Earlier Breast Cancer Detection with Artificial Intelligence

Published May-25-19

A low-cost, pain-free breast cancer screening solution that uses machine learning and artificial intelligence to detect breast cancer earlier than traditional methods.

Niramai, India

The Story:

Earlier Breast Cancer Detection with Artificial Intelligence Breast cancer is the cause of the greatest number of cancer-related deaths among women. According to the World Health Organization (WHO), approximately 627,000 women died from breast cancer in 2018, around 15% of all cancer deaths among women. Early diagnosis is a key step to decreasing mortality rates.

With that goal in mind Geetha Manjunath and Nidhi Mathur from Bangalore founded Nirami (an acronym for non-invasive risk assessment with machine intelligence) in 2016. This health tech startup uses artificial intelligence and image analysis technology to detect breast cancer at a much earlier stage than traditional methods including self-examination.

The principal technology of Nirami's solution is an AI-led diagnostic platform that uses thermal image processing and machine learning algorithms for breast cancer screening. It is a non-invasive procedure that doesn't require radiation or any incisions and can be used in hospitals and for preventative health checkups.

How it Works

A low-cost device is placed about three feet in front of a patient and takes five high-resolution thermal images of the chest area. AI is applied to them to detect the presence of tumors, and a report is sent to a certified senior radiologist.

“Reading images accurately to distinguish a normal thermal activity from an abnormal one is a computer vision problem. That is where the AI comes in because it can do pattern-based recognition,” said Manish Singhal (founding partner at pi Ventures, which provided Nirami with seed funding) in an interview with Forbes India.

Successful Trials

As of April 2019, Nirami's patented Thermalytix technology has been tested on more than 4,000 women in 12 hospitals/diagnostic centers. Additionally, three clinical trials have compared Thermalytix with current screening methods and the results published in peer-reviewed journals/conferences.

Among the key findings are:

• 27% higher accuracy than mammography.
• Able to detect cancer lesions as small as 4 mm with no palpable lumps.
• 70% higher positive predictive value than visual interpretation of thermography.

Nirami vs Mammography

Nirami has significant advantages over mammography. They include:

1)Unlike mammography which has a high capital cost for equipment and radiographers, Nirami is a low-cost solution.

2)Mammography is recommended for women over 45 years because it can't effectively detect tumors in younger women. It also uses X-rays for scanning, exposing women to radiation. Nirami, on the other hand, can detect tumors in women of all ages, even those under 40 and does not involve radiation.

According to WHO the incidence of breast cancer in women under 40 is increasing, therefore the need for earlier detection is crucial.

3)Mammography can be painful as weight is applied to the breasts during screening. There is no touch involved with Nirami's system and it is pain free.

4) Automated detection of tumors using machine intelligence.

Increasing Uptake

Having demonstrated the multiple benefits of an AI approach the task now is to increase take-up of Nirami’s system in India and other countries as well.

“The medical industry in general and oncology in particular, it's very difficult to change the behavior of users,” commented Nidhi Mathur, Co-Founder and COO, Nirami.

“And that has been our biggest challenge because we have come up with something that does things differently from what they have been seeing earlier in their lives.

“And it has been a challenge to make people understand there is a new way and there's a better way to do things now and have people accept that. Our work has primarily concentrated in India, but we always believe the opportunity ahead of us is global in nature.”

Share on      
Next Story »

What Can we Solve for You?