i4h-catheter-navigation-e2e

Runs the end-to-end catheter navigation smoke pipeline covering setup, digital twin, DRR rendering, and unit tests.

3.2k|370|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/NVIDIA/skills --skill i4h-catheter-navigation-e2e
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: i4h-catheter-navigation-e2e
Source: https://github.com/NVIDIA/skills/tree/main/skills/i4h-catheter-navigation-e2e
Command: npx skills add https://github.com/NVIDIA/skills --skill i4h-catheter-navigation-e2e

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Verifying the full Isaac for Healthcare catheter navigation workflow requires manually chaining setup checks, digital twin generation, DRR rendering, and unit tests, which is error-prone and hard to reproduce.

Core Features & Use Cases

  • Orchestrated Smoke Pipeline: Chains setup verification, TotalSegmentator-based digital twin creation, GPU DRR rendering, and CPU unit tests under one shared run directory with per-stage logs.
  • Partial Run Support: Falls back to a synthetic DRR path when no CT subject is available and clearly documents skipped stages in the summary.
  • Use Case: A robotics engineer validating a v0.7 installation can run one command flow to confirm host readiness, generate a patient cache from a CT subject, render a fluoroscopy frame, and collect unit-test evidence in a single timestamped run folder.

Quick Start

Ask your agent to run the full catheter navigation end-to-end smoke pipeline with your TotalSegmentator subject and summarize every artifact produced.

Frequently Asked Questions about i4h-catheter-navigation-e2e

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

FAQPage Schema
How do I run the full catheter navigation smoke pipeline?

Invoke the end-to-end skill with a TotalSegmentator subject set in the SUBJ variable. It initializes a timestamped run directory, verifies setup, builds the digital twin into a cache, renders a DRR, runs CPU unit tests, and writes a summary of all artifacts.

Can I run the catheter workflow smoke test without CT data?

Yes, the skill supports a partial path when no subject is provided. It skips the digital twin stage, renders a synthetic DRR instead, still runs setup checks and unit tests, and clearly labels the run as partial in the summary.

Does the catheter navigation smoke test launch the interactive viewport?

No, the end-to-end smoke explicitly skips the interactive viewport because it requires a display. For interactive keyboard-driven demos, use the separate viewport skill after the smoke run completes.

What prerequisites does the catheter navigation pipeline need?

It requires the i4h-workflows repository checked out, host setup requirements from the setup skill, a GPU for cache-based DRR rendering, and an extracted TotalSegmentator subject for the full end-to-end path.

Why did my catheter DRR render fall back to synthetic output?

The synthetic fallback triggers when no subject is set or the digital twin stage did not produce a cache. GPU render failures also cause fallback; check the stage logs in the run directory for the specific GPU setup gap.