skills.rest
NVIDIA
NVIDIAOFFICIAL
Explore all skills by this author →
WebsiteGitHub

i4h-catheter-navigation-viewport

Launch the interactive Slang fluoroscopy viewport with XPBD catheter physics and DSA rendering.

3.2k|370|Updated Feb 25, 2026
Search Tags:#simulation#viewport#DSA#catheter navigation#isaac for healthcare#xpbd physics#fluoroscopy
One-click install
npx skills add https://github.com/NVIDIA/skills --skill i4h-catheter-navigation-viewport
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: i4h-catheter-navigation-viewport
Source: https://github.com/NVIDIA/skills/tree/main/skills/i4h-catheter-navigation-viewport
Command: npx skills add https://github.com/NVIDIA/skills --skill i4h-catheter-navigation-viewport

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Setting up an interactive catheter navigation simulation requires resolving digital-twin caches, configuring display servers, and passing the correct launch flags for vessel rendering, centerline insertion, and DSA contrast. This Skill automates that launch sequence so engineers can open a live fluoroscopy viewport and teleoperate a catheter without manually assembling the command.

Core Features & Use Cases

  • Interactive Viewport Launch: Runs the i4h-workflows interactive_viewport entry point with real vessel geometry, centerline-guided insertion, DSA contrast, and configurable detector size and pixel spacing.
  • Cache Validation: Verifies the digital-twin cache (mu_volume.npy) exists before launch and directs the user to the digital-twin generation skill when missing.
  • Remote Display Handling: Applies the QT_QPA_PLATFORM=xcb workaround for remote X11 sessions and documents keyboard controls for catheter advance, retract, rotation, and C-arm presets.
  • Use Case: A robotics engineer with a patient-specific CT cache asks the agent to open the live fluoro simulation; the agent validates the cache, creates a timestamped run directory, launches the viewport, and reports the keyboard controls.

Quick Start

Ask your agent to launch the interactive catheter fluoroscopy viewport using your digital-twin cache directory with DSA and centerline-guided insertion enabled.

Frequently Asked Questions about i4h-catheter-navigation-viewport

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

FAQPage Schema
How do I launch the interactive catheter fluoroscopy viewport?▼

Run ./i4h run catheter_navigation interactive_viewport --local with --ct-dir pointing to your digital-twin cache, plus --vessel-source real, --insertion-axis centerline, and --dsa flags. The skill validates the cache and creates a timestamped run directory with logs before launching.

What keyboard controls does the catheter navigation viewport support?▼

W and S advance and retract the catheter along the centerline, A and D rotate it, X toggles DSA contrast, keys 1-4 select C-arm presets, Space pauses, R resets, and Q or Esc quits. The full table is in the catheter_navigation workflow README.

Why are the viewport keyboard controls dead over remote X11?▼

Remote X11 sessions often need QT_QPA_PLATFORM=xcb, which the launch step sets by default. Keyboard focus may also require keeping the pointer over the fluoro window on remote desktops.

Can I run the catheter viewport in a headless CI environment?▼

No, the interactive viewport requires a display server and keyboard focus, so it is unsuitable for headless CI. For headless GPU renderer verification, use the single-frame DRR rendering workflow instead.

What prerequisites does the interactive viewport need before launch?▼

You need a completed digital-twin cache containing mu_volume.npy, a display server such as local X11 or remote desktop, and a GPU with at least 8 GB VRAM (16 GB recommended). The skill exits with an error if the cache is missing.

Related Skills

Explore More Software Engineering Skills→
isaac-simisaac-sim
4.0k

occupancy-map

Generate ROS-compatible occupancy maps from USD scenes for robot navigation.

Official
Intermediate
root-5root-5

modeling

Train machine learning models with Optuna hyperparameter tuning and artifact saving.

Community
Intermediate
Skyvern-AISkyvern-AI
22.7k

testing

Tests Skyvern deployments by validating API, frontend rendering, browser sessions, and workflows.

Official
Intermediate
isaac-simisaac-sim
4.0k

isaac-sim-headless-deployment

Launches Isaac Sim headlessly for batch simulation and synthetic data generation.

Official
Intermediate