Put AI to Work
April 15-18, 2019
New York, NY

Automated medical X-ray image segmentation and medical image classification

Sunil Baliga (Wipro), Sundar Varadarajan (Wipro)
4:40pm4:50pm Tuesday, April 16, 2019
Intel® AI Builders Showcase
Location: Grand Ballroom West

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.

Photo of Sunil Baliga

Sunil Baliga

Wipro

Photo of Sundar Varadarajan

Sundar Varadarajan

Wipro

Sundar Varadarajan is a consulting partner for AI/ML within Wipro’s Product Engineering Service. Sundar has several years of experience with global organizations in information management, business intelligence, advanced analytics, data science, and artificial intelligence. He has worked for multiple industry verticals such as automotive, manufacturing, financial services, and insurance, directing and architecting AI, analytics, and information management solutions. Sundar holds multiple US patents in AI and analytics for data mining, text mining, and OLAP.