reports are comparable to or better than resident-written reports in 55% of cases.
  arXiv  Detail & Related papers  (2026-04-01T05:19:09Z)
• A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice [83.11942224668127]
  Janus-Pro-CXR (1B) is a chest X-ray interpretation system based on DeepSeek Janus-Pro model.<n>Our system outperforms state-of-the-art X-ray report generation models in automated report generation.
  arXiv  Detail & Related papers  (2025-12-23T13:26:13Z)
• Closing the Performance Gap Between AI and Radiologists in Chest X-Ray Reporting [40.40577855417923]
  We introduce MAIRA-X, a clinically evaluated multimodal AI model for longitudinal chest X-ray report generation.<n>A novel L&T-specific metrics framework was developed to assess accuracy in reporting attributes such as type, longitudinal change and placement.<n>Our results suggest MAIRA-X can effectively assist radiologists, particularly in high-volume clinical settings.
  arXiv  Detail & Related papers  (2025-11-21T10:53:26Z)
• ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification [57.22053411719822]
  ChestX-Reasoner is a radiology diagnosis MLLM designed to leverage process supervision mined directly from clinical reports.<n>Our two-stage training framework combines supervised fine-tuning and reinforcement learning guided by process rewards to better align model reasoning with clinical standards.
  arXiv  Detail & Related papers  (2025-04-29T16:48:23Z)
• Large Model driven Radiology Report Generation with Clinical Quality Reinforcement Learning [16.849933628738277]
  Radiology report generation (RRG) has attracted significant attention due to its potential to reduce the workload of radiologists. This paper introduces a novel RRG method, textbfLM-RRG, that integrates large models (LMs) with clinical quality reinforcement learning. Experiments on the MIMIC-CXR and IU-Xray datasets demonstrate the superiority of our method over the state of the art.
  arXiv  Detail & Related papers  (2024-03-11T13:47:11Z)
• ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data [115.0747462486285]
  ChatRadio-Valuer is a tailored model for automatic radiology report generation that learns generalizable representations. The clinical dataset utilized in this study encompasses a remarkable total of textbf332,673 observations. ChatRadio-Valuer consistently outperforms state-of-the-art models, especially ChatGPT (GPT-3.5-Turbo) and GPT-4 et al.
  arXiv  Detail & Related papers  (2023-10-08T17:23:17Z)
• Radiology-Llama2: Best-in-Class Large Language Model for Radiology [71.27700230067168]
  This paper introduces Radiology-Llama2, a large language model specialized for radiology through a process known as instruction tuning. Quantitative evaluations using ROUGE metrics on the MIMIC-CXR and OpenI datasets demonstrate that Radiology-Llama2 achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-08-29T17:44:28Z)
• Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report Generation [7.586632627817609]
  Radiologists face high burnout rates, partly due to the increasing volume of Chest X-rays (CXRs) requiring interpretation and reporting. Our proposed CXR report generator integrates elements of the workflow and introduces a novel reward for reinforcement learning. Results from our study demonstrate that the proposed model generates reports that are more aligned with radiologists' reports than state-of-the-art models.
  arXiv  Detail & Related papers  (2023-07-19T05:41:14Z)
• Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priors [1.1110995501996481]
  We propose two methods to remove references to priors in radiology reports. A GPT-3-based few-shot approach to rewrite medical reports without references to priors; and a BioBERT-based token classification approach to directly remove words referring to priors. We find that our re-trained model--which we call CXR-ReDonE--outperforms previous report generation methods on clinical metrics, achieving an average BERTScore of 0.2351 (2.57% absolute improvement)
  arXiv  Detail & Related papers  (2022-09-27T00:44:41Z)
• An Accurate and Explainable Deep Learning System Improves Interobserver Agreement in the Interpretation of Chest Radiograph [0.33598755777055367]
  The VinDr-CXR can classify a CXR scan into multiple thoracic diseases and localize most types of critical findings on the image. The proposed system significantly improved the agreement between radiologists themselves with an increase of 1.5% in mean Fleiss' Kappa.
  arXiv  Detail & Related papers  (2022-08-06T17:03:49Z)
• COVID-Net CXR-2: An Enhanced Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-ray Images [58.35627258364233]
  Use of chest X-ray (CXR) imaging as a complimentary screening strategy to RT-PCR testing continues to grow. We introduce COVID-Net CXR-2, an enhanced deep convolutional neural network design for COVID-19 detection from CXR images. benchmark dataset composed of 19,203 CXR images from a multinational cohort of 16,656 patients from at least 51 countries.
  arXiv  Detail & Related papers  (2021-05-14T04:29:21Z)

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.