Das Sangita, Pal Saurabh, Mitra Madhuchhanda
Department of Applied Physics, University of Calcutta, Kolkata, 700009, 92APC Road, West Bengal, India.
Department of Applied Physics, University of Calcutta, Kolkata, 700009, 92APC Road, West Bengal, India.
Comput Biol Med. 2020 Nov;126:103990. doi: 10.1016/j.compbiomed.2020.103990. Epub 2020 Sep 19.
This paper represents an unsupervised approach to detect the positions of S1, S2 heart sound events in a Phonocardiogram (PCG) recording. Insufficiency of correctly annotated heart sound database drives us to investigate unsupervised techniques. Gammatone filter bank features are used to characterize the spectral pattern of fundamental heart sound events from noise contaminated PCG data. An unsupervised spectral clustering technique is employed for segmentation of S1/S2 and non-S1/S2 heart sound events. A Feature winning score is computed to identify the S1/S2 and non-S1/S2 frames. Finally, time based threshold is applied to detect the accurate positions of S1 and S2 heart sounds. The performance of spectral clustering is compared with other clustering methods. The proposed method offers a maximum F1-score of 98% and 92.5% for normal and abnormal PCG data respectively on 2016 PhysioNet/CinC challenge dataset. The heart sound annotation algorithm provided by PhysioNet has been used as the ground truth after hand correction.
本文提出了一种无监督方法，用于在心音图（PCG）记录中检测第一心音（S1）和第二心音（S2）事件的位置。正确标注的心音数据库不足促使我们研究无监督技术。伽马通滤波器组特征用于从受噪声污染的PCG数据中表征基本心音事件的频谱模式。采用无监督谱聚类技术对S1/S2和非S1/S2心音事件进行分割。计算特征获胜分数以识别S1/S2和非S1/S2帧。最后，应用基于时间的阈值来检测S1和S2心音的准确位置。将谱聚类的性能与其他聚类方法进行比较。在2016年PhysioNet/CinC挑战赛数据集上，该方法对正常和异常PCG数据分别提供了98%和92.5%的最大F1分数。PhysioNet提供的心音标注算法在人工校正后用作基准真值。
