An efficient and robust Phonocardiography (PCG)-based Valvular Heart Diseases (VHD) detection framework using Vision Transformer (ViT)

Sonain Jamil, Arunabha M. Roy

Abstract: Highlights•A high-performance and robust DL model has been presented for accurate detection of VHDs.•To improve the performance of the classifier, ViT is employed leveraging the self-attention mechanism on TFR of 2D-PCG.•ViT provides the best performance by achieving average accuracy of 99.90 % outperforming existing SOTA VHD detection models.