Computer Vision News - February 2020

2 Summary Medical Imaging 0 Results : In one study by Madani , et al . a multi - layer CNN was trained to simultaneously classi fy 15 standard views based on label led sti l l images and videos from 267 echocardiograms. The results demonstrated 97.8% overal l accuracy where accuracy among board-certi f ied echocardiographers was 84% or lower. In another, Gao, et al . used CNN architecture integrating two-strand networks for the classi f ication of echocardiography videos from eight viewpoint classes. The resulting classi f ication accuracy was up to 92.1%. Conclusion: Deep Learning for Echocardiography Deep learning is having a profound impact on cardiac ultrasound, both in studies and in clinical use, for detection, classification, segmentation, report generation and tracking in echocardiography. The direct application of neural networks is expected to dramatically improve patient care, from primary identification to disease management, and address challenges to streamlined cardiac care. RSIPVision is a first-mover in deep learning for echocardiography. Here is a link for more information about our computer vision solutions for cardiology.