# RadMesh The AI prepares the report. You decide and sign. It reads the image, organizes your shift, prepares the draft and reviews it before you sign. With the PACS you already have and the studies kept in Colombia. A support tool for professionals. Not a medical device. Clinical AI features run in research mode. ## An agentic RIS. Built on AI from the codebase up. It is not a traditional RIS with an AI button. The worklist, the draft, the review and the notices are agents by design. Each one keeps a log; none of them signs. ## Four agents. One shift. Every task in the shift has an agent. Each one logs what it did. None of them signs, and none lowers a priority set by a human. - Prioritizes: The worklist is ordered by turnaround target and by the technologist's flag, with the reason visible on every row. - Reads the image: The AI marks the area of the image that supports each finding and links it to the sentence in the draft. Hover a sentence and see where it looked. Nothing enters the report without your approval. Research mode. CT today; other modalities in preparation. Each institution chooses which models it uses. - Reviews: It looks for findings left out of the conclusion, the unanswered clinical question, laterality and measurements. It shows you the observation and you decide. - Backup: If a study is about to miss its target, it notifies the radiologist on shift. If it is not read, it notifies the administrator to reassign it and suggests who can read. ## Turnaround under control, with a RIS that is yours. - No PACS change: it connects over DICOM from a VM in your network. - Worklist with the reason in view: by turnaround target and by the priority of the order and the technologist. - Reading targets and backup: it warns before a target is missed and suggests who can read. - Connected shifts: it knows who is on shift from Clicrad. - WhatsApp and Slack notices: only to staff on shift, with no patient data. - Service quality: what gets corrected before signing, for training. - Service templates: personal and shared, without junk templates. ## The studies stay in Colombia. Your studies live on a node dedicated to your institution, on servers in Colombia: we host it or, if your hospital prefers, it runs on its own servers. - The RadMesh central service only handles licenses, updates and signed models. It does not store patient data. - Each node is independent: one institution's data never mixes with another's or passes through the central service. - Access with a personal user and mandatory second factor. - Notices never include patient data. - Your studies are not used to train models without a signed agreement with your institution. - Any research use is approved by your own ethics committee. ## What RadMesh is, and what it is not. - It is not a medical device; the radiologist decides and signs. - Clinical AI runs in research mode. - Internal evaluations with synthetic cases, not clinical validation. ## A connected shift. Your judgment in control. Product overview, not clinical guidance or a security audit. No performance or clinical validation figures are published here. See the website for detailed feature status. ### Why The indication, prior studies, report and follow-ups should not get lost between screens or shift handovers. We are building RadMesh around the radiologist's work. - Less context scattered across tools. - Urgent work with the reason in view. - Human decisions with a traceable history. ### How Your studies live on a node dedicated to your institution, on servers in Colombia: we host it or, if your hospital prefers, it runs on its own servers. The node connects the worklist, viewer and report. Agents support specific tasks; the radiologist reviews and signs. - Priority retains its source and reason. - RAD·QC checks report text consistency before sign-off. - Deployment and configuration determine what runs locally and what may leave with authorization. ### What The website separates available, partial and planned capabilities. The vision guides development; it does not replace a demonstration of what works. - Foundation: DICOM intake, viewer, worklist and report review. - Image models are presented for research use. - Conversational workflows and extensions are verified before being announced as available. ## Published agent status - Nexus: Available. Report quality check before signing and a prioritized worklist. - Echo · Shift notices: Implemented. Notifies on-duty staff when a study is about to run late or needs reassigning. By WhatsApp or Slack, with no patient data. - RadWork: Available. Registration and verified radiologist profiles; the pool suggests who can read when a study is about to run late. Reading happens inside the institution's node. - Lumen: Available. Your service's evidence library: guidelines and protocols with answers cited to the page; if it is not in your library, it does not make things up. Appropriateness criteria (ESR iGuide): coming soon. - ClicRad: Available. Service shifts. - Iris: Research use. Catalog of signed AI models, enabled per institution. Clinical sheets for each model are in preparation. ## Published modality status - Any modality (DICOM): Available. CT, X-ray, MRI and ultrasound arrive, are stored and read in the viewer. - CT, whole body: Research use. Analysis models for lung and whole body, labeled as research. - Conventional radiography (X-ray): In preparation. Image AI for radiography, in preparation. - Report draft: Research use. The AI proposes a draft on your template; you review and sign it. ## Scope and limits RadMesh's main repository is private. This overview is public; it does not mean the product is open source. Confirm features and availability in a demo and in each installation's configuration. AI output does not replace medical judgment. Do not send patient data to external services. Source: https://www.radicalmesh.com/en