• The Journal of the Acoustical Society of Korea
• /
• v.30 no.3
• /
• pp.149-157
• /
• 2011

In this paper, we propose a new cardiac disorder classification method using an support vector machine (SVM) to combine hidden Markov model (HMM) and murmur existence information. Using cepstral features and the HMM Viterbi algorithm, we segment input heart sound signals into HMM states for each cardiac disorder model and compute log-likelihood (score) for every state in the model. To exploit the temporal position characteristics of murmur signals, we divide the input signals into two subbands and compute murmur probability of every subband of each frame, and obtain the murmur score for each state by using the state segmentation information obtained from the Viterbi algorithm. With an input vector containing the HMM state scores and the murmur scores for all cardiac disorder models, SVM finally decides the cardiac disorder category. In cardiac disorder classification experimental results, the proposed method shows the relatively improvement rate of 20.4 % compared to the HMM-based classifier with the conventional cepstral features.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.1045-1048
• /
• 2000

This paper presents the application of the wavelet transform analysis and the neural network method to the phonocardiogram (PCG) signal. Heart sound is a acoustic signal generated by cardiac valves, myocardium and blood flow and is a very complex and nonstationary signal composed of many source. Heart sound can be discriminated normal heart sound and heart murmur. Murmurs have broader frequency bandwidth than the normal ones and can occur at random position of cardiac cycle. In this paper, we classified the group of heart sound as normal heart sound(NO), pre-systolic murmur(PS), early systolic murmur(ES), late systolic murmur(LS), early diastolic murmur(ED). And we used the wavelet transform to shorten artifacts and strengthen the low level signal. The ANN system was trained and tested with the back- propagation algorithm from a large data set of examples-normal and abnormal signals classified by expert. The best ANN configuration occurred with 15 hidden layer neurons. We can get the accuracy of 85.6% by using the proposed algorithm.

• Journal of Chest Surgery
• /
• v.23 no.3
• /
• pp.532-536
• /
• 1990

We experienced surgical correction of 2 cases of discrete membranous subaortic stenosis. Case 1 was 19 years old male patient. His complaints were fatigue, exertional dyspnea, syncope and angina for 8 years. Ejection. systolic murmur was heard at the second right intercostal space and diastolic murmur was heard at the apex. A thrill was palpated over the second right intercostal space and area of the carotid artery. 2-D echo, cardiac cath and left ventriculogram revealed discrete membranous subaortic stenosis and VSD. Complete excision of discrete membrane without mymectomy was done. VSD was closed with dacron patch and aortic valve was replaced with St. Jude medical valve. Case 11 was 16 years old female whose complaints were exertional dyspnea and syncope. Ejection systolic murmur was heard at second right intercostal space, but diastolic murmur was not heard. A thrill was palpated over the second right intercostal space and the area of carotid artery. 2-D echo, cardiac cath and left ventriculogram revealed discrete membranous subaortic stenosis. Complete excision of fibrous tissue and myotomy were made and aortic valve was replaced with St. Jude medical valve. Operative finding was followed: both aortic valves showed deformity of leaflets. Subaortic region had a thickened central fibrous body from which the ridge protruded. Both patient`s postoperative course were uneventful and short-term follow-up results were good except soft systolic murmur at the aortic area.

• Journal of Korea Multimedia Society
• /
• v.19 no.3
• /
• pp.557-566
• /
• 2016

Heart sounds generated by the beating heart and blood flow reflect the turbulence created when the heart valves snap shut. Cardiac diagnosis is typically started by an auscultation using a stethoscope, from which a medical doctor, depending on his hearing capabilities and training, listens and interprets the acoustic signal. This method of diagnostic is uncertain, mostly due to the fact that human ear loses the acoustic frequency sensitivity through the years. Even though an auscultation has some weaknesses like uncertainty, it is considered as a primary tool due to its simplicity. In this paper, heart murmur detection algorithm is proposed using time and frequency characteristics of heart sound. The propose heart murmur detection method adapted conventional primary heart sound detection method in time domain and modified spectral flatness method in frequency domain for detecting heart murmurs. From experimental results, it is confirmed that the proposed algorithm detect the heart murmurs efficiently.

• Journal of Chest Surgery
• /
• v.17 no.4
• /
• pp.780-785
• /
• 1984

We had studied 20 cases of VSD patients whose murmur was sustained after open heart surgery from 1977 to 1984. The postoperative cardiac catheterization was performed on post-op. 20th day. Their ages ranged from 5 to 25 years old. Among them, 4 patients had significant residual shunt which required reoperation. [1 patient; re-op, 3 patient; refused]. Sex ratio was 13:7 in male and female. Associated anomalies were PDA, ASD, Pulmonary stenosis, Mitral insufficiency. Except 1 case, all of them was Kirklin type II VSD. Postoperative complications were I RBBB, residual shunt, cardiac tamponade due to bleeding, wound infection. Preoperative pulmonary artery systolic pressure was highly related to residual shunt in our study. Postoperative LVEDV returned to normal range on the 3rd week.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.38 no.5
• /
• pp.59-69
• /
• 2001

Recently many researches concerning heart sound analysis are being processed with development of digital signal processing and electronic components. But there are few researches about recognition of heart sound, especially full cardiac cycled heart sound, In this paper, a new recognition methods about. full cardiac cycled heart sound was proposed. For the first, the database was built by principal components analysis on training heart sound set. This database is used to recognize new input of heart sound, Ilear sounds were classified into seven classes such as normal(NO) class, pre-systolic murmurr(PS) class, early systolic murmur(ES) class, late systolic murmurr(LS) class, early diastolic murmur(EI) class, late diastolic murmur(LD) class and continuous murmuru(CM) class. As a result, we could verify that our new method has better efficiencies for the recognition the characteristics of heart sound than any precedent research. The maximum recognition rates of the new method are 71% for NO, 80% for PS and ES, 78% for LS, 87% for ED, 60% for LD and 20% for CM. Although the present results aren't practically sufficient to use our new method in recognizing heart sound, the importance of this paper is for recognition of heart sound within full cardiac cycle. We can get a better result by building a more efficient database.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.2
• /
• pp.133-140
• /
• 2010

We improve the performance of cardiac disorder classification by adding new temporal features extracted from continuous heart sound signals. We add three kinds of novel temporal features to a conventional feature based on mel-frequency cepstral coefficients (MFCC): Heart sound envelope, murmur probabilities, and murmur amplitude variation. In cardiac disorder classification and detection experiments, we evaluate the contribution of the proposed features to classification accuracy and select proper temporal features using the sequential feature selection method. The selected features are shown to improve classification accuracy significantly and consistently for neural network-based pattern classifiers such as multi-layer perceptron (MLP), support vector machine (SVM), and extreme learning machine (ELM).

• Journal of Chest Surgery
• /
• v.23 no.4
• /
• pp.758-763
• /
• 1990

A congenital fistulous communication between the coronary artery and the cardiac chamber or the pulmonary artery is a rare condition, but increasing cases with this anomaly are being recognized with wide spread use of cardiac catheterization and coronary arteriography. Recently we experienced one case of right coronary artery fistula which was associated with atrial septal defect. The patient was a 24 year old female who was admitted because of cardiac murmur, palpitation and dyspnea on exertion after pregnancy. Cardiac catheterization and selective coronary arteriography revealed that a fistulous communication, forming a large aneurysm, was noted from the right coronary artery emptied into the right ventricle. On the operation field, the right coronary artery was curved and markedly dilated from the aorta to the middle segment at acute margin of the right ventricle. The egg-sized aneurysm of dilated right coronary artery was noticed on right ventricle. The aneurysm was incised longitudinally and both the proximal opening and the termination site of the fistula were closed directly with aneurysmectomy. The right atrium was also opened to evaluate the fistulous termination site and repaired only small interatrial septal defect. Postoperative course was uneventful and she was discharged without problems

• Korean Journal of Veterinary Research
• /
• v.56 no.4
• /
• pp.261-264
• /
• 2016

A nine-month-old Pomeranian dog with exercise intolerance and syncope was presented. The dog was depressed with grade 4 systolic murmur on cardiac auscultation. Based on cardiac examination, the dog was diagnosed with severe subaortic stenosis with involvement of the anterior mitral valve. ${\beta}-blocker$ administration was initiated and clinical signs were improved, but not fully resolved. Balloon valvuloplasty was performed and the dog survived for nearly one year without clinical sign and the cardiac troponin I level was normalized. This case describes successful management of severe subaortic stenosis in a small breed dog through balloon valvuloplasty.

• Journal of Chest Surgery
• /
• v.21 no.4
• /
• pp.716-720
• /
• 1988

Since Krause first described coronary arteriovenous fistula in 1865, there have been nearly 300 additional patients with this malformation reported in the literature. Increasing numbers of patients with this anomaly are being recognized each year resulting from the widespread use of cardiac catheterization and selective coronary arteriography in the evaluation of a variety of cardiac problems. A 9 month old male was admitted with the chief complaint of cardiac murmur and frequent URI and diagnosed as coronary A-V fistula at the distal portion of left anterior descending coronary artery to the apex of the right ventricle by cardiac catheterization and aortography. On the operative field, the left anterior descending coronary was markedly dilated about 1.5 cm in diameter from the aorta to the apex of the heart. The fistula opening was closed with 5-0 Prolene continuously under cardiopulmonary bypass and moderate hypothermia[28*C]. Postoperative course was uneventful and the patient was discharged without problem.