--- title: A French startup built a radiology viewer from scratch... description: Paris-based Raidium has launched its AI-native radiology platform, Raidium Read, at Moffitt Cancer Center in the US. Built from scratch with AI at its core... canonical: https://daily.dev/posts/a-french-startup-built-a-radiology-viewer-from-scratch-with-ai-at-its-core-moffitt-cancer-center-is-t9l2wj8dj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: A French startup built a radiology viewer from scratch with AI at its core. Moffitt Cancer Center is already using it. | daily.dev og:description: Paris-based Raidium has launched its AI-native radiology platform, Raidium Read, at Moffitt Cancer Center in the US. Built from scratch with AI at its core... og:url: https://daily.dev/posts/a-french-startup-built-a-radiology-viewer-from-scratch-with-ai-at-its-core-moffitt-cancer-center-is-t9l2wj8dj og:image: https://api.daily.dev/og/posts/T9l2Wj8dj.png og:image:alt: A French startup built a radiology viewer from scratch with AI at its core. Moffitt Cancer Center is already using it. og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # A French startup built a radiology viewer from scratch with AI at its core. Moffitt Cancer Center is already using it. **[The Next Web](https://daily.dev/sources/tnw)** · 2 min read · 0 upvotes · 0 comments ## Summary Paris-based Raidium has launched its AI-native radiology platform, Raidium Read, at Moffitt Cancer Center in the US. Built from scratch with AI at its core rather than bolted onto a legacy PACS viewer, the platform uses Curia — a proprietary foundation model trained on over 200 million CT and MRI slices — to automate RECIST tumor measurements across multiple time points. The system reduces inter-reader variability by a factor of three and requires no backend integration, enabling faster deployment. FDA 510(k) clearance is expected by end of 2026, with current use limited to clinical trials and research. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Raidium's Curia model and what does it do in radiology? Curia is Raidium's proprietary foundation model trained on over 200 million CT and MRI slices from 150,000 exams. It performs organ-agnostic, automated RECIST measurements to track tumor response across multiple imaging time points, and Raidium says it cuts inter-reader variability by a factor of three compared to manual lesion tracking. _Track how AI foundation models are reshaping clinical imaging workflows through daily.dev._ ### Has Raidium's radiology platform received FDA clearance? Not yet as of the launch at Moffitt Cancer Center. Raidium Read is currently available only for clinical trials and research use there, and FDA 510(k) clearance is expected before the end of 2026, after which broader clinical deployment could follow. _Developers evaluating medical AI regulatory timelines can follow updates like this on daily.dev._ ### Why did Raidium build its own PACS viewer instead of adding AI to an existing one? Raidium's CEO Paul Herent argued standard PACS viewers have resisted evolution for twenty years, so the company built the viewer from scratch with the Curia model embedded rather than layering AI onto legacy software. This approach requires no backend integration, making deployment faster than traditional PACS installations at sites like Moffitt Cancer Center. _Engineers weighing build-versus-bolt-on AI integration strategies can find similar cases on daily.dev._ ## Similar posts on daily.dev - [Oxford spinout RADiCAIT uses AI to make diagnostic imaging more affordable and accessible — catch it at TechCrunch Disrupt 2025](https://daily.dev/posts/oxford-spinout-radicait-uses-ai-to-make-diagnostic-imaging-more-affordable-and-accessible-catch-it-az0z8adzs) · TechCrunch · 0 upvotes · 0 comments - [From Scan to Treatment Plan, AI Helps Close Breast Cancer’s Deadliest Gaps](https://daily.dev/posts/from-scan-to-treatment-plan-ai-helps-close-breast-cancer-s-deadliest-gaps-m9dlftop9) · NVIDIA · 0 upvotes · 0 comments - [Vara wins world’s first CE mark for AI that clears mammograms alone](https://daily.dev/posts/vara-wins-world-s-first-ce-mark-for-ai-that-clears-mammograms-alone-mq0rja18w) · The Next Web · 0 upvotes · 0 comments - [Advancing Explainable AI in Radiology Research with NVIDIA Clara Reason](https://daily.dev/posts/advancing-explainable-ai-in-radiology-research-with-nvidia-clara-reason-y0svrm8rd) · NVIDIA Developer · 0 upvotes · 0 comments - [New AI technique could make minimally invasive surgeries safer and more precise](https://daily.dev/posts/new-ai-technique-could-make-minimally-invasive-surgeries-safer-and-more-precise-btvc8amx4) · MIT News · 0 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#healthcare](https://daily.dev/tags/healthcare) [View this post on daily.dev](https://daily.dev/posts/a-french-startup-built-a-radiology-viewer-from-scratch-with-ai-at-its-core-moffitt-cancer-center-is-t9l2wj8dj) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"A French startup built a radiology viewer from scratch with AI at its core. Moffitt Cancer Center is already using it.","url":"https://daily.dev/posts/a-french-startup-built-a-radiology-viewer-from-scratch-with-ai-at-its-core-moffitt-cancer-center-is-t9l2wj8dj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/a-french-startup-built-a-radiology-viewer-from-scratch-with-ai-at-its-core-moffitt-cancer-center-is-t9l2wj8dj"},"datePublished":"2026-07-18T10:28:46.423Z","dateModified":"2026-09-13T18:27:25.611Z","description":"Paris-based Raidium has launched its AI-native radiology platform, Raidium Read, at Moffitt Cancer Center in the US. Built from scratch with AI at its core...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bf5f38eceec8752aac2fe7e1810f0ba3?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bf5f38eceec8752aac2fe7e1810f0ba3?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The Next Web","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The Next Web","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tnw","url":"https://daily.dev/sources/tnw"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/a-french-startup-built-a-radiology-viewer-from-scratch-with-ai-at-its-core-moffitt-cancer-center-is-t9l2wj8dj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,healthcare","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The Next Web","item":"https://daily.dev/sources/tnw"},{"@type":"ListItem","position":3,"name":"A French startup built a radiology viewer from scratch with AI at its core. Moffitt Cancer Center is already using it."}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/a-french-startup-built-a-radiology-viewer-from-scratch-with-ai-at-its-core-moffitt-cancer-center-is-t9l2wj8dj#faq","mainEntity":[{"@type":"Question","name":"What is Raidium's Curia model and what does it do in radiology?","acceptedAnswer":{"@type":"Answer","text":"Curia is Raidium's proprietary foundation model trained on over 200 million CT and MRI slices from 150,000 exams. It performs organ-agnostic, automated RECIST measurements to track tumor response across multiple imaging time points, and Raidium says it cuts inter-reader variability by a factor of three compared to manual lesion tracking. Track how AI foundation models are reshaping clinical imaging workflows through daily.dev."}},{"@type":"Question","name":"Has Raidium's radiology platform received FDA clearance?","acceptedAnswer":{"@type":"Answer","text":"Not yet as of the launch at Moffitt Cancer Center. Raidium Read is currently available only for clinical trials and research use there, and FDA 510(k) clearance is expected before the end of 2026, after which broader clinical deployment could follow. Developers evaluating medical AI regulatory timelines can follow updates like this on daily.dev."}},{"@type":"Question","name":"Why did Raidium build its own PACS viewer instead of adding AI to an existing one?","acceptedAnswer":{"@type":"Answer","text":"Raidium's CEO Paul Herent argued standard PACS viewers have resisted evolution for twenty years, so the company built the viewer from scratch with the Curia model embedded rather than layering AI onto legacy software. This approach requires no backend integration, making deployment faster than traditional PACS installations at sites like Moffitt Cancer Center. Engineers weighing build-versus-bolt-on AI integration strategies can find similar cases on daily.dev."}}]} ```