AZmed receives its 6th FDA clearance, taking Rayvolve to eight FDA-cleared findings across MSK and chest X-rays

PARIS, Sept. 15, 2026 -- AZmed, one of the leading AI companies in medical imaging, today announced its 6th U.S. Food and Drug Administration (FDA) clearance. AZchest, the company's AI tool for the analysis of thoracic abnormalities, is now cleared in the United States to detect and localize pneumothorax, pleural effusion, consolidation, and increased cardiothoracic ratio on frontal chest radiographs.

Together with lung nodules, cleared for detection in March 2025, AZchest now has five findings on a single image, bringing the Rayvolve AI suite to eight FDA-cleared findings for both musculoskeletal and chest X-rays. That makes it one of the broadest X-ray AI offerings on the U.S. market.

Chest radiography is the most common examination performed in radiology. Findings that alter patient management are not always the most conspicuous, and interreader agreement varies, particularly outside of thoracic subspecialty practice.

This new clearance was supported by two studies. In a standalone assessment of 8,453 per-finding evaluations, AZchest achieved an area under the curve (AUC) of 0.94 to 0.98 for all four findings, with per-image sensitivity between 90.8% and 97.0% and per-image specificity between 87.9% and 92.1%.

Then a multi-reader, multi-case study of 1,489 per-finding case evaluations assessed the effect on reader performance. Twenty readers (including 10 thoracic radiologists) interpreted the cases without AI and then with AZchest, with a one-month washout period in between. Reader AUC rose across the board, from 0.88 to 0.89 unaided to 0.91 to 0.94 aided, and both sensitivity and specificity improved. Thoracic radiologists recorded up to a 15.9% decrease in reading time, and readers from other specialties up to 31.0%.

"Radiologists should not need a different AI tool for every finding on the same image," said Julien VIDAL, CEO of AZmed. "We are building one suite that covers the X-ray, and every step of it carries strong clinical evidence."

U.S.-based SimonMed provided all of the clinical data behind this clearance, with images from its centers used in both the standalone assessment and the reader study. The relationship dates to 2023, when SimonMed selected AZmed as its X-ray AI partner, and its data also supported AZmed's 2024 pediatric fracture clearance. This year, SimonMed led the largest published study of AI in X-ray imaging, examining the Rayvolve AI suite across 258,373 exams from 100 medical centers in 26 countries, which was published in Radiography with Dr. Sean Raj as senior author.

This announcement comes after AZmed extended AZtrauma to joint effusions and dislocations in May 2026, building on its earlier clearance for fracture detection. That expansion also drew on SimonMed data.