RadNet’s DeepHealth Artificial Intelligence Subsidiary Demonstrates Earlier Breast Cancer Detection in New Study
RadNet, Inc. (NASDAQ: RDNT) announced that its subsidiary DeepHealth has published results in Nature Medicine demonstrating AI algorithms that can detect breast cancer up to two years earlier than current methods, outperforming expert radiologists. This advancement may enhance early cancer detection and generalizability across various clinical scenarios. The AI technology's initial product, aimed at mammogram prioritization, was submitted for FDA approval in late 2020, with expectations for approval in 2021. DeepHealth's innovations aim to improve mammography and broader medical imaging applications.
- AI algorithms detect breast cancer one to two years earlier than standard methods.
- Outperformed five expert radiologists in screening mammograms.
- Strong generalization across different clinical sites and populations.
- The initial AI product for prioritization of mammograms was submitted for FDA approval.
- Challenges remain in developing expert-level AI due to scarcity of annotated data.
- Validation of AI performance requires diverse clinical testing, complicating rollout.
CAMBRIDGE, Mass. and LOS ANGELES, Jan. 11, 2021 (GLOBE NEWSWIRE) -- RadNet, Inc. (NASDAQ: RDNT) today reported that its DeepHealth subsidiary, a leading developer of artificial intelligence (AI) for mammography interpretation, published results of its novel AI algorithms in Nature Medicine, illustrating an ability to detect breast cancer a year or more earlier than current practice.
DeepHealth compared its AI to five full-time, breast-fellowship-trained expert radiologists reading the same screening mammograms. The software exhibited higher performance than all five radiologists, and the results suggest that the AI could help detect cancer one to two years earlier than standard interpretation in many cases. Additionally, the software showed promising generalization capabilities, demonstrating strong performance when tested across clinical sites and populations that were not directly involved in training the AI algorithms.
While AI holds tremendous promise for improving screening mammography interpretation, there remain substantial challenges in developing expert-level AI. “Reaching world-class performance requires a new way of building AI,” said Gregory Sorensen, M.D., CEO, and co-founder of DeepHealth. “The brute-force methods that have worked so well in other domains, such as self-driving cars or game playing, where data is plentiful, have not translated effectively to many parts of medicine, where human data is often scarce. For example, to train the technology for better detection, AI algorithms must be developed from annotated data where the cancer status is known. Such data can be difficult to obtain. Then, to validate performance, the AI should be tested across different clinical sites and patient populations in different scenarios.”
The new study by DeepHealth demonstrates progress in resolving these challenges. “We have developed an approach that mimics how humans often learn by progressively training the AI models on more difficult tasks. By leveraging prior information learned in each successive training stage, this strategy results in AI that detects cancer accurately while also relying less on highly-annotated data,” said lead author Bill Lotter, Ph.D., CTO, and co-founder of DeepHealth. “Our approach and validation extend to 3D mammography, which is particularly important given its growing use and the significant challenges it presents for AI.”
“Our results point to the clinical utility of AI for mammography in facilitating earlier breast cancer detection,” Lotter noted, “as well as an ability to develop AI with similar benefits for other medical imaging applications. By building AI software with high performance and generalizability, DeepHealth has the potential to help radiologists enable more widespread access to high quality care.”
DeepHealth’s first AI-based product, a software package for prioritization of 2D and 3D mammograms, is based on the same core technology described in the Nature Medicine publication. This product was submitted to the FDA in late 2020, with approval anticipated in 2021.
Link to Nature Medicine paper: https://www.nature.com/articles/s41591-020-01174-9
About RadNet, Inc.
RadNet, Inc. is the 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 334 owned and/or operated outpatient imaging centers. RadNet’s core markets include California, Maryland, Delaware, New Jersey, Arizona, and New York. In addition, RadNet provides radiology information technology solutions and other related products and services to customers in the diagnostic imaging industry. Together with affiliated radiologists, and inclusive of full-time and per diem employees and technicians, RadNet has approximately 8,600 employees.
For more information, visit www.radnet.com.
About DeepHealth, Inc.
DeepHealth, a wholly owned subsidiary of RadNet, Inc., uses machine learning to distill lifetimes of insights from medical experts into software to assist physicians. DeepHealth’s mission is to enable the best care by providing products that clinicians and patients can trust, through rigorous science and clinical integration. For more information, visit www.deep.health.
CONTACTS:
DeepHealth, Inc.
Bret Baird
Chief Commercial Officer
424-832-1480
bbaird@deep.health
RadNet, Inc.
Mark Stolper
Executive Vice President and Chief Financial Officer
310-445-2800
A photo accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/ab4a5a9c-3905-4def-84aa-a15d60c43640
FAQ
What are the main findings of RadNet's DeepHealth AI study published in Nature Medicine?
When was RadNet's DeepHealth AI product submitted for FDA approval?
What does the DeepHealth study suggest for breast cancer detection?
