Xia Jun, Sun Jing, Yang Hongbo, Pan Jiahua, Guo Tao, Wang Weilian
School of Information Science and Engineering, Yunnan University, Kunming 650504, P. R. China.
Kunming Medical University, Kunming 650000, P. R. China.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2024 Feb 25;41(1):51-59. doi: 10.7507/1001-5515.202212037.
The multi-window time-frequency reassignment helps to improve the time-frequency resolution of bark-frequency spectral coefficient (BFSC) analysis of heart sounds. For this purpose, a new heart sound classification algorithm combining feature extraction based on multi-window time-frequency reassignment BFSC with deep learning was proposed in this paper. Firstly, the randomly intercepted heart sound segments are preprocessed with amplitude normalization, the heart sounds were framed and time-frequency rearrangement based on short-time Fourier transforms were computed using multiple orthogonal windows. A smooth spectrum estimate is calculated by arithmetic averaging each of the obtained independent spectra. Finally, the BFSC of reassignment spectrum is extracted as a feature by the Bark filter bank. In this paper, convolutional network and recurrent neural network are used as classifiers for model comparison and performance evaluation of the extracted features. Eventually, the multi-window time-frequency rearrangement improved BFSC method extracts more discriminative features, with a binary classification accuracy of 0.936, a sensitivity of 0.946, and a specificity of 0.922. These results present that the algorithm proposed in this paper does not need to segment the heart sounds and randomly intercepts the heart sound segments, which greatly simplifies the computational process and is expected to be used for screening of congenital heart disease.
多窗口时频重分配有助于提高心音的 Bark 频域谱系数（BFSC）分析的时频分辨率。为此，本文提出了一种将基于多窗口时频重分配 BFSC 的特征提取与深度学习相结合的新型心音分类算法。首先，对随机截取的心音片段进行幅度归一化预处理，对心音进行加窗，并使用多个正交窗口基于短时傅里叶变换计算时频重排。通过对每个获得的独立频谱进行算术平均来计算平滑频谱估计。最后，通过 Bark 滤波器组提取重分配频谱的 BFSC 作为特征。本文使用卷积网络和循环神经网络作为分类器，对提取的特征进行模型比较和性能评估。最终，多窗口时频重排改进的 BFSC 方法提取了更具判别力的特征，二元分类准确率为 0.936，灵敏度为 0.946，特异性为 0.922。这些结果表明，本文提出的算法无需对心音进行分割，而是随机截取心音片段，这大大简化了计算过程，有望用于先天性心脏病的筛查。
