Com o avanço tecnológico surgem novas ferramentas que auxiliam os médicos no diagnóstico de diversas doenças. Na área cardiovascular, após permanecer por um longo período em segundo plano, a ausculta cardíaca voltou a ser muito utilizada devido ao surgimento, no mercado, de estetoscópios digitais. Tais aparelhos contam com novos recursos tecnológicos que permitem a captação e a análise de dados de forma automática, oferecendo mais informações ao profissional da área. Levando em conta essa nova ascensão da área de Fonocardiografia,o presente trabalho se dedicou à separação das bulhas S1 e S2 por meio de ferramentas computacionais, com o propósito de auxiliar médicos não especialistas em Cardiologia a verificar a existência de possíveis anormalidades no som cardíaco. Acreditando na possibilidade de este procedimento vir a ser utilizado posteriormente para auxiliar no reconhecimento de padrões dos sons cardíacos, este trabalho se propôs a criar um algoritmo para detecção automática de anormalidades que afetam as bulhas S1 e S2. Assim, aplicou-se a técnica de Wavelet sobre uma base de dados de sons cardíacos constituída de 1209 bulhas, auditada pelo Real Hospital Português e também pelo Instituto Dante Pazzanese de Cardiologia. Os melhores resultados obtidos na separação das bulhas foram, nos sons normais, de 96,96% de acurácia para a S1 e de 97,92% para a S2. Já nos sons cardíacos com sopro, obteve-se a acurácia de 87,46% para a separação da S1 e de 89,26% para a S2. Juntos, os resultados dos sons normais e dos sons com sopro totalizaram uma acurácia de 94,02% para a separação da S1 e de 94,54% para a S2. / New technological tools are often created in the medical field to assist doctors in the clinical diagnosis of many diseases. After being forgotten for many years in the cardiovascular area, cardiac auscultation is now back in the spotlight, as soon as digital stethoscope became available in the market. New digital stethoscope records patient\'s heart sounds, which can be automatically analyzed or also sent to another device for further more detailed investigation. This feature helps physicians in the study of auscultation results. Taking into account the new rise of cardiac auscultation, the present paper attempted to provide the separation of S1 and S2 heart sounds by computer tools, in order to support non-specialist physicians in finding heart sound abnormalities. Heart sound separation can thus be employed for the creation of pattern recognition algorithms, which are able to identify abnormalities automatically. This paper proposed the development of a S1 and S2 heart sound separation algorithm by using Wavelet technique, who was applied upon a database containing 1209 individual heart sounds. The referred database was audited by Royal Portuguese Hospital and Dante Pazzanese Institute of Cardiology medical staff. The best obtained results for S1 and S2 separation in regular heart sounds were a 96.96% accuracy rate for S1 and a 97.92% accuracy rate for S2. In murmur heart sounds were obtained an 87.46% accuracy rate for S1 and an 89.26% accuracy rate for S2. Overall results achieved a 94.02% accuracy rate for S1 and a 94.54% accuracy rate for S2.

Com o avanço tecnológico surgem novas ferramentas que auxiliam os médicos no diagnóstico de diversas doenças. Na área cardiovascular, após permanecer por um longo período em segundo plano, a ausculta cardíaca voltou a ser muito utilizada devido ao surgimento, no mercado, de estetoscópios digitais. Tais aparelhos contam com novos recursos tecnológicos que permitem a captação e a análise de dados de forma automática, oferecendo mais informações ao profissional da área. Levando em conta essa nova ascensão da área de Fonocardiografia,o presente trabalho se dedicou à separação das bulhas S1 e S2 por meio de ferramentas computacionais, com o propósito de auxiliar médicos não especialistas em Cardiologia a verificar a existência de possíveis anormalidades no som cardíaco. Acreditando na possibilidade de este procedimento vir a ser utilizado posteriormente para auxiliar no reconhecimento de padrões dos sons cardíacos, este trabalho se propôs a criar um algoritmo para detecção automática de anormalidades que afetam as bulhas S1 e S2. Assim, aplicou-se a técnica de Wavelet sobre uma base de dados de sons cardíacos constituída de 1209 bulhas, auditada pelo Real Hospital Português e também pelo Instituto Dante Pazzanese de Cardiologia. Os melhores resultados obtidos na separação das bulhas foram, nos sons normais, de 96,96% de acurácia para a S1 e de 97,92% para a S2. Já nos sons cardíacos com sopro, obteve-se a acurácia de 87,46% para a separação da S1 e de 89,26% para a S2. Juntos, os resultados dos sons normais e dos sons com sopro totalizaram uma acurácia de 94,02% para a separação da S1 e de 94,54% para a S2. / New technological tools are often created in the medical field to assist doctors in the clinical diagnosis of many diseases. After being forgotten for many years in the cardiovascular area, cardiac auscultation is now back in the spotlight, as soon as digital stethoscope became available in the market. New digital stethoscope records patient\'s heart sounds, which can be automatically analyzed or also sent to another device for further more detailed investigation. This feature helps physicians in the study of auscultation results. Taking into account the new rise of cardiac auscultation, the present paper attempted to provide the separation of S1 and S2 heart sounds by computer tools, in order to support non-specialist physicians in finding heart sound abnormalities. Heart sound separation can thus be employed for the creation of pattern recognition algorithms, which are able to identify abnormalities automatically. This paper proposed the development of a S1 and S2 heart sound separation algorithm by using Wavelet technique, who was applied upon a database containing 1209 individual heart sounds. The referred database was audited by Royal Portuguese Hospital and Dante Pazzanese Institute of Cardiology medical staff. The best obtained results for S1 and S2 separation in regular heart sounds were a 96.96% accuracy rate for S1 and a 97.92% accuracy rate for S2. In murmur heart sounds were obtained an 87.46% accuracy rate for S1 and an 89.26% accuracy rate for S2. Overall results achieved a 94.02% accuracy rate for S1 and a 94.54% accuracy rate for S2.

Stethoscopes are the most commonly used medical devices for diagnosing heart conditions because they are inexpensive, noninvasive, and light enough to be carried around by a clinician. Auscultation with a stethoscope requires considerable skill and experience, but the introduction of digital stethoscopes allows for the automation of this task. Auscultation waveform segmentation, which is the process of determining the boundaries of heart sound and murmur segments, is the primary challenge in automating the diagnosis of various heart conditions. The purpose of this thesis is to improve the accuracy and efficiency of established techniques for detecting, segmenting, and classifying heart sounds and murmurs in digitized phonocardiogram audio files. Two separate segmentation techniques based on the discrete wavelet transform (DWT) and the simplicity transform are integrated into a MATLAB software system that is capable of automatically detecting and classifying sound segments. The performance of the two segmentation methods for recognizing normal heart sounds and several different heart murmurs is compared by quantifying the results with clinical and technical metrics. The two clinical metrics are the false negative detection rate (FNDR) and the false positive detection rate (FPDR), which count heart cycles rather than sound segments. The wavelet and simplicity methods have a 4% and 9% respective FNDR, so it is unlikely that either method would not detect a heart condition. However, the 22% and 0% respective FPDR signifies that the wavelet method is likely to detect false heart conditions, while the simplicity method is not. The two technical metrics are the true murmur detection rate (TMDR) and the false murmur detection rate (FMDR), which count sound segments rather than heart cycles. Both methods are equally likely to detect true murmurs given their 83% TMDR. However, the 13% and 0% respective FMDR implies that the wavelet method is susceptible to detecting false murmurs, while the simplicity method is not. Simplicity-based segmentation, therefore, demonstrates superior performance to wavelet-based segmentation, as both are equally likely to detect true murmurs, but only the simplicity method has no chance of detecting false murmurs.