Li Mingzhe, He Zhaoming, Wang Hao
Research Center of Fluid Machinery Engineering and Technology, Jiangsu University, Zhenjiang 212013, China.
Department of Mechanical Engineering, Texas Tech University, Lubbock, TX 79411, USA.
Bioengineering (Basel). 2025 Mar 14;12(3):290. doi: 10.3390/bioengineering12030290.
Intelligent heart sound diagnosis based on Convolutional Neural Networks (CNN) has been attracting increasing attention due to its accuracy and efficiency, which have been improved by recent studies. However, the performance of CNN models, heavily influenced by their parameters and structures, still has room for improvement. In this paper, we propose a heart sound classification model named CAFusionNet, which fuses features from different layers with varying resolution ratios and receptive field sizes. Key features related to heart valve diseases are weighted by a channel attention block at each layer. To address the issue of limited dataset size, we apply a homogeneous transfer learning approach. CAFusionNet outperforms existing models on a dataset comprising public data combined with our proprietary dataset, achieving an accuracy of 0.9323. Compared to traditional deep learning methods, the transfer learning algorithm achieves an accuracy of 0.9665 in the triple classification task. Output data and visualized heat maps highlight the significance of feature fusion from different layers. The proposed methods significantly enhanced the performance of heart sound classification and demonstrated the importance of feature fusion, as interpreted through visualized heat maps.
基于卷积神经网络（CNN）的智能心音诊断因其准确性和效率而受到越来越多的关注，近期研究已对其进行了改进。然而，CNN模型的性能受其参数和结构的严重影响，仍有提升空间。在本文中，我们提出了一种名为CAFusionNet的心音分类模型，该模型融合了来自不同层、具有不同分辨率比例和感受野大小的特征。与心脏瓣膜疾病相关的关键特征在每一层都由通道注意力模块进行加权。为了解决数据集规模有限的问题，我们应用了一种同构迁移学习方法。在一个由公共数据和我们的专有数据集组成的数据集上，CAFusionNet的表现优于现有模型，准确率达到了0.9323。与传统深度学习方法相比，迁移学习算法在三重分类任务中的准确率达到了0.9665。输出数据和可视化热图突出了来自不同层的特征融合的重要性。所提出的方法显著提高了心音分类的性能，并通过可视化热图证明了特征融合的重要性。
