# Coronary Angiography (angio/coronary)

> Coronary angiography read: vessels, SYNTAX segments and stenosis with QCA evidence.

Upload a whole coronary angiography study (a patient CD, a DICOM folder or single XA runs). One run returns a structured read organised in sections: run inventory with projections, a temporally consistent vessel mask, SYNTAX coronary segments, and a lesion list with quantitative coronary angiography (%DS, MLD, reference diameter, lesion length) plus an AI visual-equivalent grade. Every number traces to a measurement, and the evidence (DICOM SEG, overlay video, key frame) comes with the result. A draft cath report is available as an opt-in add-on.

Model page: https://medrun.ai/models/angio/coronary
Status: beta · version 1.0.0 · viewer: cine

## Input

Whole coronary angiography study: all XA cine runs of one procedure (patient CD or DICOM folder), diagnostic ± PCI runs. Single runs work too.

Accepted: DICOM files or folder, CD export (DICOMDIR), zip / tar.gz.

## Pricing

- `angio/coronary/interpret`: $0.12 up to 600 frames · $0.24 up to 1,500 frames · $0.36 above 1,500 frames per request
- `angio/coronary/qca`: $0.02 per call
- Draft report (opt-in, `options.report`): +$0.02 per run

## Result sections

- `#views` Views (available): Each run's injected artery (LCA/RCA), positioner angles and projection, contrast and key frames.
- `#quality` Quality (beta): Adequacy flags (short run, panned gantry, missing calibration, segmentation fallback) carried into the report's limitations.
- `#segment-vessels` Vessel segmentation (available): Temporally consistent coronary-tree mask on every frame, as DICOM SEG and an overlay video.
- `#segments` Coronary segments (available): SYNTAX coronary segment labels (11 main segments) and the list of visible segments.
- `#stenosis` Stenosis (available): Lesion list per segment with QCA %DS, MLD, reference diameter, length and an AI visual-equivalent grade; bands < 50 / 50–69 / ≥ 70 % (LM ≥ 50 %).
- `#dominance` Dominance (planned): Right, left or co-dominant circulation from the LCA and RCA runs.
- `#timi-flow` TIMI flow (planned): TIMI flow grade, corrected TIMI frame count and myocardial blush grade.
- `#lesion-features` Lesion features (planned): Calcification, thrombus, bifurcation (Medina), CTO, ostial location, tortuosity and ACC/AHA lesion type.
- `#syntax-score` SYNTAX score (planned): SYNTAX score with per-lesion breakdown and tertile.
- `#stent-sizing` Stent sizing (planned): Proximal and distal reference diameters, lesion length and a suggested stent size for a target lesion.
- `#pci-result` PCI result (planned): Pre/post-PCI comparison (residual %DS, acute gain, TIMI change, dissection).
- `#lvef` LVEF estimate (planned): Estimated LVEF from coronary runs when no LV gram or echo is available.
- `#report` Draft report (available): Opt-in draft cath report (findings, impression, limitations) written from the structured result; every number is validated against it.

## Endpoint `angio/coronary/interpret` (run)

The full read of the study: every XA run is grouped, inventoried and analysed; the result contains all sections the input supports.

Docs: https://medrun.ai/models/angio/coronary/api · OpenAPI: https://api.medrun.ai/v1/models/angio/coronary/interpret/openapi.json

### Input schema

- `files` (array; required): The angiography study: DICOM files, a folder, a CD export (DICOMDIR) or a zip. `file_…` ids from /v1/uploads or https URLs.
- `clinical_context` (object): Optional. Used for guidance only; never names, IDs or dates.
  - `age_years` (integer): Age (years)
  - `sex` (string; one of female, male, other, unknown): Sex
  - `indication` (string): For example "stable angina" or "NSTEMI".
- `options` (object): Options
  - `report` (boolean; default false): Adds a draft cath report written from the structured result (English). +$0.02 per run.
  - `return` (array; default ["json","dicom-sr","dicom-seg","sc"]): JSON is always returned. DICOM objects reference your original UIDs.
  - `previews` (boolean; default true): WebM overlay and key-frame PNGs (not diagnostic).

### Example (cURL)

```bash
response=$(curl --request POST \
  --url https://api.medrun.ai/v1/run/angio/coronary/interpret \
  --header "Authorization: Bearer $MEDRUN_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "input": {
    "files": [
      "file_01K6R4X2Q9Y7T3V5W8Z0A1B2C3"
    ],
    "options": {
      "report": false
    }
  }
}')
REQUEST_ID=$(echo "$response" | jq -r .id)
```

## Endpoint `angio/coronary/qca` (tool)

Interactive quantitative coronary angiography on a segment you pick after seeing the read: diameter profile, MLD, interpolated reference diameter, %DS and lesion length on the chosen frame.

Docs: https://medrun.ai/models/angio/coronary/qca/api · OpenAPI: https://api.medrun.ai/v1/models/angio/coronary/qca/openapi.json

### Input schema

- `source_request` (string; required): The `interpret` request whose files and result this measurement uses.
- `series_uid` (string; required): Series Instance UID of the XA run.
- `frame_number` (integer; required): 1-based DICOM frame number (end-diastolic frames work best).
- `segment` (string; required; one of LM, pLAD, mLAD, dLAD, pLCx, dLCx, pRCA, mRCA, dRCA, PDA, PLB): Coronary segment to measure (SYNTAX naming, e.g. mLAD).
- `points` (array): Optional. Two [x, y] pixel points bounding the lesion; default is the whole segment.
- `options` (object): Options
  - `calibration` (string; default "isocenter"; one of isocenter, catheter, none): Isocenter from DICOM geometry, catheter (give the size), or none (pixels only).
  - `catheter_french` (integer; one of 4, 5, 6, 7, 8): Catheter size (F)

### Example (cURL)

```bash
response=$(curl --request POST \
  --url https://api.medrun.ai/v1/run/angio/coronary/qca \
  --header "Authorization: Bearer $MEDRUN_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "input": {
    "source_request": "req_01K6R4YQ8JT97KB6CQ643DZVMX",
    "series_uid": "1.2.826.0.1.3680043.8.498.70321956482019375610283746501928",
    "frame_number": 49,
    "segment": "mLAD"
  }
}')
REQUEST_ID=$(echo "$response" | jq -r .id)
```

## Output

The MedRun result envelope: https://medrun.ai/docs/result-envelope