Tuesday December 10, 2019

IIT Kharagpur, Tata Medical Center Creates Architecture Image to Aid Cancer Research

Medical imagery can then be combined with AI to enable the reach of treatment to more people as well as provide targeted therapy based on individual symptoms

0
//
cancer research
Digital image archive set up to aid cancer research. Pixabay

Aiming to harness Artificial Intelligence (AI) and deep learning methods for medical queries in the field of image banking, Indian Institute of Technology (IIT) Kharagpur and Tata Medical Center (TMC) have created an architecture image bio-bank to aid cancer research in the country, an official said on Saturday.

The bio-bank, named the Comprehensive Digital Archive of Cancer Imaging (CHAVI), will address the emerging field of imaging-related research. On the success of the pilot project, it can be scaled up to a larger set of medical images. Medical imagery can then be combined with AI to enable the reach of treatment to more people as well as provide targeted therapy based on individual symptoms.

IIT Kharagpur, through the National Digital Library Initiative (NDLI) of the Ministry of Human Resources and Development (MHRD), has joined hands in initiating a pilot project on developing an image data bank for cancer patients, and the present focus is on radio oncology. As a pilot, radiation oncology-related images are being banked within the NDLICHAVI RO project.

cancer research
Medical imagery can then be combined with AI to enable the reach of treatment to more people as well as provide targeted therapy based on individual symptoms. Pixabay

“The overarching aim is to build up a national bank of annotated images with a flexible query interface and link it with a pipeline of radiomic (extracting a large amount of features from radiographic medical images) services for furthering radiomic research in large image datasets,” the official said in a statement.

Also, TMC has created a large repository of medical data and images of cancer patients including outcomes of treatment in many cases. It faced various challenges while building this system. The first and foremost was preserving the anonymity of patients as well as maintaining adequate referential integrity, a necessity for carrying out useful research.

A workshop titled “Structuring a Collaborative National Image Banking Program” supported by MHRD through the NDLI project was organised here on Friday at TMC to enhance the CHAVI project. Several expert doctors from India, the US, the UK and specialists in the area of Computer Science from India participated in the panel discussions and presentations.

cancer research
Several expert doctors from India, the US, the UK and specialists in the area of Computer Science from India participated in the panel discussions and presentations. Pixabay

“We need more affordable solutions in India for cancer treatment, the majority of our patients are middle class and lower middle class and cannot afford genomic analysis. Image banking combined with predictive/prescriptive AI can enable us to identify signatures as a much more cost-effective alternative,” Sanjoy Chatterjee, TMC, Kolkata said.

ALSO READ: UNICEF Reports Unprecedented Number of Children in Congo Infected by Ebola Epidemic

Talking about the unique project, Partha Pratim Chakrabarti from NDLI said: “The CHAVI project is the first of its kind. The objective of the National Digital Library of India is to make accessible material for doing research that normally could not have been done in India. With the CHAVI project, as a beginning, we have chosen cancer imaging database along with Tata Medical Centre because of their tremendous expertise”.

“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,” he added. (IANS)

Next Story

AI-based Algorithm to Help Doctors Treat Traumatic Brain Injury

AI-based algorithm to treat brain injury developed

0
Artificial Intelligence brain
An AI-based algorithm will help doctors treat patients with severe traumatic brain injury (TBI). Pixabay

Researchers, including one of Indian-origin, have developed an artificial intelligence (AI) based algorithm that could help doctors treat patients with severe traumatic brain injury (TBI).

The algorithms can predict the probability of the patient dying within 30-days with an accuracy of 80-85 per cent, said the study published in the journal Scientific Reports.

“A dynamic prognostic model like this has not been presented before. Although this is a proof-of-concept and it will still take some time before we can implement algorithms like this into daily clinical practice, our study reflects how and into what direction modern intensive care is evolving”, said Indian-origin researcher and study author Rahul Raj from Helsinki University Hospital in the Finland.

Traumatic brain injury is a significant global cause of mortality and morbidity with an increasing incidence, especially in low-and-middle income countries.

The most severe TBIs are treated in intensive care units (ICU), but in spite of the proper and high-quality care, about one in three patients dies.

Brain Injury
Traumatic brain injury is a significant global cause of mortality and morbidity. Pixabay

This is why researchers at Helsinki University Hospital (HUS) started to develop an artificial intelligence (AI) based algorithm that could help doctors treat patients with severe TBI.

At its best, such an algorithm could predict the outcome of the individual patient and give objective data regarding the condition and prognosis of the patient and how it changes during treatment.

“We have developed two separate algorithms. The first algorithm is simpler and is based only upon objective monitor data. The second algorithm is slightly more complex and includes data regarding the level of consciousness, measured by the widely used Glasgow Coma Scale score,” said study researcher Eetu Pursiainen.

As expected, the accuracy of the more complex algorithm is slightly better than for the simpler algorithm.

Also Read- Air Pollution Identified as a Life-threatening Illness: Study

“Still, the accuracy of both algorithms is surprisingly good, considering that the simpler model is based upon only three main variables and the more complex upon five main variables”, Pursiainen said.

In the future, the algorithms still have to be validated in national and international external datasets, the researchers concluded. (IANS)