FOR IMMEDIATE RELEASE
The company replaced the architecture behind its screening system, staging the rollout so classifiers in production were replaced as they cleared new internal quality benchmarks.
September 16, 2026 – SAN DIEGO, CA – Vetology, which provides AI radiology screening and on-demand teleradiology consultations to veterinary practices, has rebuilt and re-released all 94 classifiers on a new model architecture, completing the work between June and the end of August. Going forward, new classifiers will be added to the platform on a regular monthly cadence.
The live classifier library was updated in stages rather than in a single switchover. Clinics received each improvement as it cleared internal benchmarks for deployment into production. The net effect was an uninterrupted workflow, with no installations or updates to manage.
Vetology’s position is that our AI image screening tool earns its place in a practice tech stack by being reliable. That kind of dependability requires a commitment to keeping the platform current as the underlying technology advances, which is why the team set the rebuild in motion on its own initiative.
We used this opportunity to make a radical shift in our model architecture. Our latest models are a significant improvement in that they can interpret global information in a case, both within any single image as well as between linked images in a study. This closely matches how a human radiologist reads cases and the success of these models follows directly from that design. They’ve also opened a wealth of new features that we will continue to build and improve. It was demanding work, and the team was exceptional throughout. Diplomates of the American College of Veterinary Radiology, Drs. John Mattoon and Jennifer Gambino offered contextual guidance and direction as we worked toward better outcomes for each classifier.
Anthony Lutz, Manager of Data Science, Vetology
The published performance data describes the classifiers currently in service. Every figure on that page belongs to a model running on live cases today. Performance metrics have been public since January 2026, and with the rebuild complete they now reflect the latest data for every classifier currently in service. The company’s open invitation to independent researchers to test them, stands.
In March 2025, the American College of Veterinary Radiology and the European College of Veterinary Diagnostic Imaging published a joint position statement on artificial intelligence in the Journal of the American Veterinary Medical Association. It named transparency, error reporting, postimplementation monitoring, and unbiased third-party evaluation as conditions for veterinary AI worth trusting. A pilot study in the same journal a year later externally validated six commercial veterinary radiology AI services against general practice canine abdominal radiographs and reported low to moderate performance across the platforms tested.
We read both of those papers and deliberately addressed all 94 classifiers. Our data science team set a higher bar for this rebuild than the original classifiers were held to. We believe in being fully transparent about how we develop our AI. That means actively following the published recommendations of accredited institutions and professional bodies, and it means building continuous feedback loops directly into our platform so we can hear from the DVMs using the product every day. When our community raises a concern, we act on it. Our team of board-certified radiologists validates those improvements before they reach our users. We’re building a platform veterinarians can rely on and trust, because patient safety is on the line; and that trust is earned through accountability, continuous improvement, and an unwavering commitment to the standards our profession sets.
Eric Goldman, President, Vetology
Vetology’s AI screening reports are built to be interpreted by a veterinarian in support of their own diagnosis and treatment plan. When a case calls for a more nuanced understanding of complex patient dynamics, it can be routed to the company’s board-certified radiologists for a full teleradiology report.
“The question I get most from practices is whether the AI report takes the decision away from the veterinarian. It doesn’t. The report is one more input, it’s like asking a colleague to take a look. The diagnosis, the plan, and the conversation with the owner all still rely heavily on the veterinarian’s skill and expertise.
Pierre D’Amours, Vice President of Sales, Vetology
# # #
ABOUT VETOLOGY
Vetology is a veterinary diagnostic imaging support company that provides AI-generated screening reports and traditional teleradiology services by board-certified veterinary radiologists. Built by radiologists, Vetology focuses on improving patient outcomes through accuracy, speed, and reliability in diagnostic imaging. Our platform is designed to integrate seamlessly into existing hospital workflows, helping clinicians make informed decisions quickly. Learn more at vetology.net.