DIGITX’s cover photo
DIGITX

DIGITX

Higher Education

Building the Backbone of Intelligent Radiology.

About us

Industry
Higher Education
Company size
2-10 employees
Type
Nonprofit

Updates

  • We’re sharing the first two tools we’ve begun building at the DIGIT-X Lab. Both are open-source, fully on-premise, and still early — but they represent the direction we’re quietly working toward. MOSAICX: A healthcare text-structuring engine that takes unstructured clinical text: reports, notes, PDFs, and turns it into structured, machine-readable data. It’s a first step toward the digital foundations needed for reliable, AI-driven medicine. AnnotateX: A companion tool for creating high-quality textual annotations (“gold standards”), with optional AI assistance. These annotations help evaluate and refine tools like MOSAICX and support the creation of robust clinical datasets. Both tools run entirely on your own infrastructure — your data stays with you. And both will grow through collaboration, feedback, and careful iteration. DIGITX | LMU Radiology Quietly ambitious about hard things.

    [Phase 01] Our attempt in Structuring unstructured medical data - to enable the conversion of real world data to real world evidence. We are officially open-sourcing MosaicX, the first tool we’re building at the DIGITX lab. MosaicX is an early-stage medical text-structuring engine designed to transform unstructured clinical text into structured, machine-readable data. Alongside it, we’re releasing AnnotateX, our second tool for creating high-quality structured text annotations. We built it so that we can validate MosaicX. Together, these tools form the starting point of our effort to build the digital foundations needed for AI-driven precision medicine. Coming from a background in molecular hybrid imaging and image analysis (with my work in ENHANCE.PET) and moving into LLMs and clinical text feels like starting my PhD all over again. But one thing is clear: to make AI-driven precision medicine a reality, we must ensure clinical data is truly computable, including the “dark matter” of healthcare such as PDFs and free-text reports. Both MosaicX and AnnotateX are still in their infancy - a lot of work to be done, but we’re releasing them openly to learn, iterate, and grow together with the community. We are currently looking for clinical text datasets across radiology and other specialties (non imaging) to guide the next stages of development and validation. Cool thing is both of them run on-premise and can use Ollama backend. Your data stays with you. If you’re working on structured clinical data or interested in collaborating for a large scale validation, feel free to reach out. DIGITX Repository with DOIs for both the tools: https://lnkd.in/dRJpSMiV Shout out to Canva AI for the cool audio generation. DIGITX | LMU Radiology

  • View organization page for DIGITX

    138 followers

    Say hi to Sahib J.. We had 127 applicants. We chose one. Not just because he’s a strong computer scientist — though he is. But because he pays attention: to the problem, the conversation, the moment. That kind of awareness is rare. He’s joining Digit-X as our first postdoc — to help us build something we care deeply about: making clinical knowledge computable. With his expertise on large language models, computer vision and knowledge graphs, he’s stepping into the messy, high-stakes world of healthcare. That’s his new home. Welcome, Sahib. Let’s get to work. —— DIGITX | LMU Radiology Quietly ambitious about the hard things

    • No alternative text description for this image
  • 🧩 Structure First. Insight Follows. At DIGIT-X, we believe in a core principle: structure the data first — insight will follow. This week, we took a step in that direction: In collaboration with Visage Imaging and the ENHANCE.PET project, our segmentation tools — MOOSE (organs) and LION (lesions) — are now integrated directly into the Visage viewer as research tools. This integration was only possible because of Visage. Their team moved fast, understood the value, and enabled the kind of interoperability in a couple of days! These tools are not for diagnosis. But they do something important: They extract structured imaging biomarkers — volume, SUV, intensity, geometry — inside PACS, and map them to FHIR Observations. Why does that matter? Because structure at the source means less manual work later. Because once these values are in FHIR, they’re not just in a viewer — they’re in dashboards, in trials, in reasoning systems. Because radiology becomes more usable when it’s connected to the rest of care. Thanks to the Visage team for enabling this kind of integration — it sets a precedent for what’s possible. — DIGIT-X Lab Quietly ambitious about the hard things. #DIGITX #VisageImaging #enhancePET #MOOSE #LION #Segmentation #FHIR #StructuredData #DigitalTransformation #Radiology #ResearchTools

  • View organization page for DIGITX

    138 followers

    We’re hiring. DIGIT-X Lab is new, small, and still taking shape — but we’re clear on the kind of work we want to do. We’re not here to churn out papers or stack grant deadlines for their own sake. We’re building tools, structure, and ideas that actually hold up — and ideally, get used. If the work is meaningful, the rest tends to follow. This will be our first full-time hire — postdoc or research engineer. Someone who wants to help build something useful from the ground up, not just plug into an existing pipeline. If that resonates, please find the job description attached and do apply. Feel free to share or reach out if you’re curious. — DIGIT-X Lab Quietly ambitious about the hard things. #Hiring #Postdoc #ResearchEngineer #MedicalAI #MedicalImaging #RadiologyInformatics #LMUMunich #DIGITX

  • Hello from DIGIT-X. We’re live. Today marks the quiet but intentional start of DIGIT-X Lab, based in the Department of Radiology at LMU Klinikum. We’re not launching with a big reveal or a perfect roadmap. Just a clear purpose: To rethink how medical data is structured, connected, and turned into knowledge that actually helps in clinical care. That means building more than just tools. We care about infrastructure — how data moves, how imaging connects with other clinical silos, how systems talk to each other, and how AI can be a catalyst that stays transparent and speaks for itself — in natural language. We believe radiology has more to offer when it’s better connected to the rest of healthcare. That’s what DIGIT-X is here for: - To work at the intersection of healthcare data, AI, and informatics - To rethink structure — technically, semantically, and systemically - To build things that are useful, reproducible, and explainable - To stay grounded in clinical reality, even when the tech gets abstract It’s early days. We’re a new lab, still forming. But we’re quietly ambitious about the hard things — and we’re hiring our first member (Research Engineer/PostDoc) soon. Follow us if you’d like to see what comes next. — DIGIT-X Lab Digital Transformation in Radiology Department of Radiology LMU Klinikum, Munich

Similar pages