By Conor Hale

The diagnostic imaging provider RadNet has secured two software clearances from the FDA to help radiologists spot cases of breast and prostate cancer. The programs were developed by its artificial intelligence subsidiaries.

The first, led by its wholly owned DeepHealth unit, focuses on automatically identifying suspicious lesions in mammograms. The company’s Saige-Dx software labels each finding with a score based on its potential for harboring breast cancer, including from 2D mammograms and 3D digital breast tomosynthesis scans.

DeepHealth describes Saige-Dx as the successor to its Saige-Q AI-based workflow tool for prioritizing exams for review, which the FDA cleared last year. That program would only help manage a queue by indicating which mammograms contained at least one suspicious finding.

Marrying scientific strategy with eCOA implementation is key to building a successful study and minimizing patient burden. Learn how to implement migration best practices, navigate endpoint development and ensure all strategies are aligned.

According to a paper published early last year in Nature Medicine, DeepHealth’s core algorithms were able to help find smaller, more subtle signs of tumors—ultimately allowing a group of expert radiologists to detect breast cancer earlier by one to two years.

“The feedback from physicians who have worked with our software tools is overwhelmingly positive, making them more accurate and efficient at interpreting mammography images,” said DeepHealth co-founder and CEO Gregory Sorensen, who formerly served as CEO of Siemens Healthcare North America.

RadNet’s second AI clearance, which parses MRI scans for signs of prostate cancer, was obtained by its Quantib division.

Quantib’s software places a variety of automated tools on the radiologist’s reading station, including support for evaluating lesions using standardized scoring methods, calculating PSA density within the tissue and automatically segmenting a complex image of the prostate’s glands into different zones. It also provides a heat map of the organ highlighting areas of concern.

RadNet acquired Quantib this past January in a deal made alongside the separate purchase of Aidence, a company focused on AI-powered lung cancer screening. Both subsidiaries are located in the Netherlands. The Massachusetts-based DeepHealth, meanwhile, was bought by RadNet in 2020.

 “With the addition of Aidence and Quantib, we will now have effective screening solutions for the three most prevalent cancers,” Radnet Chairman and CEO Howard Berger said when announcing the deals.

“While prostate MRI is a growing area of our overall MRI business, the opportunity to create a lower-cost, more accurate service offering to Medicare and private payors allows for a conversation about creating large-scale screening programs for appropriately qualified male patient populations, akin to how mammography is utilized today to detect and manage breast disease in women,” Berger added. RadNet maintains a US network of 350 outpatient imaging centers and about 9,000 employees. The financial details of the Quantib or Aidence deals were not disclosed.

In its recent first-quarter earnings report, the company posted US$341.2 million in revenue from its imaging center segment, alongside losses of US$41.7 million in its AI reporting segment.

“Though we project losses for the next 24 months from the investments we are making in these new technologies, we continue to be more convinced than ever that AI will have a significant impact on the growth and cost structure of our business in the coming years,” Berger said.