Adaptive convolutional dictionary learning for denoising seismocardiogram to enhance the classification performance of aortic stenosis

• Published in: Computers in biology and medicine Vol. 168; p. 107763
• Main Authors: Xu, Bowen, Jiang, Fangfang, Zhu, Ziyu, Meng, Haobo, Xu, Lisheng
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.01.2024; Elsevier Limited
• Subjects: Aorta; Aortic stenosis; Classification; Classifiers; Contamination; Convolutional dictionary learning; Diagnosis; Dictionaries; Echocardiography; Heart diseases; Internal Medicine; Machine learning; Measurement; Medical signal denoising; Neural networks; Noise; Noise reduction; Other; Seismocardiogram; Sparse coding; Waveforms; Medical signal denoising; Aortic stenosis; Seismocardiogram; Sparse coding; Convolutional dictionary learning
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.107763

Aortic stenosis (AS) is the most prevalent type of valvular heart disease (VHD), traditionally diagnosed using echocardiogram or phonocardiogram. Seismocardiogram (SCG), an emerging wearable cardiac monitoring modality, is proved to be feasible in non-invasive and cost-effective AS diagnosis. However, SCG waveforms acquired from patients with heart diseases are typically weak, making them more susceptible to noise contamination. While most related researches focus on motion artifacts, sensor noise and quantization noise have been mostly overlooked. These noises pose additional challenges for extracting features from the SCG, especially impeding accurate AS classification. To address this challenge, we present a convolutional dictionary learning-based method. Based on sparse modeling of SCG, the proposed method generates a personalized adaptive-size dictionary from noisy measurements. The dictionary is used for sparse coding of the noisy SCG into a transform domain. Reconstruction from the domain removes the noise while preserving the individual waveform pattern of SCG. Using two self-collected SCG datasets, we established optimal dictionary learning parameters and validated the denoising performance. Subsequently, the proposed method denoised SCG from 50 subjects (25 AS and 25 non-AS). Leave-one-subject-out cross-validation (LOOCV) was applied to 5 machine learning classifiers. Among the classifiers, a bi-layer neural network achieved a moderate accuracy of 90.2%, with an improvement of 13.8% from the denoising. The proposed sparsity-based denoising technique effectively removes stochastic sensor noise and quantization noise from SCG, consequently improving AS classification performance. This approach shows promise for overcoming instrumentation constraints of SCG-based diagnosis. •A novel application of convolutional dictionary learning for denoising seismocardiogram (SCG).•Sparse modeling of SCG as the theoretical foundation enabling noise reduction.•Optimized denoising parameters determined through grid search on a self-collected SCG dataset.•Enhancement of Aortic stenosis classification using denoised SCG.