AI Case Study

Niramai develops screening tool that improves breast cancer diagnosis using machine learning

Niramai leverages machine learning along with big data analytics and thermal image processing to detect subtle abnormalities that cells display at very early stages of breast cancer. The tool is radiation-free, painless and contact-free and promises to reduce over diagnosis and false positives and overall improve diagnosis, in a country where breast cancer is the most common cancer in women.

Industry

Healthcare

Healthcare Equipment And Supplies

Project Overview

"In India, where incidences of breast cancer are rising, Niramai is using machine learning algorithms, big data analytics and thermal image processing to improve breast cancer diagnosis. The company's screening tool is said to be able to detect breast cancer based on subtle abnormalities that cells display as the disease begins to take hold. “Most available screening tests can detect tumors in breasts, but more than 60% of them are harmless,” says Manjunath. “Our screening tool looks for tissue abnormality and identifies only lumps that may be cancerous.”

using the technology to diagnose breast cancer has huge benefits in a country that has one of the lowest doctor-patient ratios in the world. While it may not outright replace mammography any time soon, it is increasingly finding acceptance with hospitals, and the business has begun to gain traction, although not yet turned a profit.

The radiation-free, painless, contact-free device addresses most of the problems that conventional mammograms grapple with by reducing overdiagnosis and false positives. “Since it doesn't involve touching a patient, it is more acceptable to women who shy away from clinical screening,”  she adds."

Reported Results

"Artificial intelligence (AI) – or deep learning – can save vast amounts of time and give much more accurate results, according to Geetha Manjunath, the cofounder of health tech startup Niramai."

Technology

"Niramai's screening tool uses machine learning and thermal imaging to detect cancerous tumours"

Function

R And D

Product Development

Background

"The field of cancer diagnosis is constantly evolving and changing, but diagnosticians still struggle to keep up with demand. Examining images and data is time-consuming and relies on the judgment and skills of highly specialized experts.

In India, breast cancer is the most common cancer in women, with rate as high as 25.8 per 100,000 women and mortality 12.7 per 100,000 women. According to a study, lack of early diagnosis of breast cancer may kill 76,000 Indian women a year by 2020. Worse still, India has a low survival rate for breast cancer, with just 66.1% women diagnosed with the disease between 2010 and 2014 surviving."

Benefits

Data

scans