نوع مقاله : مقاله کامل پژوهشی
نویسندگان
1 کارشناس ارشد، آزمایشگاه پردازش تصاویر پزشکی، دانشکدهی مهندسی برق، دانشگاه علم و صنعت ایران، تهران، ایران
2 دانشیار، آزمایشگاه پردازش تصاویر پزشکی، دانشکدهی مهندسی برق، دانشگاه علم و صنعت ایران، تهران، ایران
3 دانشجوی دکتری، آزمایشگاه پردازش تصاویر پزشکی، دانشکدهی مهندسی برق، دانشگاه علم و صنعت ایران، تهران، ایران
4 دانشیار، گروه قلب و عروق، مرکز قلب تهران، دانشگاه علوم پزشکی تهران، تهران، ایران
کلیدواژهها
موضوعات
عنوان مقاله English
نویسندگان English
Heart diseases are main cause factors endangering human health and life, one of the most important heart diseases is valvular heart disease, which has had an increasing trend in recent years. Therefore, if they are diagnosed and treated in time and correctly, they can improve the quality of life and increase the life expectancy, so researchers have always been looking for ways to improve and accelerate the process of diagnosing this disease. Medical images monitoring and recording the activity of the human heart are the main ways to diagnose heart diseases. Processing of these images is generally complex and time consuming, so scientists and experts have always been looking for ways to speed up and facilitate the detection process. Manifold learning is one of the nonlinear dimension reduction methods which has different algorithms and can simplify the processing of echocardiographic images. In this study, using one of the manifold learning algorithms named LLE, we examined echocardiographic images of the heart, and tried to categorize groups with mitral disorders while identifying healthy data from those with disorders. Results show that the method has carefully separated the data of the healthy group from the group with the disorder, and good results were obtained in the data classification. The results show that more than 80% of the samples of the natural group have a different pattern in terms of manifold structure from the samples with the disorder.
کلیدواژهها English