IIT G Designed An AI Based System To Detect Colorectal Cancer

IIT G Designed An AI Based System To Detect Colorectal Cancer

A team of researchers from the Indian Institute of Technology (IIT) Guwahati has designed an automated Artificial Intelligence (AI)-based system to detect colorectal cancer using colonoscopy images. Colorectal cancer is the third most common type of cancer among men and women in India, but if detected early it can be cured. The commonly used technique to detect colorectal cancer is colonoscopy, in which the specialist — physician, gastroenterologist, or oncologist — visually inspects the image obtained by the camera inserted into the colon of the subject.

"We have developed an innovative automated system that can help the physician rapidly and accurately detect colorectal cancer from colonoscopy images," said researcher Manas Kamal Bhuyan, Professor at IIT Guwahati.

Follow NewsGram on Instagram to keep yourself updated.

In the current manual approach for colonoscopy examination by physicians, observation bias may sometimes lead to an erroneous diagnosis, the researchers said. For the study, published in the journal Scientific Reports, scientists from Cotton University, Guwahati, Harvard University, the University of Texas, and Aichi Medical University, Japan collaborated with the IIT Guwahati professor.

During the visual examination, specialists check for the presence and features of abnormal tissue growths (polyps) including shape, surface structure, and contour to classify them into different categories (neoplastic and non-neoplastic). The multi-institutional team extracted the shape, texture, and color components through AI algorithms using different filters.

The statistical significance in the contribution of different components was then evaluated, followed by feature selection, classifier selection based on six measures, and cross-validation. The research team is excited with their results and believes that their work would have a global impact on the detection of colorectal cancer. (IANS/SP)

Related Stories

No stories found.
logo
NewsGram
www.newsgram.com