arXiv 2605.240122026-05-20cs.CV

基于深度学习的TIMI心肌灌注帧数自动量化（DL-TMPFC）：一种快速评估微血管功能障碍的新框架

Deep Learning-Based Automated Quantification of TIMI Myocardial Perfusion Frame Count (DL-TMPFC) from Coronary Angiography: A Novel Framework for Rapid Assessment of Microvascular Dysfunction

School of Artificial Intelligence and Digital Economy Industry, Guangzhou Institute of Science and Technology（人工智能与数字经济发展学院，广州科学研究院）；Department of Cardiology, Second Affiliated Hospital, Jiangxi Medical College, Nanchang University（南华大学江西医学院心内科，第二附属医院）；Department of Cardiology, First Affiliated Hospital of Zhejiang University School of Medicine（浙江大学医学院附属第一医院心内科）；Department of Cardiology, National University Heart Centre（国立大学心脏中心心内科）

Si Li, Yuanqing He, Chenkai Hu, Xiaogang Guo, Huay-Cheem Tan, Chieh Yang Koo, Xuan Zhang, Lei He, Jingyuan Zeng, Shan Xiao

备注：: 15 pages,8 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出DL-TMPFC框架，结合狭窄检测网络和区域感知分割网络，从冠状动脉造影中自动计算TIMI心肌灌注帧数，实现微血管功能障碍的客观量化，验证显示与专家手动测量高度一致。

摘要：

目的：冠状动脉微血管功能障碍（CMVD）影响约40%-60%的缺血和非阻塞性冠状动脉患者，但由于依赖侵入性功能测试或主观的TIMI血流分级，诊断仍具挑战性。TIMI心肌灌注帧数（TMPFC）提供了一种基于造影的客观定量测量CMVD的方法，但其临床应用受限于繁琐的手动计算和验证不足。本研究旨在开发和验证一种基于深度学习的TMPFC计算方法（DL-TMPFC），使其能够整合到临床工作流程中。方法和结果：DL-TMPFC框架包含两个组件。首先，狭窄检测网络排除阻塞性冠状动脉疾病（CAD）。然后，区域感知分割网络识别灌注区域，TMPFC计算模块自动从造影序列中确定首帧和末帧。该框架在来自三个独立机构的655名患者（445名阻塞性CAD、100名确诊CMVD、110名对照组）队列中进行了验证。DL-TMPFC与专家手动测量具有极好的一致性（偏差：-0.93帧；95%一致性界限：-5.33至+3.47；r=0.98）。DL-TMPFC通过完全自动化TMPFC并消除观察者依赖性，显著增强了临床可行性。临床上，DL-TMPFC能够准确识别全谱冠状动脉病理中的CMVD，并捕获超越二元分类的CMVD连续严重程度，实现定量风险分层。结论：DL-TMPFC实现了直接从常规造影中自动、标准化和准确地量化CMVD。通过提供自动和客观的测量，该工具为临床实践中及时识别和管理CMVD提供了即时诊断信息。

英文摘要：

Aims: Coronary microvascular dysfunction (CMVD) affects approximately 40%-60% of patients with ischemia and non-obstructive coronary arteries, yet diagnosis remains challenging due to reliance on invasive functional testing or subjective Thrombolysis In Myocardial Infarction (TIMI) flow grade. The TIMI Myocardial Perfusion Frame Count (TMPFC) offers an objective, angiography-based quantitative measure of CMVD, but its clinical translation is hindered by cumbersome manual calculation and insufficient validation. This study aims to develop and validate a deep learning-powered TMPFC calculation (DL-TMPFC), enabling integration into clinical workflows. Methods and results: DL-TMPFC framework comprised two components. A stenosis detection network first excluded obstructive coronary artery disease (CAD). A territory-aware segmentation network then identified perfusion territories and TMPFC calculation module automatically determined the first and last frames from angiographic sequences. The framework was validated in a cohort of 655 patients (445 of obstructive CAD, 100 of confirmed CMVD, 110 of control group) from three independent institutions. DL-TMPFC showed excellent agreement with expert manual measurements (bias: -0.93 frames; 95% LoA: -5.33 to +3.47; r =0.98). DL-TMPFC markedly enhanced clinical feasibility by fully automating TMPFC and removing observer dependence. Clinically, DL-TMPFC accurately identified CMVD across a full spectrum of coronary pathologies and captured the continuous severity of CMVD beyond binary classification, enabling quantitative risk stratification. Conclusion: DL-TMPFC enabled automatic, standardized, and accurate quantification of CMVD directly from routine angiography. By providing an automatic and objective measure, this tool provided immediate diagnostic information for timely recognition and management of CMVD in clinical practice.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。