FDA approves Arterys AI suite for oncology treatment

Register now

A suite of artificial intelligence tools has been approved by the Food and Drug Administration for use in treating patients, enabling clinicians to quickly measure and track lesions and nodules in MRI and CT scans.

San Francisco-based Arterys, a company that develops cloud-based medical imaging software solutions, was granted 510(k) clearance from the FDA for its Oncology AI suite; it’s the fifth such approval that Arterys has received from the agency, enabling it to make progress toward its goal of applying AI to advance medical imaging accuracy and consistency.

A 510(k) is a premarket submission made to the FDA to demonstrate that a device or application to be marketed is at least as safe and effective—or substantially equivalent—to a legally marketed device.

The company says the new oncology software complements its existing web-based offerings, and helps clinicians measure and track tumors or potential cancers, and easily apply radiological standards. Initial deep learning workflows will be for liver MRI and CT scans as well as for lung CT scans.

Also See: Scientists say artificial intelligence will deliver results in healthcare

With this new technology, radiologists can now confirm, evaluate, quantify and report on the absence or presence of lung nodules and liver lesions along with their key characteristics using a simple web browser. The company plans additional deep learning workflows for solid tumors in other organs.

"The evaluation of primary and metastatic disease in the lung and liver are among the most valuable contributions of radiologists to the care of patients with cancer," said radiologist and Arterys co-founder Albert Hsiao, MD. "We desperately need more efficient technology to automatically track lung and liver lesions to further improve diagnosis, assess response to treatment, and automate reporting with standardized terminology including Lung-RADS and LI-RADS.”

Oncology AI runs on the Arterys MICA (Medical Imaging Cloud AI) platform, which complies with patient data privacy and security requirements in 27 countries. The software uses deep learning to automate the segmentation of lung nodules and liver lesions, with accuracy equal to segmentations performed manually by experienced clinicians. The intent is to enable faster recognition of cancers as soon as possible from imaging studies.

“FDA clearance of our Oncology AI suite will help clinicians to quickly measure and track tumors over time," says Arterys CEO Fabien Beckers. “Additionally, our software enables seamless collaboration for clinicians, so second opinions can be easily gathered from within the hospital, or from outside experts."

For reprint and licensing requests for this article, click here.