Murmur Detection and Clinical Outcome Classification Using a VGG-like Network and Combined Time-Frequency Representations of PCG Signals

Zhongrui Bai1, Baiju Yan2, Xianxiang Chen3, Yirong Wu3, Peng Wang3
1School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, 2Shanghai Jiao Tong University, 3Aerospace Information Research Institute, Chinese Academy of Sciences (AIRCAS)


For the George B. Moody PhysioNet Challenge 2022, our team, PhysioDreamfly, developed a deep neural network approach for detecting murmurs and identifying abnormal clinical outcomes from phonocardiograms (PCGs). In our approach, a VGG-like CNN model is used as the classifier. Images consisting of Log-Mel spectrograms and wavelet scalogram that transformed from unsegmented PCGs are used as model inputs. We combined the murmur and outcome labels to address the two tasks as one multi-label task, and introduced a weighted focal loss function to optimize the model. Our murmur detection classifier received a weighted accuracy score of 0.737 (ranked 10th out of 62 teams) and Challenge cost score of 9577(ranked 15th out of 62 teams) on the hidden validation set.