RadOverlay
AI-driven radiology report generation
For Radiologists, By Radiologists.

RadOverlay™ is on a mission to streamline reporting for radiologists through cutting-edge AI automation. Our software handles the drudgery when drafting structured reports, taking the transcription process from minutes to seconds. By eliminating tedious data entry, we help radiologists focus on interpreting images, not copying.

This leads to faster turnaround times, reduced burnout, and improved reporting quality across practices. Wherever you read, RadOverlay integrates seamlessly into your workflow. We're building the future of radiology—starting today.

Products
RadOverlay Desktop screenshot
RadOverlay Desktop

Transform handwritten worksheets into fully structured reports with the power of AI and convenience of workstation integration.

TI-RADS Report Builder webapp screenshot
TI-RADS Report Builder

A free-to-use webapp to quickly prepare ACR TI-RADS reports on nodules from thyroid ultrasound.

Meet Our Team
Bradford Bennett, MD
Co-Founder & CEO
Brad is a board-certified radiologist and the founder of Falcon Radiology, PLLC, an independent teleradiology practice. He completed his radiology residency at The Johns Hopkins Hospital and a neuroradiology fellowship at the Hospital of the University of Pennsylvania. After a year in private practice, he launched his own solo teleradiology company to gain greater flexibility, spend more time with his young family, and explore radiology-focused entrepreneurship. Dr. Bennett is passionate about improving radiologist workflow, promoting physician autonomy, and building sustainable, high-quality radiology practice models. He co-founded RadOverlay to address workflow inefficiencies common among teleradiologists.
Daniel Himmelstein, PhD
Co-Founder & CTO
Daniel has authored several software and data tools to streamline biomedical research, including Manubot for collaborative manuscript authoring on GitHub and Hetionet, a popular knowledge graph for drug repurposing. Prior to founding RadOverlay, Daniel was the Chief Data Scientist at Related Sciences where he co-led the data team to develop AI/ML approaches for systematic drug target prioritization. Daniel received his PhD in Biological & Medical Informatics from the University of California, San Francisco. As an undergraduate at Cornell University, he majored in Biometry & Statistics.