<< All versions
Skill v1.0.0
currentTrusted Publisher100/100microsoft/healthcareai-examples/ground-zeroshot
──Details
PublishedSeptember 26, 2026 at 12:19 AM
Content Hashsha256:653bade9e933998b...
Git SHA
──Files
Files (1 file, 2.5 KB)
SKILL.md2.5 KBactive
SKILL.md · 57 lines · 2.5 KB
version: "1.0.0" name: ground-zeroshot description: Ground CXR findings using MI2 zero-shot classification. Returns per-finding probabilities bucketed into positive/possible for the agent to use when writing the report. argument-hint: |
- image_path: required file path or http(s) URL to the CXR image (PNG or JPEG)
- extra_labels: optional list of additional label strings to score alongside the default set
ground-zeroshot
Calls the MI2 zero-shot classifier and returns bucketed per-finding probabilities. Does not write a report — the agent produces the report using the write-report skill after grounding.
Budget
- Tool calls: 1 — exactly one
mcp_medimageinsig_zeroshot_classifycall per image. - Do not retry on success.
How to use
- Resolve the image. If
image_pathis an http(s) URL, pass it through to the tool unchanged — do NOT download it,curlit, or turn it into a local file; the MCP server fetches URLs itself. Otherwise it is a local path: the MCP tool runs in a different working directory, so if it is not absolute, resolve it viarealpath; if it can't be resolved, ask the user.
- Assemble the label list. Read the canonical label list from below and use those strings verbatim. Append any caller-provided
extra_labels.
- Call the classifier. Call
mcp_medimageinsig_zeroshot_classifywithfile_path= absolute path andlabels= assembled list. One call per image.
- Bucket the scores. Use these cutoffs:
- ≥ 0.20 → positive
- 0.08 – 0.20 → possible
- < 0.08 → absent (omit)
- Return the findings. Return the positive and possible labels with their raw scores. Do not write a report. The agent decides what to do next.
NIH ChestX-ray14 labels (MI2 format)
Pass these strings as the labels argument to zeroshot_classify. Format is "<modality> <body_part> <view> <condition>" — MI2 is sensitive to this structure, do not reword.
x-ray chest anteroposterior Atelectasisx-ray chest anteroposterior Cardiomegalyx-ray chest anteroposterior Consolidationx-ray chest anteroposterior Edemax-ray chest anteroposterior Effusionx-ray chest anteroposterior Emphysemax-ray chest anteroposterior Fibrosisx-ray chest anteroposterior Herniax-ray chest anteroposterior Infiltrationx-ray chest anteroposterior Massx-ray chest anteroposterior Nodulex-ray chest anteroposterior Pleural_Thickeningx-ray chest anteroposterior Pneumoniax-ray chest anteroposterior Pneumothorax