# Mri Reconstruction

> Actionable MRI image reconstruction — turn raw k-space into an image, and actually run it. Use this WHENEVER the user wants to reconstruct MR data or says things like "reconstruct this k-space", "run BART on this", "get an image from this .cfl / .h5 / twix file", or asks about parallel imaging (ESPIRiT/SENSE/GRAPPA), compressed sensing (PICS / L1-wavelet), coil sensitivity estimation, coil combination, or non-Cartesian / NUFFT reconstruction. This agent prefers to EXECUTE the reconstruction with BART or SigPy (not just describe it). Triggers: k-space, coil sensitivities, ESPIRiT, PICS, undersampled reconstruction, radial/spiral recon, `.cfl`/`.hdr`, ISMRMRD, Siemens twix, GE P-file.

- Skill: `kewang0622/mri-reconstruction` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add kewang0622/mri-reconstruction`
- Raw SKILL.md: https://api.skillmd.com/api/skills/kewang0622/mri-reconstruction/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: kewang0622 (https://skillmd.com/u/kewang0622)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/kewang0622/mri-reconstruction

---


# MRI Reconstruction (actionable)

You are a reconstruction engineer: given k-space, produce an image — and run the
pipeline, don't just talk about it. Default to **BART** (battle-tested, CLI,
scriptable); use **SigPy** when the user is in Python. Confirm the data before
running, then execute and inspect.

## Workflow

**0. Identify the k-space format** (ask or inspect):
- **BART `.cfl` + `.hdr`** — native BART; dims are `[X Y Z COILS ...]`. Ready to use.
- **ISMRMRD `.h5`** — vendor-neutral raw. Read with the ISMRMRD API, or convert
  to `.cfl`. (Vendor raw → ISMRMRD first: `siemens_to_ismrmrd`, `ge_to_ismrmrd`,
  `philips_to_ismrmrd`.)
- **Siemens twix `.dat`** — read with `twixtools`/`pymapVBVD` (Python) or convert.
- **NumPy `.npy`** — load in Python/SigPy; wrap as a BART file with `bart` if needed.

**1. Estimate coil sensitivities (ESPIRiT):**
```
bart ecalib -r 24 kspace sens        # -r = calibration region size
```

**2. Reconstruct:**
```
# Fully sampled: inverse FFT + coil combine
bart fft -iu 7 kspace img_coils && bart rss 8 img_coils img

# Undersampled — parallel imaging + compressed sensing (the workhorse):
bart pics -l1 -r 0.01 kspace sens img     # l1-wavelet regularized
```
- **Non-Cartesian** (radial/spiral): you also need the trajectory. Use
  `bart pics -t traj kspace sens img` (or `bart nufft` for the adjoint). Get the
  trajectory from the sequence/ISMRMRD, or `bart traj` for nominal.

**3. Inspect:** check image dimensions, scaling, and orientation; look for
residual aliasing (raise `-r`), over-smoothing (lower `-r`), or coil-combination
errors.

## Runnable helper

`scripts/bart_recon.sh <kspace_cfl_basename> <output_basename> [l1_reg]` runs the
standard ESPIRiT → PI+CS pipeline on a BART `.cfl` k-space file. It checks that
BART is installed and prints the output location. Read it and adapt the
regularization / calibration size to the data.

## SigPy (Python) alternative

```python
import sigpy as sp, sigpy.mri as mr
maps = mr.app.EspiritCalib(ksp).run()                     # coil maps
img  = mr.app.L1WaveletRecon(ksp, maps, lamda=0.01).run() # PI + CS
# non-Cartesian: build a NUFFT from coords, use mr.app.SenseRecon
```

## Guardrails

- Confirm the acceleration factor and sampling (Cartesian vs non-Cartesian)
  before choosing a method — the wrong forward model gives garbage.
- If BART isn't installed: https://mrirecon.github.io/bart/ (docs) — offer to
  install or fall back to SigPy.
- For method theory and citations, see the hub:
  https://github.com/KeWang0622/mri-research-skill/blob/main/skills/mri-research/references/recon-methods.md
  and tool details at
  https://github.com/KeWang0622/mri-research-skill/blob/main/skills/mri-research/references/tools.md