Feature extraction using time-frequency/scale analysis and ensemble of feature sets for crackle detection

Pulmonary crackles are used as indicators for the diagnosis of different pulmonary disorders. Crackles are very common adventitious sounds which have transient characteristic. From the characteristics of crackles such as timing and number of occurrences, the type and the severity of the pulmonary diseases can be obtained. In this study, a novel method is proposed for crackle detection. In this method, various feature sets are extracted using time-frequency and time-scale analysis. The extracted feature sets are fed into support vector machines both individually and as an ensemble of networks. Besides, as a preprocessing stage in order to improve the success of the model, frequency bands containing no-information are removed using dual tree complex wavelet transform, which is a shift invariant transform with limited redundancy and an improved version of discrete wavelet transform. The comparative results of individual feature sets and ensemble of sets with pre-processed and non pre-processed data are proposed.

[1]  Y.P. Kahya,et al.  A Multi-Channel Device for Respiratory Sound Data Acquisition and Transient Detection , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[2]  Nizamettin Aydin,et al.  Denoising embolic Doppler ultrasound signals using Dual Tree Complex Discrete Wavelet Transform , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[3]  A. R. Nath,et al.  Inspiratory crackles—early and late , 1974 .

[4]  P Piirilä,et al.  Separation of pulmonary disorders with two-dimensional discriminant analysis of crackles. , 1996, Clinical physiology.

[5]  Nick Kingsbury,et al.  The dual-tree complex wavelet transform: a new technique for shift invariance and directional filters , 1998 .

[6]  P. Piirilä,et al.  Crackles: recording, analysis and clinical significance. , 1995, The European respiratory journal.

[7]  Mete Yeginer,et al.  Elimination of vesicular sounds from pulmonary crackle waveforms , 2008, Comput. Methods Programs Biomed..

[8]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[9]  Richard Baraniuk,et al.  The Dual-tree Complex Wavelet Transform , 2007 .

[10]  H. Pasterkamp,et al.  Respiratory sounds. Advances beyond the stethoscope. , 1997, American journal of respiratory and critical care medicine.

[11]  Berkman Sahiner,et al.  Dual system approach to computer-aided detection of breast masses on mammograms. , 2006, Medical physics.

[12]  Lars Kai Hansen,et al.  Neural Network Ensembles , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[14]  Mete Yeginer,et al.  Feature extraction for pulmonary crackle representation via wavelet networks , 2009, Comput. Biol. Medicine.

[15]  S. Lehrer.  Understanding Lung Sounds , 2002 .

[16]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[17]  Andrey Vyshedskiy,et al.  Transmission of crackles in patients with interstitial pulmonary fibrosis, congestive heart failure, and pneumonia. , 2005, Chest.

[18]  Noam Gavriely,et al.  Breath Sounds Methodology , 1995 .