Pre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus Dataset

查看原文 / View Original 编辑 / Edit

Computer Science > Computer Vision and Pattern Recognition arXiv:2610.08813 (cs) [Submitted on 23 Sep 2026] Title: Pre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus Dataset Authors: Xiao Wang, Yuxiang Zhang, Dan Xu, Yuehang Li, Shiao Wang, Bo Jiang, Yaowei Wang, Yonghong Tian, Jin Tang.

计算机科学 > 计算机视觉与模式识别 arXiv:2610.08813 (cs) [提交于 2026 年 9 月 23 日] 标题：预训练、推理、基准测试：CheXpert Plus 数据集上的 X 光报告生成作者：Xiao Wang, Yuxiang Zhang, Dan Xu, Yuehang Li, Shiao Wang, Bo Jiang, Yaowei Wang, Yonghong Tian, Jin Tang。

Abstract: X-ray image-based Radiology Report Generation (RRG) constitutes a critical research direction within medical artificial intelligence, with great potential to alleviate clinicians’ diagnostic workload and shorten patient waiting periods. Despite substantial advances over recent years, the field faces evident bottlenecks stemming from insufficient standardized benchmarks and inadequate domain adaptation of generic large models.

摘要：基于 X 光图像的放射学报告生成 (RRG) 是医学人工智能领域的一个关键研究方向，具有减轻临床医生诊断工作量和缩短患者等待时间的巨大潜力。尽管近年来取得了实质性进展，但该领域仍面临明显的瓶颈，主要源于标准化基准的不足以及通用大模型在领域适应性上的欠缺。

Notably, the newly released CheXpert Plus dataset is provided without accompanying baseline implementations and evaluation results, which impedes standardized training, quantitative evaluation and fair comparison among follow-up algorithms. To mitigate this limitation, we establish a comprehensive benchmark encompassing prevailing X-ray report generation models and Large Language Models on CheXpert Plus.

值得注意的是，新发布的 CheXpert Plus 数据集并未提供配套的基准实现和评估结果，这阻碍了后续算法的标准化训练、定量评估和公平比较。为了缓解这一局限，我们在 CheXpert Plus 上建立了一个涵盖主流 X 光报告生成模型和大语言模型的综合基准。

This benchmark delivers a reliable comparative foundation for upcoming methods and enables researchers to rapidly identify state-of-the-art approaches within this domain. Beyond benchmark construction, we rethink X-ray RRG under the paradigm of large models and propose a novel framework termed MambaXray-PRB.

该基准为后续方法提供了可靠的比较基础，使研究人员能够快速识别该领域的最先进方法。除了基准构建之外，我们在大模型范式下重新思考了 X 光 RRG，并提出了一种名为 MambaXray-PRB 的新颖框架。

Our framework improves report generation performance and enhances model interpretability via multi-stage large-model pre-training and multi-modal Chain-of-Thought reasoning. The pipeline consists of three successive phases: self-supervised auto-regressive modeling, X-ray-report contrastive learning, and post-training optimization for reasoning and report generation.

我们的框架通过多阶段大模型预训练和多模态思维链推理，提高了报告生成性能并增强了模型的可解释性。该流程包含三个连续阶段：自监督自回归建模、X 光-报告对比学习，以及用于推理和报告生成的训练后优化。

Extensive experiments on IU X-ray, MIMIC-CXR, and CheXpert Plus datasets validate the effectiveness of MambaXray-PRB for radiology report generation. The source code of this paper is available on this https URL.

在 IU X-ray、MIMIC-CXR 和 CheXpert Plus 数据集上的大量实验验证了 MambaXray-PRB 在放射学报告生成方面的有效性。本文的源代码可在该 https URL 获取。