IIT Kharagpur and Tata Medical Center have set up a national bank of images of CT scan, MRI scan, PET scan and other imaging procedures to facilitate sharing of data in cancer research, a common practice in western countries.

The project, Comprehensive Digital Archive of Cancer Imaging (CHAVI), intends to apply artificial intelligence and deep learning methods to decode the hidden signature from the images and provide targeted therapy based on individual symptoms.

The national bank of medical images was talked about at a workshop on “Structuring a Collaborative National Image Banking Program”, organised by the two institutions at Tata Medical Center in New Town on Friday.

“Cancer is one of the most dreaded diseases in our country. If we are able to create a very well defined, annotated database, it will help researchers as well as doctors to be able to do early, more accurate diagnosis and provide better treatment for our people, which is a lot more cost effective,” said Parthapratim Chakrabarti, a former director of IIT Kharagpur, who attended the workshop.

The IIT, through the National Digital Library Initiative (NDLI) of the ministry of human resource development, is contributing to a pilot project on developing an image data bank for cancer patients, said Partha Pratim Das, a professor of computer science and engineering at the institute.

“It’s a common practice in the west to have a common bank for hospitals to share data on diseases like cancer. This helps doctors dig deep into records and history of the patients and then decide on making accurate diagnosis and start the treatment. Through this project we intend to introduce the practice here. This is a pilot project. Later, more hospitals are expected to be part of it,” said Das.

As part of the pilot project, radiation oncology-related images are being banked within the National Digital Library Initiative Digital Archive of the Cancer Imaging project.

The workshop, coordinated by Sanjoy Chatterjee of Tata Medical Center and professor Jayanta Mukhopadhyay from IIT Kharagpur, included presentations and panel discussions with experts in medical and computer science/artificial intelligence.

Several doctors from India, the US and the UK and computer science specialists from India also took part in the day-long proceedings.

Emiliano Spezi from Cardiff University explained the importance of the project: “The scope of image banking is to enable cancer research and move it forward, to access data that is more diverse and come from different centres, different patients and different ethnic groups to help doctors make more informed decisions and deliver personalised treatments.”

Indrajit Mallick, a doctor attached to the radiotherapy unit of the Tata Medical Center, said the advanced techniques were expected to decode a lot of features from the images that still remain unknown.