Asaeikheybari Golnoush, El-Harasis Majd, Gupta Amit, Shoemaker M Benjamin, Barnard John, Hunter Joshua, Passman Rod S, Sun Han, Kim Hyun Su, Schilling Taylor, Telfer William, Eldridge Britta, Chen Po-Hao, Midya Abhishek, Varghese Bibin, Harwood Samuel J, Jin Alison, Wass Sojin Y, Izda Aleksandar, Park Kevin, Abraham Abel, Van Wagoner David R, Tandon Animesh, Chung Mina K, Madabhushi Anant
Department of Electrical, Computer and Systems Engineering, School of Engineering, Case Western Reserve University, Cleveland, OH (G.A.).
Division of Cardiovascular Medicine, Vanderbilt University School of Medicine, Nashville, TN (M.E.-H., M.B.S., B.V.).
Circ Arrhythm Electrophysiol. 2024 Dec;17(12):e012679. doi: 10.1161/CIRCEP.123.012679. Epub 2024 Dec 3.
Atrial fibrillation (AF) recurrence is common after catheter ablation. Pulmonary vein (PV) isolation is the cornerstone of AF ablation, but PV remodeling has been associated with the risk of AF recurrence. We aimed to evaluate whether artificial intelligence-based morphological features of primary and secondary PV branches on computed tomography images are associated with AF recurrence post-ablation.
Two artificial intelligence models were trained for the segmentation of computed tomography images, enabling the isolation of PV branches. Patients from Cleveland Clinic (N=135) and Vanderbilt University (N=594) were combined and divided into 2 sets for training and cross-validation (D, n=218) and internal testing (D, n=511). An independent validation set (D, N=80) was obtained from University Hospitals of Cleveland. We extracted 48 fractal-based and 12 shape-based radiomic features from primary and secondary PV branches of patients with AF recurrence (AF+) and without recurrence after catheter ablation of AF (AF-). To predict AFrecurrence, 3 Gradient Boosting classification models based on significant features from primary (M), secondary (M), and combined (M) PV branches were built.
Features relating to primary PVs were found to be associated with AF recurrence. The M classifier achieved area under the curve values of 0.73, 0.71, and 0.70 across the 3 datasets. AF+ cases exhibited greater surface complexity in their primary PV area, as evidenced by higher fractal dimension values compared with AF- cases. The M classifier results revealed a weaker association with AF+, suggesting higher relevance to AF recurrence post-ablation from primary PV branch morphology.
This largest multi-institutional study to date revealed associations between artificial intelligence-extracted morphological features of the primary PV branches with AF recurrence in 809 patients from 3 sites. Future work will focus on enhancing the predictive ability of the classifier by integrating clinical, structural, and morphological features, including left atrial appendage and left atrium-related characteristics.
导管消融术后房颤（AF）复发很常见。肺静脉（PV）隔离是房颤消融的基石，但PV重塑与房颤复发风险相关。我们旨在评估基于人工智能的计算机断层扫描图像上肺静脉主支和分支的形态特征是否与消融术后房颤复发相关。
训练了两个人工智能模型用于计算机断层扫描图像的分割，以实现肺静脉分支的分离。来自克利夫兰诊所（N = 135）和范德比尔特大学（N = 594）的患者被合并，并分为两组用于训练和交叉验证（D，n = 218）以及内部测试（D，n = 511）。从克利夫兰大学医院获得了一个独立验证集（D，N = 80）。我们从房颤复发（AF+）患者和房颤导管消融术后未复发（AF-）患者的肺静脉主支和分支中提取了基于分形的48个和基于形状的12个放射组学特征。为了预测房颤复发，构建了3个基于肺静脉主支（M）、分支（M）和联合（M）显著特征的梯度提升分类模型。
发现与肺静脉主支相关的特征与房颤复发有关。M分类器在这3个数据集中的曲线下面积值分别为0.73、0.71和0.70。与AF-病例相比，AF+病例的肺静脉主支区域表现出更高的表面复杂性，分形维数值更高证明了这一点。M分类器结果显示与AF+的关联较弱，表明肺静脉主支形态与消融术后房颤复发的相关性更高。
这项迄今为止最大的多机构研究揭示了人工智能提取的肺静脉主支形态特征与来自3个地点的809例患者房颤复发之间的关联。未来的工作将集中于通过整合临床、结构和形态特征，包括左心耳和左心房相关特征，来提高分类器的预测能力。
