Cardiovascular Segmentation using Fully Convoluted Networks

Today, radiologists read increasing amount  of medical images to diagnosing  and treating injuries and diseases.  According to Mayo Clinic, there is an increase in ~500% of MR images from 1999.  In detecting cardiovascular disease, doctors rely on MRI cardiac imaging. Fully automatic segmentation enables doctors to measure structural and functional of the cardiac anatomic regions (especially right ventricle and left ventricle) of interest efficiently.  In this presentation, I will talk about our fully convolutional network architecture that learns from 2D slices of MRI cardiac images to  enable fully automated left ventricle segmentation. Also, I will talk about our challenges in available data sets, reducing computational time and enabling real-time detection.
 

Arvind Rapaka is VP of Engineering at Techvedika. He founded eComtics - acquired by Techvedika. He has over 14 years of engineering development experience. He has held held leadership roles at Yahoo, Veraz Networks, and GE. He has as published papers in IEEE and other technical journals.