Raidium Read is designed to help cancer centers streamline complex imaging review.
PARIS and SAN FRANCISCO, July 16, 2026 /PRNewswire/ — Raidium, the AI-native radiology company combining a world-class foundation model research lab with a unified clinical viewer, today announced the U.S. launch of Raidium Read (R.Read), applying its AI-native imaging solution initially to oncology research centers. Raidium has already been deployed at Moffitt Cancer Center, one of the nation’s leading cancer research centers, where it was selected to replace the legacy radiomics tool. The Raidium platform offers whole-body lesion detection, AI segmentation models, and longitudinal transfer of lesions across follow-up and prior studies, supporting complex oncology imaging workflows in clinical research settings, as a first demonstration of agentic AI applied to radiology.
The timing reflects an urgent need at the center of cancer care. Recent research shows that early, precise lesion detection can spare the majority of patients from surgery. Simultaneously, the WHO is advancing new guidelines around early screening and detection of precancerous lesions. Across oncology, clinicians and executives are looking for tools that can help identify lesions earlier, track them more precisely, and act faster.
Radiology sits at the center of that imperative, with AI rapidly reshaping its role. Industry estimates consistently show that more than 70% of all FDA-approved AI-enabled medical devices are in the radiology category. Yet adoption at the workflow level remains fragmented. Most AI tools arrive as narrow point solutions that add clicks, context-switching, and cognitive load to an already strained reading room. A 2025 Philips Future Health Index survey found that 41% of radiologists feel current AI tools do not adequately address their real-world needs.
Raidium was built from a different premise. Rather than adding AI on top of 20-year-old existing interfaces, Raidium built an AI-native viewer from the ground up, designed to fit real-world radiologist workflows. The result is a single, integrated tool that reduces friction, improves usability, and brings complex oncology review into one clinical environment. R. Read, launching in the U.S. for oncology today, is the first full expression of that architecture, available now as a standalone pipeline for clinical trial use before its use in clinical practice (pending regulatory clearances).
“For twenty years, the standard PACS viewers have resisted evolution, easily outmatched by the rigid limitations of early AI. Today, however, agentic AI is driving a quiet revolution: a single, fluid convergence of everyday accessibility, conversational logic, and advanced reasoning that is finally poised to redefine the reading room,” said Paul Herent, MD, CEO and Co-Founder of Raidium. “We are initially targeting oncology follow-up because no convincing AI solution has yet solved this complex workflow. It is a game-changer for cancer centers, where a significant amount of a radiologist’s time is dedicated to this tedious and repetitive task.”
For now, R. Read is designed for the realities of oncology imaging, where speed, consistency, and clarity matter:
- Less manual effort across search, review, and follow-up.
- Decrease inter-reader variability by 3x (Organ-agnostic automated RECIST measurements across time points with foundation models).
- Easier longitudinal tracking for trials and oncology care.
- Less documentation burden while preserving radiologist oversight.
- Streamlined radiologist-clinician communication (e.g., tumor boards) for better medical decision-making.
“Raidium’s unified approach empowers us to explore research projects that would have seemed impossible not too long ago,” said Cesar Lam, MD, a radiologist at Moffitt Cancer Center’s Diagnostic Imaging and Interventional Radiology Department. “It is transforming and empowering how we conduct oncology clinical research projects, giving our teams a tool designed for the complexity of real-world imaging data.”
R. Read is available now for clinical trial and oncology research use, with final regulatory clearance for clinical practice and care routines forthcoming. Raidium is pursuing 510(k) clearance for a subset of features and expects to announce clearance before year-end 2026. Cancer centers can get started immediately without integration prerequisites, reducing implementation friction and making the workflow easier to adopt in existing environments. Raidium is accepting registrations from qualified oncology centers on an invitation basis at raidium.eu/viewer.
About Raidium
Raidium is an AI-native radiology company building the tools that radiologists have been waiting for. Combining a world-class foundation model research lab with a unified, promptable AI viewer, Raidium automates complex radiology workflows from indication to final report while keeping the radiologist in control at every step. The Raidium Read Onco (R.Read Onco) platform automates RECIST imaging endpoints for use in clinical practice and clinical trials. The Curia foundation model demonstrates state-of-the-art performance across imaging tasks, with peer-reviewed publication forthcoming in Radiology AI. Raidium operates globally with offices in Paris, France and Silicon Valley, USA.
Media Contact:
The Media Joy JoJo Abbasi
+18478090406
418914@email4pr.com
View original content to download multimedia:https://www.prnewswire.com/news-releases/raidium-brings-ai-powered-oncology-imaging-workflow-to-us-cancer-centers-302826946.html
SOURCE Raidium
