Loading

Mitral Valve Abnormality Detection by fully end to end with Deep Neural Network
Vishal Chandra1, Vinay Singh2, Prattay Guha Sarkar3

1Vishal Chandra*, computing and information technology Usha Martin University, Ranchi, India.
2Vinay Singh, computing and information technology Usha Martin University, Ranchi, India.
3Prattay Guha Sarkar, cardiology, RIMS, Ranchi, India.
Manuscript received on January 24, 2020. | Revised Manuscript received on February 05, 2020. | Manuscript published on February 30, 2020. | PP: 1997-2004 | Volume-9 Issue-3, February 2020. | Retrieval Number: C5372029320/2020©BEIESP | DOI: 10.35940/ijeat.C5372.029320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The purpose of this research is to automatically identify normal and abnormal mitral leaflets in an apical four-chamber view.one of the widely spread valvular diseases is mitral valve disease in underdeveloped countries, still a burden for health sociality as well as countries. around 80 percent of valvular diseases are mitral valve disease problems. As far as World Heart Foundation Guidelines are concerned, It is totally based on mitral leaflets morphology. Due to the dependency on the sonographer’s experience, it is highly subjective for argument. Measurement of thickness of leaflets, calcification detection, the pliability of leaflets required high experience about echocardiography as well as morphology. The motive of this research is to automatically identify the normal or abnormal mitral valve. If there is an abnormality in mitral leaflets then further investigation needed otherwise there is no further investigation that means measuring thickness, mitral valve area should not be required to measure. This research consists of two parts first automatically localize the region of interest second classifies the mitral leaflets whether normal or abnormal for localization yolo3 model mechanism with custom backend instead of darknet is used for taking area of interest automatically and for classification of normal and abnormal mitral leaflets, proposed pipeline is used, having f1, mAp score, and other matrices have measured.PR and ROC curves are drowned to support the results in the evaluation. the motive of this research is to serve nonexpert to identify abnormalities in mitral leaflets and sonographers to assess more efficiently. We used the Apical four-chamber view for this research.
Keywords: Object detection, Mitral valve detection, classification, abnormalities.