On efficiently detecting fine/coarse crackles and squawks in lung sound recordings by means of fractal dimension
L. J. Hadjileontiadis, I. T. Rekanos (Thessaloniki, Greece; Helsinki, Finland)
Source: Annual Congress 2002 - Airway obstruction measurement (FOT - NEP) sleep and lung sound analysis
Disease area: Interstitial lung diseases
Abstract Detection of discontinuous adventitious lung sounds, i.e., fine/coarse crackles (FC, CC) and squawks (SQ), seems to play an important role in the non-invasive diagnosis of pulmonary dysfunctions, especially when it is based on the auscultation findings. Due to physicians' subjectivity in the interpretation of lung sound recordings, an objective, fast and accurate detector of FC, CC and SQ would, in turn, enhance the diagnostic character of lung sounds and lead to more accurate characterisation of the associated pulmonary pathology [e.g., pulmonary fibrosis (PF), interstitial fibrosis (IF), chronic bronchitis (CB), allergic alveolitis (AA)]. In this study we have constructed an efficient technique for detecting FC, CC and SQ in clinical auscultative recordings. The technique is based on a fractal-dimension (FD) analysis of lung sounds. The FD, as a measure of signal complexity, is increased when FC, CC and SQ are present in the recordings and decreased when they are absent (background noise). Analysis of pre-classified lung sounds (FC: 6 cases-PF, IF; CC: 5 cases-CB; SQ: 5 cases IF, AA) drawn from two lung sound databases (Kraman, S.S. Lung Sounds 1993, USA: ACCP; Lehrer, S. Understanding Lung Sounds 1993, USA: W. B. Saunders Co) demonstrate the efficiency of the proposed method, since it clearly detects the location and the duration of FC, CC and SQ (100% detectability, p<0.001), despite their variation either in time duration and/or amplitude. Since it is not dependent on subjective human judgment, it is robust, and has low computational cost, the FD-detector could be easily used in pulmonary intensive care units for continuous real-time FC, CC and SQ screening.
Rating:
You must login to grade this presentation.
Share or cite this content
Citations should be made in the following way:
L. J. Hadjileontiadis, I. T. Rekanos (Thessaloniki, Greece; Helsinki, Finland). On efficiently detecting fine/coarse crackles and squawks in lung sound recordings by means of fractal dimension. Eur Respir J 2002; 20: Suppl. 38, 327
You must login to share this Presentation/Article on Twitter, Facebook, LinkedIn or by email.
Member's Comments
Related content which might interest you:
Related content which might interest you:
Efficient extraction of fine/coarse crackles and squawks from lung sound recordings using wavelet packets and higher-order statistics Source: Eur Respir J 2002; 20: Suppl. 38, 33s Year: 2002
The wavelet transformation for the detection of pathological lung sounds Source: Eur Respir J 2001; 18: Suppl. 33, 462s Year: 2001
The use of computer aided lung sound analysis to characterise lung sounds in a healthy population Source: Annual Congress 2009 - Respiratory physiotherapy assessment Year: 2009
Automatic wheezing-episode detector using spectrogram analysis of breath sounds Source: Eur Respir J 2003; 22: Suppl. 45, 446s Year: 2003
An algorithm to automatically identify cough sounds from clinical recordings Source: Annual Congress 2003 - Cough and sleep disorders Year: 2003
On efficiently categorising fine and coarse crackles using continuous wavelet transform Source: Eur Respir J 2004; 24: Suppl. 48, 123s Year: 2004
Dynamic dead space in face masks used with noninvasive ventilators: a lung model study Source: Eur Respir J 2004; 23: 129-135 Year: 2004
Lung sounds intensity: can we rely on recordings at spontaneous airflow? Source: International Congress 2017 – Assessing pulmonary and extra-pulmonary function in chronic disease Year: 2017
Reliability of computer aided lung sound analysis detecting crackles in bronchiectasis patients – a potential outcome measure for respiratory physiotherapy Source: Annual Congress 2008 - Mucociliary clearance, novel techniques and assessments, in adult, paediatric and mechanically ventilated patients Year: 2008
Crackle sound analysis in a porcine ARDS model to create a non-invasive recruitment monitoring Source: Annual Congress 2008 - Pathophysiology of acute lung injury Year: 2008
Measuring lung function using sound waves: role of the forced oscillation technique and impulse oscillometry system Source: Breathe 2015; 11:57-65 Year: 2015
Quantitative analysis of the influence of ‘supporting the cheeks‘ on input impedance and upper airways impedance measurements Source: Eur Respir J 2006; 28: Suppl. 50, 421s Year: 2006
The effect of high-frequency oscillatory vibration on peak expiratory flow generated by a MI-E cough assist device in a mechanical lung model Source: International Congress 2018 – Chronic respiratory disease: respiratory muscle function, breathing exercises and airway clearance techniques Year: 2018
The prediction of airway wall thickening by computer aided lung sound analysis Source: Annual Congress 2012 - Lung function tests in monitoring airway diseases Year: 2012
Least square fitting method for the analysis of chest wall asynchronies Source: Annual Congress 2009 - New data on respiratory function - from experimental approaches to man Year: 2009
Incremental components of reinflation volume assessed by crackle sound analysis in excised dog lungs Source: Eur Respir J 2001; 18: Suppl. 33, 259s Year: 2001
Automatic recognition of abnormal sleep respiratory events using a transthoracic impedance sensor included inside a pacemaker Source: Eur Respir J 2004; 24: Suppl. 48, 116s Year: 2004
Analysis of quiet breathing in COPD using fiber grating vision sensor Source: Annual Congress 2007 - Advances in respiratory mechanics Year: 2007
Validation of breathing frequency algorithms in impedance pneumography Source: International Congress 2018 – New methods and concepts in tests of lung and respiratory muscle function Year: 2018
Detection and characterization of apneas using tracheal sound and suprasternal pressure signals Source: International Congress 2018 – New diagnostic tools for sleep and breathing and healthcare provision options Year: 2018