Virgo Surgical Video Solutions, Inc., a leader in endoscopic AI technologies, announced the official launch of EndoML at Digestive Disease Week (DDW) 2025. EndoML is an innovative artificial intelligence development platform specifically designed to empower gastroenterologists and pharmaceutical researchers, significantly accelerating the journey from AI concept to clinical application.
EndoML leverages Virgo’s powerful AI foundation model, EndoDINO, which was trained on an extensive dataset comprising over 130,000 full-length gastrointestinal (GI) endoscopy videos. The EndoDINO model has previously demonstrated state-of-the-art performance across diverse GI endoscopy applications, including anatomical landmark recognition, polyp segmentation, and inflammatory bowel disease (IBD) severity scoring.
“The EndoML platform puts the power of artificial intelligence directly into the hands of clinicians and researchers, allowing them to harness the full power of AI in gastroenterology,” said Matt Schwartz, CEO of Virgo. “Our goal is to streamline and democratize AI development in the field, facilitating quicker transitions from research innovations to tangible patient care improvements. I’ll be doing live demos of EndoML at DDW 2025.”
EndoML enables researchers to seamlessly train custom AI models using their proprietary datasets.
Also Read: Dataminr Raises $100M from Fortress with Ongoing Backing from NightDragon to Accelerate Generative AI and Agentic AI Solutions for Enterprise and Government Markets
Powered by EndoDINO as a backbone model, researchers can expect to achieve superior model performance, while requiring less labeled data. Developed models become readily accessible for ongoing research, collaboration, and further advancements within the scientific community. Notably, Virgo has previously demonstrated EndoML’s remarkable accuracy and effectiveness for Mayo Endoscopic Scoring at both frame-level and video-level analyses.
Chris Lawcock, Virgo‘s VP of Engineering, emphasized the platform’s versatility: “EndoML not only simplifies AI model development but also provides pharmaceutical sponsors flexibility to train and deploy these models on their own terms. EndoML models seamlessly integrate within VirgoTrials, our data capture and management solution for clinical trials. At the same time, sponsors can also leverage EndoML models in their own data analysis environments. It’s a comprehensive toolset designed to meet the unique needs of clinical and pharmaceutical research.”
Source: PRNewswire
