Automated clustering of independent components for discontinuous sounds thoracic imaging

Discontinuous lung sounds (DLS), also known as crackles, are abnormal sounds produced by different pulmonary pathologies (PP) whose thoracic spatial distribution and prevalence are relevant for diagnosis purpose. Recently, DLS imaging has been proposed to help diagnose and follow-up PP where automated recognition of DLS is meaningful. The present study focuses on the automated selection of independent components (ICs) associated with DLS. Extraction of ICs information for clustering by k-means is achieved in two ways: (1) forming features vectors (FVs) containing the kurtosis, entropy and sparsity of each IC or (2) by applying mutual information (MI) or Euclidean distance (ED) to all ICs. Next, silhouette index is computed to estimate the number of necessary clusters (C). Afterward, to detect just the clusters containing ICs of DLS a selection index is proposed. Finally, to estimate the number of DLS per ICs in each selected cluster a time-variant AR modeling is applied; the estimated number is shown in conjunction with the 2D-ICs spatial distribution. The methodology is applied to simulated and real cases; DLS imaging results are also compared against clinical auscultation. The results showed that the automated selection via FVs is promising to imaging DLS.