De Silva Kasun, Campbell Timothy G, Bennett Richard G, Turnbull Samual, Bhaskaran Ashwin, Anderson Robert D, Davey Christopher, O'Donohue Alexandra K, Schindeler Aaron, Selvakumar Dinesh, Kotake Yasuhito, Hsu Chi-Jen, Chong James J H, Kizana Eddy, Kumar Saurabh
Department of Cardiology, Westmead Hospital, Sydney, New South Wales, Australia (K.D.S., T.G.C., R.G.B., S.T., A.B., D.S., Y.K., C.-J.H., J.J.H.C., E.K., S.K.).
Westmead Applied Research Centre, University of Sydney, New South Wales, Australia (K.D.S., T.G.C., R.G.B., A.B., R.D.A., C.D., Y.K., S.K.).
Circ Arrhythm Electrophysiol. 2025 Jul;18(7):e013611. doi: 10.1161/CIRCEP.124.013611. Epub 2025 Jun 13.
Accurate delineation of scar patterns is valuable for guiding catheter ablation of ventricular tachycardia. We hypothesized that scar and its pattern of distribution can be determined from intracardiac electrograms using computational signal processing and that further improvements in classification can be achieved with a convolutional neural network.
A total of 5 sheep underwent anteroseptal infarction (plus 1 healthy control) with electroanatomic mapping (129±12 days post-infarct). A whole-heart histological model of the postinfarction scar was created and coregistered to ventricular electrograms. Electrograms were matched to scar pattern categories; no scar, at least endocardial scar: at least intramural scar (intramural scar sparing the endocardium), or epicardial-only scar (epicardial scar sparing the endocardium/intramural space). A suite of signal-processing features was extracted from bipolar electrograms. Furthermore, bipolar and unipolar electrograms were used to train a time series convolutional neural network (InceptionTime).
A total of 11 551 electrograms were matched to 451 biopsies. Bipolar and unipolar voltage alone were poor classifiers of scar patterns. For each of the scar labels, 20 bipolar electrogram features (predominantly within the frequency domain) yielded an area under the curve of 0.815, 0.810, 0.704, and 0.681 to predict no scar, at least endocardial scar, at least intramural scar, and epicardial-only scar, respectively. Substantial improvement was achieved with a convolutional neural network trained on unipolar electrograms: areas under the curve and accuracy (averaged across wavefronts) were 0.977 and 0.929 for no scar, 0.970 and 0.919 for at least endocardial scar, 0.909 and 0.959 for at least intramural scar and 0.926 and 0.958 for epicardial-only scar.
Convolutional neural network-derived analysis of unipolar electrogram data has excellent predictive value for determination of scar patterns. Computational analyses of electrogram data beyond voltage and other time-domain features are necessary to improve the identification of arrhythmogenic sites in the ventricle.
准确描绘瘢痕模式对于指导室性心动过速的导管消融具有重要价值。我们假设可以使用计算信号处理从心内电图确定瘢痕及其分布模式，并且卷积神经网络可以进一步提高分类效果。
总共5只绵羊接受了前间隔梗死（加1只健康对照），并进行了电解剖标测（梗死后129±12天）。创建了梗死后期瘢痕的全心组织学模型，并将其与心室电图进行配准。将电图与瘢痕模式类别进行匹配；无瘢痕、至少心内膜瘢痕、至少壁内瘢痕（壁内瘢痕不累及心内膜）或仅心外膜瘢痕（心外膜瘢痕不累及心内膜/壁内间隙）。从双极电图中提取了一组信号处理特征。此外，使用双极电图和单极电图训练了一个时间序列卷积神经网络（InceptionTime）。
总共11551份电图与451份活检标本进行了匹配。仅双极和单极电压对瘢痕模式的分类效果较差。对于每种瘢痕标签，20个双极电图特征（主要在频域内）预测无瘢痕、至少心内膜瘢痕、至少壁内瘢痕和仅心外膜瘢痕的曲线下面积分别为0.815、0.810、0.704和0.681。使用单极电图训练的卷积神经网络取得了显著改善：无瘢痕的曲线下面积和准确率（跨波前平均）分别为0.977和0.929，至少心内膜瘢痕为0.970和0.919，至少壁内瘢痕为0.909和0.959，仅心外膜瘢痕为0.926和0.958。
基于卷积神经网络的单极电图数据分析对瘢痕模式的确定具有出色的预测价值。除电压和其他时域特征外，对电图数据进行计算分析对于改善心室致心律失常部位的识别是必要的。
