Mosaic Clinical Technologies Announces FDA Breakthrough Device Designation for Cognita’s Generative AI Model for Radiology

Breakthrough designation means Cognita™ will engage in prioritized interaction with FDA regarding clearance of device designed to help solve the radiology capacity bottleneck

NASHVILLE, Tenn. & MENLO PARK, Calif.--(BUSINESS WIRE)--Mosaic Clinical Technologies™, a wholly-owned subsidiary of Radiology Partners, is pleased to announce that Cognita™, its AI business unit developing generative vision-language models (VLMs) for radiology, has received U.S. Food and Drug Administration (FDA) Breakthrough Device Designation for Cognita Chest X-Ray (CXR)™¹ across multiple critical indications. Cognita CXR is an industry-first generative vision-language model designed to assist radiologists in the interpretation of chest X-rays and is the first radiology generative AI model, and one of very few radiology AI solutions, to be granted this designation².

Cognita CXR¹ applies a proprietary, cutting edge vision-language model to interpret chest X-rays and draft radiology results for physician review. Unlike traditional imaging AI systems that flag the presence of individual findings in isolation, Cognita’s approach analyzes the imaging study and generates comprehensive preliminary findings that are fully-integrated into existing radiology workflows. Licensed radiologists review and finalize the AI-generated findings.

Preliminary internal clinical validation indicates potential for meaningfully enhanced detection and significant capacity gains. For example, internal clinical validation showed that participating radiologists using Cognita CXR achieved enhanced detection of up to 16% - 65% for certain significant findings, showing the model’s potential to significantly improve diagnostic accuracy. Preliminary data also showed the potential to boost the average interpretation efficiency of participating radiologists by 18%.

The FDA’s Breakthrough Device Program is designed to accelerate the development and review of innovative technologies with the potential to significantly improve patient care. The program is reserved for technologies that may offer more effective diagnosis or treatment of life-threatening or irreversibly debilitating conditions. With this designation, Cognita will benefit from prioritized interactions and closer collaboration with the FDA to help bring this breakthrough technology to a US healthcare system under an acute diagnostic capacity strain and in urgent need of new solutions.

“Breakthrough Device Designation marks a significant milestone for Cognita CXR,” said Dr. Nina Kottler, Chief Medical AI Officer at Mosaic Clinical Technologies. “It reflects the urgency of the capacity crisis in radiology and provides the opportunity to work closely with the FDA as we advance through the regulatory process. We believe this is an important step toward bringing AI into everyday radiology practice in a way that enables physicians to practice at the top of their license and expands access to high-quality imaging care worldwide.”

Demand for diagnostic imaging continues to rise globally while the supply of radiologists remains constrained. This significant imbalance is leading to a persistent and acute long-term workforce shortage that increases patient wait times, impacts healthcare facility operations, and contributes to diagnostic errors and radiologist burnout. Delays in imaging interpretation can slow downstream care decisions and contribute to bottlenecks across health systems. Cognita is actively developing and validating solutions to assist radiologists in the interpretation of all X-ray types and 3D computed tomography (CT) imaging across all anatomies, which will be fully incorporated into the Mosaic OS platform.

“Building generative AI that can interpret medical images is one of the most complex challenges in applied AI. Inputs can contain up to 1 billion pixels, encoding entire medical textbooks' worth of information. On top of this, real-world radiology is defined by corner cases,” said Dr. Louis Blankemeier, co-founder and CEO of Cognita. “It requires advanced model architectures, methods breakthroughs, large-scale, real-world clinical data, and reinforcement learning through continuous radiologist feedback. The FDA’s Breakthrough Device Designation enables closer collaboration as we continue evaluating this approach in clinical settings through Radiology Partners’ network.”

“Radiology Partners was founded to transform how radiology is practiced and delivered,” said Rich Whitney, Chairman and CEO of Radiology Partners. “The Breakthrough Device Designation for Cognita reflects our commitment to pairing great physicians with advanced technology to address the growing demand for diagnostic imaging while meaningfully improving the diagnostic value we offer to clients and patients.”

Cognita™ operates as the AI business unit of Mosaic Clinical Technologies™, a wholly owned subsidiary of Radiology Partners, the largest radiology practice in the U.S, with more than 4,000 radiologists in its network. This milestone reflects the strength of a full-stack approach that brings together Cognita’s AI models, Mosaic Clinical Technologies’ workflow and infrastructure platform, and real-world feedback and reinforcement learning from the largest radiology user base globally.

About Mosaic Clinical Technologies™ and MosaicOS™

Mosaic Clinical Technologies™, the technology services division of Radiology Partners (RP), is powering the future of radiology through MosaicOS™—a proprietary imaging management platform designed to meet the specialty’s most pressing challenges. A fully cloud-native and AI-native operating system, MosaicOS™ is where innovation meets impact, seamlessly integrating diagnostic technologies, AI-powered tools and smart workflows into a single scalable solution. Mosaic Clinical Technologies™ supports RP’s national network of affiliated practices and commercial partners across the imaging landscape, redefining what is possible in enterprise imaging. Connect with us on LinkedIn. Contact us at [e-mail].

About Cognita Imaging Inc.

Cognita™, a subsidiary of Mosaic, is a healthcare AI company with a mission to increase the world’s access to healthcare. To achieve this, Cognita's initial focus is on expanding the capacity and quality of radiology by developing comprehensive AI solutions that help radiologists work more accurately, efficiently, and with greater satisfaction. Cognita™ combines breakthrough AI innovation with Mosaic Clinical Technologies’™ radiology infrastructure solutions and the enterprise scale of Radiology Partners, whose network of over 4,000 radiologists performs more than 55 million imaging studies annually. Connect with us on LinkedIn and top tier engineers interested in making an impact on global healthcare should reach out to us at [e-mail].

About Radiology Partners

Radiology Partners, through its affiliated practices, is the leading technology-enabled radiology practice in the U.S., serving more than 3,400 hospitals and other healthcare facilities with high quality radiology, technology and artificial intelligence solutions. As a physician-led and physician-owned practice, our mission is to transform radiology by innovating across clinical value, technology, service and economics, while elevating the role of radiology and radiologists in healthcare. Using a proven healthcare services model, Radiology Partners provides consistent, high-quality care to patients, while delivering enhanced value to the hospitals, clinics, imaging centers and referring physicians we serve. Learn more at radpartners.com and connect with us on LinkedIn, X, Instagram and YouTube. Talented radiologists who want to practice with industry leading, cutting-edge tools should reach out to us at [e-mail].

Meet the Radiology Partners, Mosaic Clinical Technologies™ and Cognita™ teams at the European Society of Radiology Congress (ECR), one of the largest radiology conferences in the world, in Vienna, Austria, March 4-8, 2026.

¹CAUTION: Investigational device. Limited by United States law to investigational use.
² Based on publicly-available information.