AI可自动诊断心脏磁共振影像，准确率超95%。
Development of an automated, reliable, and clinically meaningful artificial intelligence (AI) tool for diagnosing cardiac disease from conventional cardiovascular magnetic resonance (CMR) images
- 用大语言模型自动提取报告标签，整合多模态影像数据
- 多模型融合后对肥厚型心肌病等五类疾病诊断AUC达0.966
- 代码与模型开源，临床部署路径清晰
心血管磁共振（CMR）可无创评估心肌结构、功能与病理，但解读需丰富经验，人工智能可提供支持。然而现有AI模型受限于数据标注繁琐、性能不足及落地困难。本研究构建了自动化数据预处理流程，利用开源本地运行的大语言模型（LLMs）从非结构化报告中提取诊断标签，并对动态影像和延迟增强（LGE）序列进行多模态预处理。基于三种视觉基础模型（DINO、VST、UMedPT），采用两阶段微调策略，覆盖肥厚型心肌病（HCM）、扩张型心肌病（DCM）、缺血性心肌病（ICM）、心脏淀粉样变性（CA）及正常对照（NOR）共988例病例，其中742例用于训练，246例用于验证。在独立测试集1067例患者中，单模型最高诊断准确率达AUC 0.937（HCM）和0.945（CA）。通过多模型与多模态集成，整体表现进一步提升：HCM（AUC=0.959，CI [0.936-0.978]）、CA（AUC=0.966，CI [0.939-0.986]）、NOR（AUC=0.872，CI [0.852-0.894]）、DCM（AUC=0.848，CI [0.808-0.885]）、ICM（AUC=0.840，CI [0.809-0.868]）。所有训练与推理代码及模型权重已公开于https://github.com/sinaamirrajab/CMR_CVD。
原文摘要 · Abstract (English)
Aims: Cardiovascular magnetic resonance (CMR) imaging enables non-invasive assessment of myocardial structure, function, and pathology, but requires substantial experience in interpretation of CMR images that could be supported by artificial intelligence (AI)-based models. However, use of AI models for enhanced CMR reading is limited by labor-intensive data curation, suboptimal model performance, and unclear implementation pathways. Methods and results: We developed an automated data curation pipeline for CMR-based cardiovascular disease (CVD) diagnosis, integrating open-source locally-run large language models (LLMs) to extract diagnostic labels from narrative CMR reports and preprocessing multimodal imaging data, including cine and late-gadolinium-enhancement (LGE) CMR sequences. Three vision foundation models (DINO, VST, UMedPT) were fine-tuned across these modalities in a two-stage approach. The dataset comprised hypertrophic cardiomyopathy (HCM), dilated cardiomyopathy (DCM), ischemic cardiomyopathy (ICM), cardiac amyloidosis (CA), and normal controls (NOR). A total of 988 curated cases were randomly divided into 742 for training and 246 for validation. Fine-tuned AI-models achieved high discriminative diagnostic performance on an independent test set comprising 1067 patients , with individual AUC-ROC values of up to 0.937 for the correct diagnosis of HCM and 0.945 for cardiac amyloidosis. Ensemble strategies combining multiple models and modalities further improved AI-based diagnostic accuracy and robustness, achieving the highest overall diagnostic performance for HCM (AUC=0.959, CI [0.936-0.978]), CA (AUC=0.966, CI [0.939-0.986]), NOR (AUC=0.872, CI [0.852-0.894]), DCM (AUC=0.848, CI [0.808-0.885]) and ICM (AUC=0.840, CI [0.809-0.868]). All training and inference code, along with the trained model weights, are publicly available on https://github.com/sinaamirrajab/CMR_CVD.
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。