A team of researchers from the Indian Institute of Technology Guwahati (IIT Guwahati) led by Prof. Manas Kamal Bhuyan, Professor, Dept of Electronics and Electrical Engineering of IIT Guwahati, along with scientists from renowned research institutes around the world, have designed an automated Artificial Intelligence-based system to detect colorectal cancer using colonoscopy images. Results of their work have recently been published in a prestigious journal belonging to the Nature group – Scientific Reports.  The paper has been co-authored by Dr. Kangkana Bora of Cotton University, Guwahati, Dr. Kunio Kasugai of Aichi Medical University, Japan. Prof. Zhongming Zhao from the University of Texas, Health Science Centre, Houston, USA, and Dr. Saurav Mallik of

Harvard University, USA have also contributed to the study.

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.  In the current manual approach for colonoscopy examination by physicians, observation bias may sometimes lead to an erroneous diagnosis.

“We have developed an innovative automated system that can help the physician rapidly and accurately detect colorectal cancer from colonoscopy images,” says Prof. Bhuyan, Professor, Dept of Electronics and Electrical Engineering of IIT Guwahati.  This is important because it prevents delays in diagnosis – quoting the late doyen of oncology Dr. V. Shanta “Fear not cancer diagnosis, but its delay.”  Furthermore, currently doctors waste a lot of time and energy on manually analysing the images, valuable time that can be spent on devising management and treatment strategies for the patient.

Scientists from Cotton University, Guwahati, Harvard University, University of Texas Health Science Centre Houston and Aichi Medical University, Japan have collaborated with the IIT Guwahati professor in this development. Assisted by his then-post doctorate student, Dr. Kangkana Bora, who is now an assistant professor at the Cotton University, Prof Bhuyan analysed real colonoscopy images generated by Dr. Kunio Kasugai of Aichi Medical University, to develop the AI based cancer detection system.

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 artificial intelligence 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.

“Our extensive experiments show that the proposed method outperforms the existing feature-based (conventional) approaches for colonic polyp detection,” the authors write in their paper. To evaluate the robustness of their system, they compared their work with four classical deep learning models and found theirs to be better than others. “Our AI algorithm can be easily integrated with the current methods of diagnosis, which is a significant USP for this work,” says Dr. Kangkana Bora, then the Post Doctorate student of IIT Guwahati and currently Assistant Professor at the Cotton University.

The research team is excited with their results and believe that their work would have a global impact in the detection of colorectal cancer. They plan to commercialize the technology in the future as the market need is enormous. However, before commercialization, they have laid out an ambitious research plan to finetune their system.

“The work we have reported only focuses on single frames selected by the doctors. In future, we will integrate it with video tracking and automatic frame selection”, says Prof. Bhuyan. The team also proposes to implement their analytical approach into a computational tool for easy use.