Raidium Introduces Promptable AI Model for Medical Imaging

French medtech firm Raidium has launched ONCOPILOT, an artificial intelligence (AI)-based promptable foundation model capable of measuring solid tumors in 3D and in real time with expert-level accuracy.

In seconds, ONCOPILOT provides clinicians with the volumetric biomarkers needed to accelerate the development of new treatments and enhance clinical decision-making. Natively integrated into the PACS viewer, this AI assistant transforms image analysis into a fast, interactive, and reproducible process—a key component in establishing faster and more consistent oncology care.

Designed for Expert Use, Embedded in Clinical Workflows

While most medical AI tools operate as peripheral modules, ONCOPILOT was designed as a natively integrated copilot within Raidium’s proprietary PACS viewer. No export, no context switching: the AI operates directly within the familiar reading interface, maintaining seamless workflow continuity. With a simple click or manual selection, users can prompt ONCOPILOT to generate an editable 3D mask of the target lesion—ready for direct use.

Each manual correction contributes to the AI’s ongoing learning, continuously improving segmentation quality based on real-world usage. This in situ learning capability represents a significant advantage over static, pre-trained models, according to Raidium. Future versions will automatically localize target lesions, calculate complex biomarkers (e.g., total tumor burden, growth kinetics), and draft structured reports with final validation resting with radiologists.

“With ONCOPILOT, we are delivering on a bold vision: an AI copilot for radiologists, capable of handling complex measurements like tumor volumetry while reinforcing the expert’s central role in clinical decisions. As a radiologist, I know how valuable—yet time-consuming—these analyses are. ONCOPILOT was designed to give clinicians their time back, increase data reliability, and bring precision medicine into routine oncology workflows,” Raidium Co-Founder/CEO and radiologist Dr. Paul Hérent said.

A True Imaging Copilot

ONCOPILOT’s collaborative approach keeps the radiologist at its center, ensuring clinical control, full traceability of edits, and continuous learning from human interaction. ONCOPILOT embodies an augmented radiology paradigm, where AI does not replace the physician but takes over repetitive tasks while providing advanced analytics—fluidly, without friction or cognitive overload.

“With ONCOPILOT, we demonstrate that a generalist, interactive AI can empower experts by instantly providing complex volumetric metrics. It is a true copilot for oncologic imaging,” stated Dr. Léo Machado, AI research radiologist at Raidium and first study author.

Traditional tumor measurements following RECIST 1.1 are labor-intensive, poorly reproducible, and typically restricted to two dimensions. By transforming a simple click into an editable mask, ONCOPILOT simplifies radiologist workflows and opens the door to volumetric biomarkers essential for personalized medicine.

• Clinical value for patients: With more precise 3D analysis, ONCOPILOT enables earlier and more personalized therapeutic decisions, such as adjusting chemotherapy regimens or dosing strategies based on actual tumor volume rather than mere diameters. Over time, patients will benefit from novel imaging biomarkers that make precision medicine viable for routine follow-up.
• Value for clinical research: Next-generation therapies—including immunotherapies, antibody-drug conjugates (ADCs), and targeted radioligands—often induce complex, nonlinear responses. ONCOPILOT is designed to extract advanced biomarkers such as total tumor burden, ultra-early response signatures, and comprehensive whole-body longitudinal follow-up. These metrics support faster go/no-go decisions, improve adaptive trial design, and help identify surrogate endpoints that can shorten time-to-market. 

Beyond clinical use, ONCOPILOT serves as a biomarker factory for cloud-based clinical trials, enabling companies to standardize, accelerate, and de-risk imaging analysis at scale. With ONCOPILOT, Raidium sets a new standard for precision oncologic imaging. Regulatory processes are underway, and the company is actively working to accelerate clinical deployment while exploring partnerships to expand into other imaging modalities such as PET-CT and MRI.

Key features of ONCOPILOT:

• Real-time 3D, multi-organ measurements
• Radiologist-level precision—mean DICE score of 0.79 after editing
• Speed: 17.2 seconds per measurement—17% faster than manual 2D reading
• Reduced inter-reader variability—standard deviation improved from 2.4 mm to 1.7 mm
• Seven organs covered as opposed to one or two for most AI solutions

Founded in 2022 by Dr. Hérent and Pierre Manceron (now chief scientific officer), Raidium is developing the first 3D foundation model for precision radiology—a large multimodal model. It is delivered to radiologists through a product AI-native PACS viewer, enabling direct interaction with the model, like a radiology copilot. Initial applications focus on enhancing biomarkers in clinical trials, particularly in oncology and liver diseases, before expanding to the broader radiology workflow. Raidium is supported by a team of 15 engineers and researchers from top educational backgrounds and previous experiences at Owkin, Meta, Cardiologs, Datadog, and more. The company is based in Paris, and is part of the Paris Biotech Santé Incubator (Cochin) and Station F 21st program.

* Peer-reviewed study published on April 25, 2025, in npj Precision Oncology.