提升脊柱MRI报告生成的临床准确性，引入异常热图增强模型判断。
Beyond Fluency: A Clinical Benchmark and Anomaly-Enhanced Baseline for Spine MRI Report Generation
- 用半监督U-Net++生成椎间盘异常热图，增强视觉定位能力。
- 热图使报告诊断准确率显著提升，尤其在细微异常检测上表现突出。
- 适合临床医生与医学AI研发者参考，推动可解释的影像报告系统发展。
放射科报告撰写耗时且存在阅片者间差异，自动化报告生成成为视觉语言模型（VLMs）的重要临床应用。我们针对腰椎MRI任务对主流VLMs进行基准测试，重点关注诊断准确性，发现标准的词汇和语义评估指标无法反映临床正确性：流畅、结构良好的报告可能得分高，却包含重要临床错误。为解决这一问题，我们提出一种与架构无关的框架，通过半监督U-Net++模型生成空间定位的椎节异常热图，作为VLM输入的增强信号。该热图不仅提升模型对解剖结构的敏感性，还提供独立的可解释输出，便于临床审查，推动实现诊断可靠、视觉可解释的腰椎MRI VLM系统。
原文摘要 · Abstract (English)
Radiology reporting is time-consuming and subject to inter-rater variability, making automated report generation an attractive clinical application for Vision-Language Models (VLMs). We benchmark state-of-the-art VLMs on lumbar spine MRI with a focus on diagnostic accuracy and demonstrate that standard lexical and semantic metrics poorly reflect clinical correctness: fluent, well-structured reports can score highly while containing clinically meaningful diagnostic errors. To address this failure mode, we propose an architecture-agnostic framework that augments VLM inputs with spatially localized, disc-level anomaly heatmaps generated by a semi-supervised U-Net++ model. These heatmaps both improve anatomical sensitivity through explicit visual grounding and provide an independent interpretability output for clinical oversight, moving us closer to diagnostically reliable, visually grounded VLMs for lumbar spine MRI interpretation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。