Automated medical X-ray image segmentation and medical image classification

Medical experts spend significant time and effort in diagnosing medical images, which involves segmentation of region of interest and classification of images for diagnostics. Sunil Baliga and Sundar Varadarajan share Wipro’s medical image segmentation and diagnosis solution—a deep learning platform that can assist in the process of image segmentation and diagnosis, which improves speed and productivity.

This solution was developed using 8th generation Intel Core i7 processors and the Intel Distribution of OpenVINO. It segments the lung area in a CT scan and classifies chest and lung X-rays and CT scans as either “normal” or “abnormal” for diagnostics. Results have shown high accuracy with this solution—about 90% on segmentation and over 97% on classification for each image.