文献速递心脏核医学

人工智能驱动的SPECT心肌灌注显像冠状动脉疾病诊断:一项综合性深度学习研究

Artificial intelligence-powered coronary artery disease diagnosis from SPECT myocardial perfusion imaging: a comprehensive deep learning study.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2025-02-20

本研究纳入940例接受SPECT心肌灌注显像的患者(其中281例有侵入性冠状动脉造影ICA),利用定量灌注SPECT提取静息和负荷极坐标图,开发并比较13种深度学习模型及6种训练策略用于冠状动脉疾病诊断。以专家阅片为参考时,DenseNet201 Late Fusion模型在每血管分析中AUC达0.89;以ICA为参考时,最佳模型在每血管分析中AUC为0.71(策略3)和每患者分析中AUC为0.77(策略5)。作者认为深度学习模型可作为核医学医师的辅助工具,但仅限LAD供血区。

要点

  • 以专家阅片为参考,DenseNet201 Late Fusion模型每血管分析AUC=0.89,ResNet152V2 Late Fusion模型每患者分析AUC=0.83。
  • 以ICA为参考,策略3 WoAug InceptionResNetV2 EarlyFusion每血管分析AUC=0.71,策略5 WoAug ResNet152V2 EarlyFusion每患者分析AUC=0.77。
  • 作者认为所提深度学习模型可辅助核医学医师诊断和报告,但仅限LAD供血区。

核心结论

  • 本研究证实基于SPECT心肌灌注显像极坐标图的深度学习分析在冠状动脉疾病诊断中具有潜力。
  • 在自动化专家阅片诊断方面,模型性能有前景,准确率接近专家分析水平。
  • 使用不同的数据组合策略(如纳入和不纳入ICA的数据)以及不同的训练方法(如半监督学习)可提高深度学习模型的性能。
  • 所提深度学习模型可与计算机辅助诊断系统结合,作为核医学医师的助手以改善诊断和报告,但仅限LAD供血区。

研究设计与样本

  • 共纳入940例接受SPECT心肌灌注显像的患者,其中281例纳入ICA。
  • 使用定量灌注SPECT提取静息和负荷状态的极坐标图。
  • 定义两项任务:任务1以专家阅片评估SPECT心肌灌注显像为参考进行自动化CAD诊断;任务2基于ICA报告参考从SPECT心肌灌注显像诊断CAD。
  • 任务2中使用6种策略训练深度学习模型,实现13种不同深度学习模型及4种输入类型(有无数据增强)进行训练、验证和测试,共728个模型。
  • 以100例有ICA作为参考标准的患者(与任务1相同患者)按血管和按患者评估模型。

主要发现

  • 任务1中,DenseNet201 Late Fusion模型每血管分析AUC=0.89,ResNet152V2 Late Fusion模型每患者分析AUC=0.83,均优于其他模型。
  • 任务2中,基于ICA预测CAD的最佳模型:每血管分析为策略3(训练数据中结合专家阅片和ICA诊断)WoAug InceptionResNetV2 EarlyFusion,AUC=0.71;每患者分析为策略5(半监督方法)WoAug ResNet152V2 EarlyFusion,AUC=0.77。
  • 显著性图显示模型可有助于聚焦相关区域进行决策。

关键数值与推荐

  • 任务1每血管分析最佳模型DenseNet201 Late Fusion的AUC=0.89。
  • 任务1每患者分析最佳模型ResNet152V2 Late Fusion的AUC=0.83。
  • 任务2每血管分析最佳模型策略3 WoAug InceptionResNetV2 EarlyFusion的AUC=0.71。
  • 任务2每患者分析最佳模型策略5 WoAug ResNet152V2 EarlyFusion的AUC=0.77。

临床怎么用

  • 作者认为所提深度学习模型可与计算机辅助诊断系统结合,作为核医学医师的助手以改善诊断和报告,但仅限LAD供血区。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Myocardial perfusion imaging (MPI) using single-photon emission computed tomography (SPECT) is a well-established modality for noninvasive diagnostic assessment of coronary artery disease (CAD). However, the time-consuming and experience-dependent visual interpretation of SPECT images remains a limitation in the clinic. PURPOSE: We aimed to develop advanced models to diagnose CAD using different supervised and semi-supervised deep learning (DL) algorithms and training strategies, including transfer learning and data augmentation, with SPECT-MPI and invasive coronary angiography (ICA) as standard of reference. MATERIALS AND METHODS: A total of 940 patients who underwent SPECT-MPI were enrolled (281 patients included ICA). Quantitative perfusion SPECT (QPS) was used to extract polar maps of rest and stress states. We defined two different tasks, including (1) Automated CAD diagnosis with expert reader (ER) assessment of SPECT-MPI as reference, and (2) CAD diagnosis from SPECT-MPI based on reference ICA reports. In task 2, we used 6 strategies for training DL models. We implemented 13 different DL models along with 4 input types with and without data augmentation (WAug and WoAug) to train, validate, and test the DL models (728 models). One hundred patients with ICA as standard of reference (the same patients in task 1) were used to evaluate models per vessel and per patient. Metrics, such as the area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, specificity, precision, and balanced accuracy were reported. DeLong and pairwise Wilcoxon rank sum tests were respectively used to compare models and strategies after 1000 bootstraps on the test data for all models. We also compared the performance of our best DL model to ER's diagnosis. RESULTS: In task 1, DenseNet201 Late Fusion (AUC = 0.89) and ResNet152V2 Late Fusion (AUC = 0.83) models outperformed other models in per-vessel and per-patient analyses, respectively. In task 2, the best models for CAD prediction based on ICA were Strategy 3 (a combination of ER- and ICA-based diagnosis in train data), WoAug InceptionResNetV2 EarlyFusion (AUC = 0.71), and Strategy 5 (semi-supervised approach) WoAug ResNet152V2 EarlyFusion (AUC = 0.77) in per-vessel and per-patient analyses, respectively. Moreover, saliency maps showed that models could be helpful for focusing on relevant spots for decision making. CONCLUSION: Our study confirmed the potential of DL-based analysis of SPECT-MPI polar maps in CAD diagnosis. In the automation of ER-based diagnosis, models' performance was promising showing accuracy close to expert-level analysis. It demonstrated that using different strategies of data combination, such as including those with and without ICA, along with different training methods, like semi-supervised learning, can increase the performance of DL models. The proposed DL models could be coupled with computer-aided diagnosis systems and be used as an assistant to nuclear medicine physicians to improve their diagnosis and reporting, but only in the LAD territory. CLINICAL TRIAL NUMBER: Not applicable.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Hajianfar G, Gharibi O, Sabouri M, et al. Artificial intelligence-powered coronary artery disease diagnosis from SPECT myocardial perfusion imaging: a comprehensive deep learning study. Eur J Nucl Med Mol Imaging. 2025. PMID: 39976703. doi:10.1007/s00259-025-07145-x

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。