FDA Gives Green Light to MedCognetics’s Breast Cancer Screening AI

MedCognetics has announced that its AI-enabled breast cancer screening software, QMTriage, has been cleared by the U.S. Food and Drug Administration (FDA).

According to the World Health Organization (WHO), breast cancer is the most frequently diagnosed form of the disease worldwide, and the number of new cases is expected to increase from 2.3 million in 2020 to over 3 million by 2040.

As a result of this alarming trend, many AI researchers and developers are hard at work creating algorithms that can spot breast cancer in its earliest, most treatable stages. MedCognetics joins a growing list of companies whose products have been approved by the FDA.

QMTriage accepts regular 2D mammograms, which are analyzed by machine learning algorithms for possible cancer signs. If any are detected, the system assigns labels to them and flags the scan for radiologist review.

Customers can use the digital health software platform on their own computers, in the cloud, or online. This makes it one of the easiest medical AI algorithms to use right now.

MedCognetics collaborated with UTSW Medical Center to create the AI, and the latter also owns a portion of the startup. In order to train the algorithms, UTSW patients’ mammogram images were anonymized. According to CEO Debasish Nag’s statement this week, MedCognetics took special care to include patients of various racial and ethnic backgrounds in the training set in order to guarantee that the AI could be used to reliably screen for cancer in people of all backgrounds.

According to study findings provided to the FDA, QmTriage identified breast cancer symptoms in a test set of 800 mammograms with a sensitivity of 87% and specificity of 89%. Nearly half of these mammograms showed evidence of breast cancer through a subsequent biopsy.

“The American Cancer Society has stated that in 2022 approximately 287,850 new cases of invasive breast cancer will be diagnosed in women,” stated Nag. “MedCognetics is committed to leveraging our technology to help improve outcomes across a diverse group of patients and to do so, partnered with the both University of Texas at Dallas and the University of Texas Southwestern Medical Center to address these disparities.”

Nag referred to the 510(k) clearance of QmTiage by the FDA as a crucial initial step toward the company’s eventual expansion into new types of cancer. The 501(k) application can be compared to the model set by Zebra Medical’s HealthMammo. That device, which uses its own AI to automatically flag suspicious lesions in 2D mammograms, was given the go-ahead in 2020 and functions similarly to the offerings from MedCognetics and Qlarity.

Other companies, such as Paige, RadNet, and even Google’s DeepMind division, have also entered the fray by creating new AI models to detect the disease in various imaging and pathology data.

Radiologists don’t just have QmTriage to choose from when it comes to AI-powered options for accelerating the breast cancer screening process. QuantX, developed by Qlarity Imaging and given the go-ahead by the FDA in 2017, was the first system of its kind to use machine learning AI to detect anomalies in breast scans.

Also, Read the Latest News on Technology & AI