skills.rest
nahisaho
nahisahoCOMMUNITY
Explore all skills by this author →
GitHub

scientific-radiology-ai

Build explainable MONAI pipelines for radiology classification, segmentation, and reporting.

3|1|Updated Feb 11, 2026
Search Tags:#ai#medical-imaging#structured-report#radiology#monai#grad-cam
One-click install
npx skills add https://github.com/nahisaho/satori --skill scientific-radiology-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scientific-radiology-ai
Source: https://github.com/nahisaho/satori/tree/main/src/.github/skills/scientific-radiology-ai
Command: npx skills add https://github.com/nahisaho/satori --skill scientific-radiology-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides an end-to-end AI radiology pipeline that delivers classification, segmentation, explainability, and structured reporting for medical imaging.

Core Features & Use Cases

  • MONAI-based classification, segmentation, Grad-CAM explainability, and structured radiology report generation.
  • Grad-CAM visualization and explainability to support clinical decision-making.
  • AI-RADS scoring integration and report-ready outputs for radiology workflows.
  • Use cases include CT/MRI/X-ray image analysis, automated report drafting, and clinician review support.

Quick Start

Run the end-to-end radiology AI pipeline to classify images, generate Grad-CAM explanations, and produce a structured report.

Frequently Asked Questions about scientific-radiology-ai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an AI radiology pipeline for medical image classification and segmentation?▼

Grad-CAM visualization provides explainability for AI radiology predictions by highlighting critical image regions used for classification. This supports clinical decision-making and integrates with AI-RADS scoring to generate report-ready outputs for clinician review.

Can I generate structured radiology reports automatically from CT and MRI scans?▼

Yes, you can automatically generate structured radiology reports from CT, MRI, or X-ray datasets. The pipeline leverages MONAI and PyTorch to deliver accurate predictions, Grad-CAM explanations, and report-ready outputs for clinical scenarios.

How does Grad-CAM explainability work for medical imaging predictions?▼

Grad-CAM visualization provides explainability for AI radiology predictions by highlighting critical image regions used for classification. This supports clinical decision-making and integrates with AI-RADS scoring to generate report-ready outputs for clinician review.

Does this MONAI-based pipeline support AI-RADS scoring integration?▼

Yes, the pipeline supports AI-RADS scoring integration. It applies MONAI-based models on medical imaging datasets to deliver predictions, Grad-CAM explanations, and structured reports with AI-RADS scoring for radiology workflows.

What is the best way to automate radiology report drafting from X-ray image analysis?▼

The best way to automate report drafting is running an end-to-end radiology AI pipeline that classifies X-ray images, generates Grad-CAM explanations, and produces structured reports. This leverages MONAI and PyTorch for accurate predictions and automated output.

Related Skills

Explore More Data & Analytics Skills→
youyinnnyouyinnn
1

pydicom

Read, write, and anonymize DICOM medical imaging datasets.

Community
Intermediate
maziyarpanahimaziyarpanahi
5.0k

structuring-radiology-reports

Convert free-text radiology reports into structured findings, impressions, measurements, and follow-up recommendations.

Community
Advanced
xlelibertyxleliberty

senior-computer-vision

Build and deploy computer vision pipelines for detection, segmentation, and classification.

Community
Advanced
Yezez9Yezez9

pyhealth

Develop, test, and deploy healthcare machine learning models with clinical data.

Community
Advanced