PC-MCL: Patient-Consistent Multi-Cycle Learning with multi-label bias correction for respiratory sound classification
This work addresses a critical issue in automated pulmonary disease diagnosis by improving generalization in respiratory sound classification, though it is incremental with specific methodological enhancements.
The paper tackled patient-specific overfitting and multi-label bias in respiratory sound classification by proposing PC-MCL, which achieved an ICBHI Score of 65.37% on the ICBHI 2017 benchmark, outperforming existing baselines.
Automated respiratory sound classification supports the diagnosis of pulmonary diseases. However, many deep models still rely on cycle-level analysis and suffer from patient-specific overfitting. We propose PC-MCL (Patient-Consistent Multi-Cycle Learning) to address these limitations by utilizing three key components: multi-cycle concatenation, a 3-label formulation, and a patient-matching auxiliary task. Our work resolves a multi-label distributional bias in respiratory sound classification, a critical issue inherent to applying multi-cycle concatenation with the conventional 2-label formulation (crackle, wheeze). This bias manifests as a systematic loss of normal signal information when normal and abnormal cycles are combined. Our proposed 3-label formulation (normal, crackle, wheeze) corrects this by preserving information from all constituent cycles in mixed samples. Furthermore, the patient-matching auxiliary task acts as a multi-task regularizer, encouraging the model to learn more robust features and improving generalization. On the ICBHI 2017 benchmark, PC-MCL achieves an ICBHI Score of 65.37%, outperforming existing baselines. Ablation studies confirm that all three components are essential, working synergistically to improve the detection of abnormal respiratory events.