Towards Domain Invariant Heart Sound Abnormality Detection using Learnable Filterbanks

Objective: Cardiac auscultation is the most practiced non-invasive and cost-effective procedure for the early diagnosis of heart diseases. While machine learning based systems can aid in automatically screening patients, the robustness of these systems is affected by numerous factors including the stethoscope/sensor, environment, and data collection protocol. This paper studies the adverse effect of domain variability on heart sound classification and develops strategies to address this problem. Methods: We propose a novel Convolutional Neural Network (CNN) layer, consisting of time-convolutional (tConv) units, that emulate Finite Impulse Response (FIR) filters. The filter coefficients can be updated via backpropagation and be stacked in the front-end of the network as a learnable filterbank. These filters can incorporate properties such as linear/zero phase-response and symmetry while improving robustness due to domain variability. Results: Our methods are evaluated using multi-domain heart sound recordings obtained from publicly available phonocardiogram (PCG) datasets. On multi-domain evaluation tasks, the proposed method surpasses the top-scoring systems found in the literature for heart sound classification. Our systems achieved relative improvements of up to 11.84% in terms of a modified accuracy (Macc) metric, compared to state-of-the-art methods. Conclusion: The results demonstrate the effectiveness of the proposed learnable filterbank CNN architecture in achieving robustness towards sensor/domain variability in PCG signals. Significance: The proposed methods pave the way for deploying automated cardiac screening systems in diversified and underserved communities.