Radion gives radiology agents calibrated instruments—and lets radiologists watch every slice they touch.

An open-source DICOM reading room, 42-tool Model Context Protocol harness, and 185-task CT, radiograph, and MR scoreboard. Code computes the millimetres and Hounsfield units; the agent cannot report a measurement it did not take.

STUDY 1.2.826.0.1.3680043…5343public · synthetic phantom
Axial z=64/120 (-16.5 mm) · WL -600 / WW 1500Mid thorax · carina & hilar window
agent FOV · step #4RLAP
RECIST: 12.4 × 9.8 mmROI mean: +34.2 HUVol: 1,001 mm³
z
Physician finding review (keys a c r):
Live MCP Harness Ledger (SSE)5 calls · 93 ms geometry
Linked Structured Report

Pulmonary nodule in the left lower lobe superior segment: 12.4 × 9.8 mm on axial slice z=64 (-16.5 mm), mean attenuation +34.2 HU, volume 1,001 mm³ [preliminary — awaiting named physician review].

Exports: DICOM SEG · DICOM TID 1500 SR · FHIR R5 DiagnosticReport

git clone https://github.com/cYoren/radion && cd radion
cp .env.example .env
sed -i "s/^RADION_API_KEY=.*/RADION_API_KEY=$(openssl rand -hex 32)/" .env
./scripts/demo.sh   # Orthanc + OHIF + Reading Room on 127.0.0.1:8100

Why radiology AI fails on raw screenshots—and how a deterministic harness fixes the contract.

Sending uncalibrated JPEGs to a multimodal model loses voxel spacing, rescale intercepts, and 3D orientation. Radion separates visual reasoning from physical measurement so every number in a draft report traces back to a verifiable DICOM operation.

Clinical & Engineering RequirementUninstrumented Vision-Language PromptingRadion Harness + Reading Room
Linear, RECIST & Cobb geometryEstimated by eye from rescaled 2D pixels; ignores anisotropic slice thicknessComputed in 3D patient LPS millimetres from affine cosines; 4-point RECIST checks 90° ± 10° orthogonality
Attenuation & density claimsWindowed grey levels confused with Hounsfield UnitsCalibrated RescaleSlope · SV + RescaleIntercept before any ROI or threshold tool executes
Hallucinated report numbersFree-text narrative can invent sizes, slices, or series numberspropose_finding and draft_report reject any number not backed by a ledgered measurement_id
Radiologist supervisionOpaque final paragraph; impossible to see which slices the model actually inspectedLive SSE step stream, animated FOV crop box, visited-slice rail, and 1-key accept / correct / reject
Archive interoperabilityMarkdown blob trapped in a chat windowWrites standards-compliant DICOM SEG, DICOM TID 1500 SR, and FHIR R5 DiagnosticReport back to Orthanc / OHIF
Negative-screen phrasingOver-confident “exam is normal” statements on narrow triage headsExplicitly lists checked vs unchecked sections; never emits “normal” as a clinical rule-out

42 MCP tools across 8 radiological toolsets.

Both the radiologist's hand instruments on the Reading Room canvas and external AI agents over stdio or http://127.0.0.1:8812/mcp call the exact same Python functions. Every call is recorded to an append-only ledger with arguments, latency, view artifacts, and provenance digests.

Enhanced Multi-frame & NIfTI-1 ready
Expands PerFrameFunctionalGroupsSequence volumes, targets individual series via series_uid, and imports research .nii / .nii.gz with automatic from_dicom=False SEG/SR guards.
ADR 0014 PHI data-class lock
Uploaded clinical exams default to restricted. Remote model calls are refused unless the study is public or carries a named deidentified_attested record.
Corroborated multi-tool evidence
Independent detectors fuse into content-addressed evidence bundles graded A–D with recorded conflicts, skip reasons, and patient-bootstrap confidence intervals.

core

Study navigation, affine coordinates & calibrated views

list_studies, get_study, list_series, get_acquisition, find_landmarks, find_extreme, map_point, render_view, mark

measure

Voxel-to-millimetre & Hounsfield physics in patient LPS space

measure_distance, measure_bidimensional (RECIST 1.1 4-point), measure_cobb, measure_angle, measure_area, measure_roi, measure_mask, measure_ratio, measure_profile

segment

3D connected-component & HU-bounded volumetric masks

segment_region, segment_threshold

compare & calculators

Longitudinal volume doubling & published clinical formulas

compare_prior, calculate (Fleischner, Lung-RADS, volume doubling time, adrenal washout, cardiothoracic ratio, NASCET, Evans index)

quality & evidence

Slice geometry checks, corroborated detector graph & linked reporting

check_quality, get_evidence, propose_finding (rejects unmeasured numbers), draft_report (EN / PT structured templates)

bench

Leak-tested evaluation over stdio & streamable HTTP

list_tasks, start_task, submit_task, score_run

An objective 185-task scoreboard across CT, chest radiograph, and MR.

Instruments without a benchmark are a demo; a benchmark without instruments measures guessing. Radion ships four public task packs with an oracle ceiling (feeding reference masks through the real measurement tools to prove zero-bug voxel-to-mm plumbing) and a scripted non-ML floor, plus leakage tests guaranteeing ground truth never crosses the MCP wire.

Modality & PackMeasured Task FamiliesOracle Plumbing CheckGround-Truth Provenance
Chest CT (Synthetic Phantom)Planted solid & subsolid pulmonary nodules, lung volumes, LAA-950 emphysemaAnalytical mask sanity check (≤ 1 voxel margin)Deterministic generator (`radion phantom`, Apache-2.0, 2026)
Computed Tomography (Public Masks)Organ volumetry, lesion longest-axis & perpendicular RECIST diameters, HU attenuationReference-mask voxel→mm plumbing checkPublic reference masks documented in `docs/BENCH-SPEC.md` (2026)
Chest Radiograph (DX / CR)Cardiothoracic ratio, projection distances & calibrated RAD-DINO triage operating pointsProjection geometry + patient-bootstrap CIs (`docs/EVALUATION-CXR.md`)MIT `microsoft/rad-dino` frozen encoder + patient-disjoint Platt calibration (2026)
Magnetic Resonance (MR)Cross-sectional area, multi-series `series_uid` targeting & volumetric mask metricsReference-mask affine conversion checkEnhanced Multi-frame DICOM & NIfTI-1 (`from_dicom=False`, 2026)

Benchmark provenance: reproducible reports published at docs/EVALUATION-AGENT.md, docs/EVALUATION-CXR.md, and docs/BENCH-SPEC.md (generated by radion bench report · scope: non-clinical software benchmark · source year: 2026 · last checked: 2026-11-17 · owner: Medhub Engineering, radion v0.1.1 · review cadence: 90 days). Open roadmap items include live frontier-model runs (B3), promptable anatomy segmentation adapters (B4 / T2), and labelled claim-level interpretation packs (B5).

One Docker workstation. Zero mandatory cloud dependencies.

Radion deliberately avoids microservice sprawl and proprietary viewer lock-in. It composes proven open-source medical imaging infrastructure behind a single loopback gateway so imaging departments, teleradiology groups, and AI labs can evaluate it on a single Linux or macOS machine in minutes.

  • Orthanc 1.13 + OHIF 3.13: standard DICOMweb (QIDO-RS, WADO-RS, STOW-RS) and C-STORE port 4242, with automatic background polling for newly arrived stable studies.
  • Postgres 17 + Content-Addressed Store: durable FOR UPDATE SKIP LOCKED job queue, immutable SHA-256 mask artifacts, unified benchmark/study ledger, and physician review audit trail.
  • Permissive Apache-2.0 Core: code licences and neural weight licences are audited separately in LICENSE_MATRIX.md; copyleft archive components sit strictly across protocol boundaries.

Evaluate Radion with your imaging team or AI lab

Run the full Apache-2.0 stack yourself today, or scope a focused technical pilot with Medhub for private PACS integration, custom structured report templates (EN / PT / DE / FR / IT), or site-specific benchmark packs.

  • On-premise / VPC deployment alongside Orthanc or hospital PACS
  • Benchmarking internal or open-weight VLMs against your own reviewed cases
  • Bilingual structured reporting workflows with SOP-level traceability

Frequently asked questions

Why do vision-language models need a deterministic DICOM harness instead of reading PNG screenshots?

A PNG screenshot strips pixel spacing, slice thickness, rescale slope/intercept, patient orientation cosines, and FrameOfReferenceUID. When an LLM guesses '12 mm' or '35 HU' from pixels alone, the number is uncalibrated text. In Radion, Python computes every distance, angle, area, volume, and Hounsfield statistic directly from validated DICOM or NIfTI voxel geometry, and propose_finding rejects any numeric claim that lacks a recorded measurement_id.

How does the Reading Room integrate with OHIF Viewer and an existing PACS?

Radion ships with Orthanc 1.13 (DICOMweb + C-STORE on port 4242) and OHIF 3.13 out of the box. The Study screen defaults to the Live Reading Viewport—showing the agent's animated field-of-view crop, visited-slice rail, and click-to-measure calipers—and provides a 1-click toggle into OHIF hydrated with exported DICOM SEG masks and DICOM TID 1500 Structured Reports.

Does patient imaging data ever leave the hospital or workstation?

No by default. Every Docker Compose port binds to 127.0.0.1, and every study carries an ADR 0014 data class (public, deidentified_attested, or restricted). Uploaded clinical DICOMs default to restricted: remote LLM APIs and external MCP egress are blocked in code unless an operator explicitly configures local endpoints or records a named de-identification attestation.

Which AI agents and MCP clients work with Radion?

Any client speaking the Model Context Protocol (stdio or streamable HTTP on :8812/mcp) can drive Radion's 42 tools—including Claude Code, Claude Desktop, custom Python/TypeScript MCP agents, or Radion's built-in OpenAI-compatible multimodal runner (which supports local vLLM, Ollama, llama.cpp, or gated cloud endpoints). External MCP tool calls targeting a study automatically stream live into the Reading Room over Server-Sent Events.

How do radiologist corrections improve future evaluations without leaking PHI?

When a radiologist clicks Accept, Correct, or Reject on a proposed finding in the Reading Room (or re-measures a lesion with the hand caliper), Radion records the named physician review, updates the linked EN/PT structured report, and compiles accepted or corrected measurements into a local private benchmark pack (site-reviewed) containing study UIDs and millimetre coordinates with zero patient identifiers.

Is Radion a cleared diagnostic medical device?

No. Radion is open-source Apache-2.0 software built for research, objective agent benchmarking, and physician-supervised clinical decision support. It is not cleared, certified, or registered by the FDA, EMA, MHRA, or ANVISA, never emits the word 'normal' as a rule-out, and embeds its research disclaimer as a structured field on every report.

Research, benchmarking, and physician-supervised decision support boundary

Radion is open-source engineering software (Apache-2.0) and is not a certified or cleared medical device under FDA, EU MDR, UKCA, or ANVISA regulations. Shipped detectors and benchmark baselines are not clinically validated for autonomous diagnosis, screening rule-out, or unattended patient triage. Every generated report carries this notice as a required structured field and requires review and sign-off by a qualified physician.