DeepHealth to Present Recent Clinical Evidence Demonstrating the Breadth and Impact of Its AI Portfolio at RSNA 2026
Studies across breast, thyroid, lung and prostate imaging highlight advances in cancer detection, risk assessment and
Press Release Disclaimer: This is a press release distributed through the XPR Media network. It has not been independently verified by our newsroom.

![]()
CHICAGO, Nov. 19, 2026 (GLOBE NEWSWIRE) — DeepHealth, a global leader in AI-powered health informatics and a wholly owned subsidiary of RadNet, Inc. (Nasdaq: RDNT), will present recent evidence on the clinical and workflow impacts of its AI-powered solutions across breast, thyroid, lung and prostate imaging at the Radiological Society of North America (RSNA) 2026 annual meeting.
Five podium presentations and two scientific posters will explore the role of DeepHealth AI in cancer detection, risk assessment and faster, more consistent interpretation across cancer types and imaging modalities.
Clinical podium presentations
All presentation times are U.S. Central Time.
- AI improves thyroid ultrasound report consistency1
Sunday, Nov. 29, at 9 a.m.
In a prospective, real-world deployment of DeepHealth’s Thyroid Solution across more than 90,000 exams in the U.S., radiologists retained all five AI-generated nodule descriptors without modification in 88.7% of nodules. The findings demonstrate the feasibility of incorporating AI-generated reporting into routine care and its potential to improve report consistency and expedite the radiologist workflow.
- AI improves prostate cancer detection across readers and populations2
Monday, Nov. 30, at 8 a.m.
Variation in prostate MRI interpretation across patient populations and reader experience levels can affect follow-up recommendations. This reader study evaluates DeepHealth’s AI-powered prostate cancer detection across patient populations, imaging acquisitions and readers with varying experience levels. The findings suggest that AI-enabled prostate MRI could improve lesion localization and streamline workflows, supporting more consistent interpretation and follow-up across clinical settings.
- AI flags potential breast cancer risk years before diagnosis in U.S. screening3
Sunday, Nov. 29, at 1:15 p.m.
Research in a diverse U.S. population examined the ability of DeepHealth’s AI to review prior digital breast tomosynthesis (DBT) screening exams and flag the breast that will later be diagnosed with cancer, exploring its potential to identify signs associated with future cancer earlier. Using DeepHealth’s AI in DBT to detect cancer risk early could improve breast cancer outcomes, particularly in the U.S., where DBT is prevalent.
- AI detection in dense breasts includes aggressive and nonaggressive cancers4
Tuesday, Dec. 1, at 9:30 a.m.
Building on the ASSURE study, published in Nature Health and encompassing 579,583 exams and 2,762 cancers, this analysis of a real-world deployment found higher overall, invasive and aggressive cancer detection in women with dense breasts using DeepHealth’s AI-powered screening workflow. The findings suggest that the workflow’s benefits extend to cancers with potentially greater clinical consequences.
- Image-based risk model supports personalized breast cancer risk assessment5
Wednesday, Dec. 2, at 10 a.m.
Traditional breast cancer risk models such as Tyrer-Cuzick can underestimate risk in underserved populations, particularly Black women. This retrospective study evaluates DeepHealth’s image-only deep learning model using DBT images to predict breast cancer risk. The model performed strongly in identifying women at elevated risk, with estimates closely matching observed cancer rates across patient subgroups. The findings support its potential to help physicians personalize screening and follow-up through more equitable risk assessment.
Two scientific posters will examine opportunities to improve the consistency and specificity of AI-supported mammography interpretation:
- Breast arterial calcification detection6
Sunday, Nov. 29, at 11:45 a.m.
Breast arterial calcifications (BAC) may indicate cardiovascular and peripheral vascular disease,7 yet detection and reporting of BAC remain inconsistent and subjective despite emerging notification requirements. This retrospective evaluation of DeepHealth’s AI algorithm for detecting and localizing BAC found high performance across imaging modalities, breast densities and patient ages. The findings suggest AI could help standardize reporting of BAC, allowing radiologists to identify a risk marker from existing mammograms that may prompt further assessment.
- Incorporating prior exams reduces false-positive findings8
Wednesday, Dec. 2, at 12:45 p.m.
Radiologists compare current and prior exams to distinguish interval changes from stable findings and avoid unnecessary recalls, yet many AI devices analyze mammograms in isolation. This study examines how incorporating prior mammograms in DeepHealth’s AI algorithm can reduce false-positive AI detections in DBT images, potentially reducing the unnecessary review of benign findings and helping radiologists focus on more relevant findings.
“Our connection to RadNet and our collaboration with customers and clinical partners worldwide keep real-world clinical insights at the heart of how we develop and validate AI,” said Sham Sokka, Chief Operating and Technology Officer, DeepHealth. “The evidence we generate builds confidence in its use and guides how we bring clinical and operational intelligence together in everyday practice across the imaging journey and care settings.”
DeepHealth’s scientific program at RSNA builds on an expanding body of clinical evidence, including hundreds of publications, peer-reviewed studies and real-world evidence.9 This year, peer-reviewed publications highlighted the clinical and operational value of AI across breast, prostate and lung imaging. Recent findings include a DeepHealth study published in Radiology showing that an AI-supported screening workflow improved general radiologists’ breast cancer detection, narrowing the performance gap with breast imaging specialists.10 A retrospective study published in European Radiology found that combining radiologists’ prostate MRI assessments with AI risk classification could have avoided nearly one in five biopsies while maintaining 98.4% sensitivity for clinically significant cancer.11 In lung imaging, an independent retrospective study of 39,323 chest CT exams at Erasmus Medical Center found that DeepHealth’s lung AI technology12 was associated with a 14.6% reduction in adjusted median reporting time, suggesting potential efficiency and capacity benefits.13
DeepHealth will exhibit at RSNA 2026, Nov. 29-Dec. 2 in Booth 1329, South Hall, at McCormick Place in Chicago. DeepHealth will also host Experience Theater sessions with clinicians, customers and industry experts on AI in practice and the future of imaging. For more information about DeepHealth at RSNA 2026, visit deephealth.com/RSNA-2026.
About DeepHealth
DeepHealth is a wholly owned subsidiary of RadNet, Inc. (NASDAQ: RDNT) and serves as the umbrella brand for RadNet’s Digital Health segment. DeepHealth provides AI-powered health informatics with the aim of empowering breakthroughs in care through imaging. DeepHealth leverages advanced AI for operational efficiency and improved clinical outcomes in breast, chest, musculoskeletal, neuro, prostate and thyroid health. At the heart of DeepHealth’s portfolio is a cloud-native operating system – DeepHealth OS – that unifies data across the clinical and operational workflow. Thousands of imaging centers and radiology departments around the world use DeepHealth solutions to enable earlier, more reliable and more efficient disease detection, including in large-scale cancer screening programs. DeepHealth’s human-centered, intuitive technology aims to push the boundaries of what’s possible in healthcare. Learn more at deephealth.com.
About RadNet, Inc.
RadNet, Inc. is a leading national provider of freestanding, fixed-site diagnostic imaging services in the United States based on the number of locations and annual imaging revenue. RadNet has a network of owned and/or operated outpatient imaging centers. RadNet’s imaging center markets include Arizona, California, Delaware, Florida, Idaho, Indiana, Maryland, New Jersey, New York, Texas and Virginia. In addition, RadNet provides radiology information technology and artificial intelligence solutions marketed under the DeepHealth brand, radiology professional services and other related products and services to customers in the diagnostic imaging industry globally. Together with contracted radiologists, and inclusive of full-time and per diem employees and technologists, RadNet has over 12,000 team members. Learn more at radnet.com.
Forward Looking Statements
This communication contains certain “forward-looking statements” within the meaning of the safe harbour provisions of the U.S. Private Securities Litigation Reform Act of 1995, Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934, as amended. Forward-looking statements can be identified by words such as: “anticipate,” “believe,” “could,” “estimate,” “expect,” “forecast,” “intend,” “may,” “outlook,” “plan,” “potential,” “possible,” “predict,” “project,” “seek,” “should,” “target,” “will” or “would,” the negative of these words, and similar references to future periods. Examples of forward-looking statements include statements regarding our technology’s ability to stage-shift disease through proactive, timely intervention and discussions regarding our product features. Actual results could differ materially from those currently anticipated due to a number of risks and uncertainties, many of which are beyond RadNet’s control.
Forward-looking statements are neither historical facts nor assurances of future performance. Instead, they are based only on management’s current beliefs, expectations and assumptions regarding the future of RadNet’s business, future plans and strategies, projections, anticipated events and trends, the economy and other future conditions. Because forward-looking statements relate to the future, they are subject to inherent uncertainties, risks and changes in circumstances that are difficult to predict and many of which are outside of RadNet’s control. RadNet’s actual results and financial condition may differ materially from those indicated in the forward-looking statements as a result of various factors. Neither RadNet, nor any of its directors, executive officers, or advisors, provide any representation, assurance or guarantee that the occurrence of the events expressed or implied in any forward-looking statements will actually occur, or if any of them do occur, what impact they will have on the business, results of operations or financial condition of RadNet. Should any risks and uncertainties develop into actual events, these developments could have a material adverse effect on RadNet’s business and the ability to realize the expected benefits of the technology. Risks and uncertainties that could cause results to differ from expectations include, but are not limited to: (1) the ability to recognize the anticipated benefits of the technology, and (2) the risk of legislative, regulatory, economic, competitive, and technological changes, and other risks and uncertainties described in the “Risk Factors,” “Management’s Discussion and Analysis,” and other sections of our filings with the Securities and Exchange Commission, including our most recent Annual Report on Form 10-K and Quarterly Reports on Form 10-Q. The foregoing review of important factors should not be construed as exhaustive and should be read in conjunction with the other cautionary statements that are included elsewhere. Additional information concerning risks, uncertainties and assumptions can be found in RadNet’s filings with the Securities and Exchange Commission (the “SEC”), including the risk factors discussed in RadNet’s most recent Annual Report on Form 10-K, as updated by its Quarterly Reports on Form 10-Q and future filings with the SEC.
Forward-looking statements included herein are made only as of the date hereof and, except as required by applicable law, RadNet does not undertake any obligation to update any forward-looking statements, or any other information in this communication, as a result of new information, future developments or otherwise, or to correct any inaccuracies or omissions in them which become apparent. All forward-looking statements in this communication are qualified in their entirety by this cautionary statement.
DeepHealth Media Contact
Andra Axente
Director of Communications
+31614440971
andra.axente@deephealth.com
RadNet Media Contact
Jane Mazur
Senior Vice President, Corporate Communications
+1 585-355-5978
jane.mazur@radnet.com
References:
- Haslam et al. Radiology Adoption of AI-Generated Thyroid Ultrasound Reports Demonstrates Concordance and Clinical-Grade Performance at Scale. RSNA Chicago. 2026.
- Melnick et al. Generalizable Prostate MRI AI Improves Cancer Detection Across Diverse Populations, Acquisitions, and Reader Experience: A Multi-Reader Study. RSNA Chicago. 2026.
- Louis et al. AI Flags the Cancer-Affected Breast on Prior Tomosynthesis Screens Years Before Diagnosis in a Diverse US Population. RSNA Chicago. 2026.
- Louis et al. Detection of Aggressive vs. Non-Aggressive Cancers in Dense Breasts in the Assure Study with 579,583 Exams and 2,762 Cancers. RSNA Chicago. 2026.
- Kim et al. Image-Only Deep Learning Risk Model Using Digital Breast Tomosynthesis Supports Equitable, Personalized Prediction of Invasive Breast Cancer Risk. RSNA Chicago. 2026.
- Ng et al. Closing the BAC Reporting Gap: Standalone AI Delivers Consistent Detection and Localization across Mammography Modalities, Breast Densities, and Patient Age. RSNA Chicago. 2026.
- Nandurkar et al. Breast Arterial Calcification as a Predictor for Future Cardiovascular Events and Mortality: A Systematic Review and Meta-analysis. Journal of Breast Imaging. 2026.
- Kim et al. Incorporating Priors Reduces False Positive AI Detections in Screening DBT Mammography. RSNA Chicago. 2026.
- Data on file.
- McCabe et al. Closing the Performance Gap between Generalists and Breast Imaging Specialists Using a Nationally Deployed AI Workflow for Screening Mammography. Radiology. July 21, 2026.
- Guenzel, K., Poirot, M.G., van Loon, A. et al. Multicentre evaluation of artificial intelligence risk classification for detection of clinically significant prostate cancer on biparametric MRI. European Radiology. September 26, 2026.
- Not available in the U.S.
- Paramasamy et al. Impact of Commercial Artificial Intelligence on Radiologist Reading Time for Pulmonary Nodule Evaluation at Chest CT. Radiology. September 2026.

Media gallery

