Acoustic thoracic image of crackle sounds using linear and nonlinear processing techniques

Abstract

In this study, a novel approach is proposed, the imaging of crackle sounds distribution on the thorax based on processing techniques that could contend with the detection and count of crackles; hence, the normalized fractal dimension (NFD), the univariate AR modeling combined with a supervised neural network (UAR-SNN), and the time-variant autoregressive (TVAR) model were assessed. The proposed processing schemes were tested inserting simulated crackles in normal lung sounds acquired by a multichannel system on the posterior thoracic surface. In order to evaluate the robustness of the processing schemes, different scenarios were created by manipulating the number of crackles, the type of crackles, the spatial distribution, and the signal to noise ratio (SNR) at different pulmonary regions. The results indicate that TVAR scheme showed the best performance, compared with NFD and UAR-SNN schemes, for detecting and counting simulated crackles with an average specificity very close to 100%, and average sensitivity of 98 ± 7.5% even with overlapped crackles and with SNR corresponding to a scaling factor as low as 1.5. Finally, the performance of the TVAR scheme was tested against a human expert using simulated and real acoustic information. We conclude that a confident image of crackle sounds distribution by crackles counting using TVAR on the thoracic surface is thoroughly possible. The crackles imaging might represent an aid to the clinical evaluation of pulmonary diseases that produce this sort of adventitious discontinuous lung sounds.

Pulmonary crackle characterization: approaches in the use of discrete wavelet transform regarding border effect, mother-wavelet selection, and subband reduction

“…Many authors have presented different respiratory crackles filtering (Hadjileontiadis and Panas, 1997;Mastorocostas et al, 2000;Sankur et al, 1996;Tolias et al, 1997), feature extraction (CharlestonVillalobos et al, 2007;Ponte et al, 2013;Yeginer and Kahya, 2009;Yeginer and Kahya, 2010), Volume 31, Number 2, p. 148-159, 2015 and classification techniques (Abbas and Fahim, 2010;Charleston-Villalobos et al, 2011;Chen and Chou, 2014;Dokur, 2009;Içer and Gengec, 2014;Kandaswamy et al, 2004;Lu and Bahoura, 2008;Pesu et al, 1998;Serbes et al, 2013;Xie et al, 2012;Yeginer and Kahya, 2005;Zhenzhen et al, 2012).…”

Computerized Diagnosis of Respira tory Disorders

“…In the recent decades, computerized techniques have been increasingly employed for objective and quantitative analysis and comparison of respiratory sounds. Moreover, increasing number of studies has been carried out with multi-channel measurements with an aim to analyze the characteristics with respect to different auscultation locations simultaneously [1,2].…”

“…Autoregressive (AR) processes are known to be successful in modeling respiratory sounds [2][3][4][5]. In this work, their multivariate versions, namely, vector autoregressive (VAR) processes, are considered.…”

Sistema para la Detección Automática de Estertores Crepitantes basado en Dispositivos Móviles Inteligentes

“…Se emplearon sonidos respiratorios de diez (N=10) sujetos sanos, no fumadores, adquiridos previamente por nuestro grupo de trabajo [4]. Los sonidos respiratorios fueron adquiridos a una frecuencia de muestreo de 10 kHz.…”

“…Se han propuesto métodos computarizados para eliminar las limitaciones del estetoscopio en la detección de crepitancias, e.g., la detección visual con el análisis de forma de onda en tiempo expandido (TEWA), la detección automática basada en el análisis tiempo frecuencia [3] o el modelado autorregresivo variante en el tiempo (TVAR) [4]. Desafortunadamente, el empleo de sistemas computarizados para el análisis de sonidos respiratorios (CORSA) se ha limitado principalmente a centros de salud y de investigación altamente especializados.…”