VBoussot/ImpactReg

IMPACT-Reg — Multimodal Medical Image Registration

Robust multimodal (MR / CT / CBCT) deformable registration presets, built with KonfAI. Alignment is driven by the IMPACT semantic similarity metric — deep features from pretrained segmentation / foundation models (MIND, TotalSegmentator, MRSegmentator) — so cross-modality pairs align while the deformation stays smooth and physically plausible.

Each preset is a self-contained KonfAI app: on the fixed grid it produces the moving image resampled onto the fixed image (MovedImage) and the DisplacementField. Presets can be ensembled (their displacement fields are averaged into one transform).

🧩 Presets

Preset	Pair	Engine	Description
Generic_Rigid	any	elastix	Rigid alignment (mutual information, multi-resolution)
Generic_Rigid_BSpline	any	elastix	Rigid, then B-spline deformable refinement
MR_CT_HeadNeck	MR/CT	elastix + IMPACT	MR/CT head & neck preset
MR_CT_TS	MR/CT	elastix + IMPACT	MR/CT with MIND + TotalSegmentator features
MR_CT_MRSeg	MR/CT	elastix + IMPACT	MR/CT with MIND + MRSegmentator features
CBCT_CT_HeadNeck	CBCT/CT	elastix + IMPACT	CBCT/CT head & neck preset
CBCT_CT_TS	CBCT/CT	elastix + IMPACT	CBCT/CT with TotalSegmentator features
CBCT_CT_MRSeg	CBCT/CT	elastix + IMPACT	CBCT/CT with MRSegmentator features
ConvexAdam_Coarse	any	itk-impact (native)	Global coarse coupled-convex init (IMPACT/MIND)
ConvexAdam_Fine	any	itk-impact (native)	Adam instance-optimisation (tileable; expects a pre-aligned start)
ConvexAdam_Composite	any	itk-impact (native)	Coarse + fine ConvexAdam in one app (IMPACT/MIND)

Inputs: Fixed, Moving, and optional FixedMask / MovingMask (restrict the metric region).

🚀 Usage

pip install impact-reg-konfai
# Register a moving image onto a fixed image (ensemble several presets by listing them):
impact-reg-konfai register ConvexAdam_Composite -f fixed.nii.gz -m moving.nii.gz -o ./Output --gpu 0

• Generic runner (single preset): konfai-apps infer VBoussot/ImpactReg:ConvexAdam_Composite -i fixed.nii.gz -i moving.nii.gz -o output/
• Interactive: SlicerImpactReg — a 3D Slicer extension driving these presets.

The ConvexAdam_* presets depend on itk-impact; resolving the app installs it automatically (it reuses your existing PyTorch, CPU or GPU).

⚡ Performance & VRAM

ConvexAdam presets (native, GPU) benchmarked on an NVIDIA RTX PRO 5000 (24 GB) with a real abdomen MR→CT pair, 222 × 226 × 124 @ 2 mm (single pass, no TTA):

Preset	Stages	Time / case	Peak VRAM
ConvexAdam_Fine	fine (150 Adam iters)	≈ 0.5 s	~2.1 GB
ConvexAdam_Coarse	linear + coarse	≈ 4.6 s	~2.1 GB
ConvexAdam_Composite	linear + coarse + fine	≈ 5.1 s	~2.1 GB

Per-stage breakdown: linear pre-align ≈ 4.2 s (ITK affine, MI) · coarse ≈ 0.4 s · fine ≈ 0.5 s. One-time TorchScript feature-model load ≈ 7 s (amortised across a batch). Times scale with case size; --tta k multiplies runtime. The elastix + IMPACT presets run through elastix and scale differently.

🔗 Links & Citation

• 🧠 KonfAI: github.com/vboussot/KonfAI
• 📦 PyPI: impact_reg_konfai
• 🩻 Slicer: SlicerImpactReg
• 📄 Paper: KonfAI — arXiv:2508.09823