TY - GEN
T1 - A neuro-fuzzy approach of bubble recognition in cardiac video processing
AU - Parlak, Ismail Burak
AU - Egi, Salih Murat
AU - Ademoglu, Ahmet
AU - Balestra, Costantino
AU - Germonpre, Peter
AU - Marroni, Alessandro
AU - Aydin, Salih
PY - 2011
Y1 - 2011
N2 - 2D echocardiography which is the golden standard in clinics becomes the new trend of analysis in diving via its high advantages in portability for diagnosis. By the way, the major weakness of this system is non-integrated analysis platform for bubble recognition. In this study, we developed a full automatic method to recognize bubbles in videos. Gabor Wavelet based neural networks are commonly used in face recognition and biometrics. We adopted a similar approach to overcome recognition problem by training our system through real bubble morphologies. Our method does not require a segmentation step which is almost crucial in several studies. Our correct detection rate varies between 82.7-94.3%. After the detection, we classified our findings on ventricles and atria using fuzzy k-means algorithm. Bubbles are clustered in three different subjects with 84.3-93.7% accuracy rates. We suggest that this routine would be useful in longitudinal analysis and subjects with congenital risk factors.
AB - 2D echocardiography which is the golden standard in clinics becomes the new trend of analysis in diving via its high advantages in portability for diagnosis. By the way, the major weakness of this system is non-integrated analysis platform for bubble recognition. In this study, we developed a full automatic method to recognize bubbles in videos. Gabor Wavelet based neural networks are commonly used in face recognition and biometrics. We adopted a similar approach to overcome recognition problem by training our system through real bubble morphologies. Our method does not require a segmentation step which is almost crucial in several studies. Our correct detection rate varies between 82.7-94.3%. After the detection, we classified our findings on ventricles and atria using fuzzy k-means algorithm. Bubbles are clustered in three different subjects with 84.3-93.7% accuracy rates. We suggest that this routine would be useful in longitudinal analysis and subjects with congenital risk factors.
KW - Decompression Sickness
KW - Echocardiography
KW - Fuzzy K-Means Clustering
KW - Gabor Wavelet
KW - Neural Networks
UR - http://www.scopus.com/inward/record.url?scp=79960056384&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-21984-9_24
DO - 10.1007/978-3-642-21984-9_24
M3 - Conference contribution
AN - SCOPUS:79960056384
SN - 9783642219832
T3 - Communications in Computer and Information Science
SP - 277
EP - 286
BT - Digital Information and Communication Technology and Its Applications - International Conference, DICTAP 2011, Proceedings
T2 - International Conference on Digital Information and Communication Technology and Its Applications, DICTAP 2011
Y2 - 21 June 2011 through 23 June 2011
ER -