i4h-catheter-navigation

bởi nvidia

Overview of `workflows/catheter_navigation/` (fluorosim DRR, XPBD physics, vasculature digital twin). Use when the user asks what the catheter navigation…

npx skills add https://github.com/nvidia/skills --skill i4h-catheter-navigation

i4h Catheter Navigation Workflow

Purpose

Orient on the endovascular catheter navigation workflow before touching a specific stage: which CLI modes exist, how fluorosim / physics / digital-twin pieces fit together, and which per-stage skill to invoke next. This skill routes - it runs no pipeline stage itself.

Base Code

These steps drive the i4h-workflows base code (the workflows/catheter_navigation/ tree). To reuse an existing checkout, set I4H_WORKFLOWS to its path (no clone happens). Otherwise this resolves the current repo, or clones to ~/i4h-workflows - pick that default without prompting. Run every command below from the resolved root:

# Resolve the i4h-workflows base code (provides workflows/catheter_navigation/).
ROOT="${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>/dev/null)}"
if [ ! -d "$ROOT/workflows/catheter_navigation" ]; then
  ROOT="${I4H_WORKFLOWS:-$HOME/i4h-workflows}"
  [ -d "$ROOT/workflows/catheter_navigation" ] || git clone https://github.com/isaac-for-healthcare/i4h-workflows "$ROOT"
fi
export I4H_WORKFLOWS="$ROOT"; cd "$ROOT"

Basics

  • Mode registry (source of truth): workflows/catheter_navigation/metadata.json - lists ./i4h modes and their runtime commands.
  • Human docs: workflows/catheter_navigation/README.md - data download, digital-twin build, viewport controls, troubleshooting.
  • Each pipeline stage has its own skill. Compose them or use [[i4h-catheter-navigation-e2e]] for a full smoke run.
  • No CT data is shipped; users bring their own NIfTI/DICOM (e.g. TotalSegmentator subset).

Supported Modes

Fallback when ./i4h modes catheter_navigation fails (setup incomplete):

ModePurpose
preprocess_ctCT -> attenuation volume (mu_volume.npy) + optional HU cache
segment_vesselsArterial tree mask + centerline (vasculature digital twin)
render_drrSingle DRR frame (synthetic phantom if no cache)
interactive_viewportLive fluoroscopy viewport with XPBD catheter physics

Subprojects

DirectoryPurpose
workflows/catheter_navigation/scripts/simulation/fluorosim/examples/interactive_catheter_slang_viewport.pyInteractive viewport glue script (invoked by interactive_viewport mode)
workflows/catheter_navigation/scripts/simulation/fluorosim/rendering/Local DRR rendering helpers used by viewport fallback path
workflows/catheter_navigation/metadata.json./i4h mode registry and command wiring
Installed packagesfluorosim, vasculature_digital_twin, catheter_vasculature_solver provide renderer + digital twin + solver runtime
workflows/catheter_navigation/tests/CPU smoke tests (no GPU required)

Run

Run the step below before answering. Each step is a separate bash call; variables persist in the local agent's tmux session.

Step 1 - list supported modes

REPO_ROOT="${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>/dev/null)}"; [ -d "$REPO_ROOT/workflows/catheter_navigation" ] || REPO_ROOT="$HOME/i4h-workflows"
"${REPO_ROOT}/i4h" modes catheter_navigation

If the command fails, use the Supported Modes fallback table above.

Skill Index

SkillPurpose
i4h-catheter-navigation-setupHost/GPU preflight, PYTHONPATH, smoke-test verify
i4h-catheter-navigation-digital-twinDownload CT data, preprocess, segment vessels
i4h-catheter-navigation-render-drrRender a single DRR frame
i4h-catheter-navigation-viewportLaunch interactive fluoroscopy + catheter sim
i4h-catheter-navigation-smokeRun CPU unittest smoke suite
i4h-catheter-navigation-e2eEnd-to-end smoke (setup -> digital twin -> render -> tests)

Prerequisites

  • NVIDIA GPU with CUDA >= 12.8 and Vulkan-capable driver for GPU modes (render, viewport).
  • For any hands-on stage, run [[i4h-catheter-navigation-setup]] first.
  • For patient-specific runs, run [[i4h-catheter-navigation-digital-twin]] before viewport or cache-based DRR.

Limitations

  • Overview/routing only - each stage has its own skill; this one performs no preprocessing, rendering, or simulation.
  • RL/IL training integration with Isaac Lab is not yet a first-class skill stage in v0.7; use the workflow README and fluorosim API for custom data generation.

Troubleshooting

  • Error: mode not found - Cause: typo or ./i4h not run from repo root. Fix: cd to repo root and re-run Step 1; inspect workflows/catheter_navigation/metadata.json.
  • Error: import errors for fluorosim / vasculature_digital_twin / catheter_vasculature_solver - Cause: dependencies not installed in active env. Fix: run [[i4h-catheter-navigation-setup]] and install README requirements.

Final Response

The response is incomplete unless it includes all three parts below, each separated by a blank line.

  1. Orientation - one short paragraph: fluorosim stack, digital twin, ./i4h modes.

  2. Supported modes - heading plus markdown table from Step 1 or the Supported Modes fallback table.

  3. Available skills - heading plus the full Skill Index table copied into the response.

Then recommend [[i4h-catheter-navigation-setup]] if setup is not done, and name one next stage skill matched to the user's goal.

Thêm skills từ nvidia

compileiq-debug
nvidia
Sử dụng khi có điều gì đó không ổn: Search() bị treo, tất cả các đánh giá đều trả về INVALID_SCORE, điểm số không cải thiện, mọi cấu hình đều trả về cùng một số, lỗi ptxas…
create-github-pr
nvidia
Tạo pull request GitHub bằng cách sử dụng gh CLI. Sử dụng khi người dùng muốn tạo PR mới, gửi mã để xem xét, hoặc mở pull request. Từ khóa kích hoạt -…
nemoclaw-maintainer-cross-issue-sweep
nvidia
Quét các vấn đề đang mở khác để tìm những vấn đề mà một PR nhất định có thể sửa hoặc vô tình làm hỏng. Đưa ra các cơ hội sửa lỗi liền kề và rủi ro mâu thuẫn với file:dòng…
fhir-basics
nvidia
Dạy các tác nhân cách hoạt động của API FHIR R4, những tài nguyên có sẵn, cách truy vấn chúng với tham số tìm kiếm, và cách phân tích chính xác tất cả các định dạng phản hồi…
compileiq-validate-result
nvidia
Sử dụng SAU KHI tìm kiếm hoàn tất và TRƯỚC KHI yêu cầu tăng tốc hoặc gửi ACF. Tải tệp CSV dump_results, trích xuất các ứng viên top-K (đơn mục tiêu)…
changelog-audit
nvidia
Kiểm tra Warp CHANGELOG.md trước khi phát hành: khôi phục các mục bị mất, sắp xếp theo tác động người dùng, tinh chỉnh ngôn ngữ mục, xuống dòng và (chế độ nhánh phát hành) so sánh bump…
maintain-dynamic-plugins
nvidia
Duy trì các bộ nạp plugin động NeMo Relay, tệp kê khai, SDK gốc Rust, giao thức worker gRPC, SDK worker Python, tài liệu, kiểm thử và phạm vi quy trình phát hành
dgx-diagnose
nvidia
Chẩn đoán các sự cố thường gặp của DGX Station GB300 — lỗi CUDA, nhắm sai GPU, lỗi container vLLM/SGLang, vấn đề trạng thái MIG, lỗi NVLink/Fabric Manager,…