PDF(Pubmed)
Abstract：
UNASSIGNED: Predicting the origin of premature ventricular contraction (PVC) from the preoperative electrocardiogram (ECG) is important for catheter ablation therapies. We propose an explainable method that localizes PVC origin based on the semantic segmentation result of a 12-lead ECG using a deep neural network, considering suitable diagnosis support for clinical application.
UNASSIGNED: The deep learning-based semantic segmentation model was trained using 265 12-lead ECG recordings from 84 patients with frequent PVCs. The model classified each ECG sampling time into four categories: background (BG), sinus rhythm (SR), PVC originating from the left ventricular outflow tract (PVC-L), and PVC originating from the right ventricular outflow tract (PVC-R). Based on the ECG segmentation results, a rule-based algorithm classified ECG recordings into three categories: PVC-L, PVC-R, as well as Neutral, which is a group for the recordings requiring the physician\'s careful assessment before separating them into PVC-L and PVC-R. The proposed method was evaluated with a public dataset which was used in previous research.
UNASSIGNED: The evaluation of the proposed method achieved neutral rate, accuracy, sensitivity, specificity, F1-score, and area under the curve of 0.098, 0.932, 0.963, 0.882, 0.945, and 0.852 on a private dataset, and 0.284, 0.916, 0.912, 0.930, 0.943, and 0.848 on a public dataset, respectively. These quantitative results indicated that the proposed method outperformed almost all previous studies, although a significant number of recordings resulted in requiring the physician\'s assessment.
UNASSIGNED: The feasibility of explainable localization of premature ventricular contraction was demonstrated using deep learning-based semantic segmentation of 12-lead ECG.Clinical trial registration: M26-148-8.
UNASSIGNED: The deep learning-based semantic segmentation model was trained using 265 12-lead ECG recordings from 84 patients with frequent PVCs. The model classified each ECG sampling time into four categories: background (BG), sinus rhythm (SR), PVC originating from the left ventricular outflow tract (PVC-L), and PVC originating from the right ventricular outflow tract (PVC-R). Based on the ECG segmentation results, a rule-based algorithm classified ECG recordings into three categories: PVC-L, PVC-R, as well as Neutral, which is a group for the recordings requiring the physician\'s careful assessment before separating them into PVC-L and PVC-R. The proposed method was evaluated with a public dataset which was used in previous research.
UNASSIGNED: The evaluation of the proposed method achieved neutral rate, accuracy, sensitivity, specificity, F1-score, and area under the curve of 0.098, 0.932, 0.963, 0.882, 0.945, and 0.852 on a private dataset, and 0.284, 0.916, 0.912, 0.930, 0.943, and 0.848 on a public dataset, respectively. These quantitative results indicated that the proposed method outperformed almost all previous studies, although a significant number of recordings resulted in requiring the physician\'s assessment.
UNASSIGNED: The feasibility of explainable localization of premature ventricular contraction was demonstrated using deep learning-based semantic segmentation of 12-lead ECG.Clinical trial registration: M26-148-8.
摘要：
■根据术前心电图（ECG）预测室性早搏（PVC）的起源对于导管消融治疗很重要。我们提出了一种可解释的方法，该方法基于使用深度神经网络的12导联ECG的语义分割结果来定位PVC起源，为临床应用考虑合适的诊断支持。
基于深度学习的语义分割模型是使用来自84例频繁PVC患者的265个12导联ECG记录进行训练的。该模型将每个ECG采样时间分为四类：背景（BG），窦性心律(SR),源自左心室流出道的PVC（PVC-L），和源自右心室流出道的PVC（PVC-R）。根据心电分割结果,基于规则的算法将ECG记录分为三类：PVC-L，PVC-R,以及中立，这是一组录音，需要医生仔细评估，然后再将它们分成PVC-L和PVC-R。所提出的方法是用以前研究中使用的公共数据集进行评估的。
■对所提出的方法的评估实现了中性率，准确度,灵敏度,特异性，F1分数，以及私有数据集上0.098、0.932、0.963、0.882、0.945和0.852的曲线下面积，公共数据集上的0.284、0.916、0.912、0.930、0.943和0.848，分别。这些定量结果表明，所提出的方法优于几乎所有以前的研究，尽管大量的记录导致需要医生的评估。
■使用基于深度学习的12导联ECG语义分割证明了可解释定位室性早搏的可行性。临床试验注册：M26-148-8。
基于深度学习的语义分割模型是使用来自84例频繁PVC患者的265个12导联ECG记录进行训练的。该模型将每个ECG采样时间分为四类：背景（BG），窦性心律(SR),源自左心室流出道的PVC（PVC-L），和源自右心室流出道的PVC（PVC-R）。根据心电分割结果,基于规则的算法将ECG记录分为三类：PVC-L，PVC-R,以及中立，这是一组录音，需要医生仔细评估，然后再将它们分成PVC-L和PVC-R。所提出的方法是用以前研究中使用的公共数据集进行评估的。
■对所提出的方法的评估实现了中性率，准确度,灵敏度,特异性，F1分数，以及私有数据集上0.098、0.932、0.963、0.882、0.945和0.852的曲线下面积，公共数据集上的0.284、0.916、0.912、0.930、0.943和0.848，分别。这些定量结果表明，所提出的方法优于几乎所有以前的研究，尽管大量的记录导致需要医生的评估。
■使用基于深度学习的12导联ECG语义分割证明了可解释定位室性早搏的可行性。临床试验注册：M26-148-8。
