agentleFS
aizechaizech/clinical-skills/.agents/skills/radiology-dataset-guide/SKILL.md

radiology-dataset-guide

Skill4 starsChanged 7 months agoMITView on GitHub

Guides researchers and developers through radiology dataset selection, access, and utilization for AI development. Use when user mentions "radiology dataset", "medical imaging data", "RSNA challenge", "MIMIC data access", or needs dataset guidance.

The file

Files
SKILL.md

Radiology Dataset Guide Skill

Triggers

  • "radiology dataset"
  • "medical imaging data"
  • "RSNA challenge"
  • "MIMIC data access"
  • "CheXpert download"
  • "dataset comparison"
  • "training data preparation"
  • "public dataset"

Parameters

  • task_type (required): ML/AI task being solved
    • detection - Abnormality/nodule/cancer detection
    • segmentation - Organ or lesion segmentation
    • classification - Disease or finding classification
    • reconstruction - Image reconstruction/enhancement
    • quantification - Measurement and feature extraction
  • anatomy (optional): Body region or organ system
  • modality (optional): Imaging modality preference
  • access_requirements (optional): Data use restrictions
  • commercial_use (optional): Boolean for commercial application intent

Dataset Inventory

DatasetModalityPrimary TaskAccessAnnotations
RSNA Bone AgeX-rayRegressionPublicAge, quality
RSNA PneumoniaChest X-rayDetectionPublicBounding boxes
RSNA Brain HemorrhageCTDetectionPublicBounding boxes, type
NIH ChestX-ray14Chest X-rayClassificationPublicLabels
CheXpertChest X-rayClassificationInstitutionalLabels
MIMIC-CXRChest X-rayMultiPhysioNetLabels, reports
CheXphotoChest X-rayClassificationPublicSynth/real pairs
LUNA16CTDetectionPublicNodule centers
KiTSCTSegmentationPublicKidney/tumor
BraTSMRISegmentationResearchMulti-modal seg
PANDAHistologyClassificationPublicBiopsy grades
OBJ-CXRChest X-rayDetectionPublicBounding boxes

Output Format

Returns structured JSON with:

  • Relevant datasets ranked by suitability
  • Annotation quality and completeness
  • Access procedure and requirements
  • Key publications and benchmarks
  • Preprocessing recommendations
  • Compliance and ethics considerations

Usage Examples

task_type: detection
anatomy: lung
modality: CT

task_type: classification
anatomy: chest
commercial_use: true

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.