# Chest CT (ct/chest)

> Chest CT read: nodules with Fleischner or Lung-RADS, PE with RV strain, lungs, pleura and ribs.

Upload a CT pulmonary angiography study as received from the scanner or PACS. The run picks the thin contrast-enhanced soft-tissue series and checks the pulmonary arteries' opacification first: without it the study is stated not assessable for embolism, with the measured attenuation. On an opacified study it answers whether there is a pulmonary embolism, outlines every clot in 3D with its lobe, side and volume, gives the most proximal level (central or peripheral) and the total clot burden, and flags an RV/LV diameter ratio of 1.0 or more (right ventricular strain) with the ESC 2019 risk-class guidance. Outlines return as DICOM SEG on your slices, measurements as a TID 1500 SR, with key-slice images of the largest clots.

Model page: https://medrun.ai/models/ct/chest
Status: beta · version 1.0.0 · viewer: volume

## Input

A CT pulmonary angiography study: the DICOM folder, a CD export or a zip of it (all series; the thin contrast-enhanced soft-tissue series is chosen for you). Axial slices of 3 mm or thinner.

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

## Pricing

- `ct/chest/interpret`: $0.15 per request
- Draft report (opt-in, `options.report`): +$0.02 per run

## Result sections

- `#pulmonary-embolism` Pulmonary embolism (available): Pulmonary arterial opacification checked first (not assessable without it); pulmonary embolism present or absent; every clot outlined in 3D with its lobe, side and volume; the most proximal level (central or peripheral), the total clot burden, and the RV/LV ratio of 1.0 or more flag with the ESC 2019 risk-class guidance.
- `#rv-lv-ratio` RV/LV ratio (planned): Right and left ventricular diameters, the RV/LV ratio and the main pulmonary artery diameter.
- `#lung-nodules` Lung nodules (planned): Nodule detection, 3D outline, diameter and volume, type and the Fleischner 2017 management.
- `#triage` Emergency triage (planned): Fast flags for pulmonary embolism, pneumothorax, aortic dissection or large aneurysm, and large effusions.
- `#lung-rads` Lung-RADS (planned): Screening LDCT category, nodule growth against the prior and the S modifier.
- `#cancer-risk` Lung-cancer risk (planned): 1–6-year lung-cancer risk from a screening LDCT.
- `#emphysema` Emphysema (planned): Lobe-wise low-attenuation area (LAA-950) and distribution.
- `#ild` Interstitial lung disease (planned): ILD features, extent and the UIP-pattern category on HRCT.
- `#infection` Infection extent (planned): Consolidation and ground-glass outlines with involvement per lobe.
- `#airways` Airways (planned): Airway tree, wall thickness and broncho-arterial ratio for bronchiectasis and wall thickening.
- `#pleural-effusion` Pleural and pericardial effusion (planned): Effusion outline, side, volume and density.
- `#pneumothorax` Pneumothorax (planned): Pneumothorax detection, side, volume and tension signs.
- `#rib-fractures` Rib fractures (planned): Rib fracture detection with rib numbering, type and flail segment.
- `#coronary-calcium` Coronary calcium (planned): Agatston-equivalent coronary calcium score and category on non-gated chest CT.
- `#segment-lungs` Lung, lobe and vessel segmentation (planned): Lungs, five lobes, pulmonary arteries, veins and airways as masks with volumes.
- `#report` Draft report (available): Opt-in draft report (findings, impression, limitations) written from the structured result; every number is validated against it.

## Endpoint `ct/chest/interpret` (run)

The full read of the chest CT study: the CT pulmonary angiography series is analysed and the result contains all sections the study supports.

Docs: https://medrun.ai/models/ct/chest/api · OpenAPI: https://api.medrun.ai/v1/models/ct/chest/interpret/openapi.json

### Input schema

- `files` (array; required): The chest CT study: DICOM files, a folder, a CD export or a zip (all series are fine). `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 "suspected pulmonary embolism, D-dimer raised" or "dyspnoea after surgery".
- `options` (object): Options
  - `report` (boolean; default false): Adds a draft chest CT report written from the structured result (English). +$0.02 per run.
  - `return` (array; default ["json","dicom-sr","dicom-seg"]): JSON is always returned. DICOM objects reference your original UIDs.

### Example (cURL)

```bash
response=$(curl --request POST \
  --url https://api.medrun.ai/v1/run/ct/chest/interpret \
  --header "Authorization: Bearer $MEDRUN_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "input": {
    "files": [
      "file_01K7CTCHEST000000000000000"
    ],
    "options": {
      "report": false
    }
  }
}')
REQUEST_ID=$(echo "$response" | jq -r .id)
```

## Output

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