🧠 TorchScript Models for the IMPACT Semantic Similarity Metric
This repository provides a collection of TorchScript-exported pretrained models designed for use with the IMPACT similarity metric, enabling semantic medical image registration through feature-level comparison.
The IMPACT metric is introduced in the following preprint, currently under review:
IMPACT: A Generic Semantic Loss for Multimodal Medical Image Registration
V. Boussot, C. Hémon, J.-C. Nunes, J. Dowling, S. Rouzé, C. Lafond, A. Barateau, J.-L. Dillenseger
arXiv:2503.24121 [cs.CV]
🔧 The full implementation of IMPACT, along with its integration into the Elastix framework, is available in the repository:
➡️ github.com/vboussot/ImpactLoss
This repository also includes example parameter maps, TorchScript model handling utilities, and a ready-to-use Docker environment for quick experimentation and reproducibility.
📚 Pretrained Model
The TorchScript models provided in this repository were exported from publicly available pretrained networks. These include:
- TotalSegmentator (TS) — U-Net models trained for full-body anatomical segmentation
- Segment Anything 2.1 (SAM2.1) — Foundation model for segmentation on natural images
- DINOv2 — Self-supervised vision transformer trained on diverse datasets
- Anatomix — Transformer-based model with anatomical priors for medical images
Each model provides multiple feature extraction layers, which can be selected independently using the corresponding model l_Layers. This can be configured through the LayerMask parameter in the IMPACT configuration.
In addition, the repository also includes:
- MIND — A handcrafted descriptor, wrapped in TorchScript
| Model | Specialization | Paper / Reference | Field of View | License | Preprocessing |
|---|---|---|---|---|---|
| MIND | Handcrafted descriptor | Heinrich et al., 2012 | 2*r*d + 1 (r: radius, d: dilation) |
Apache 2.0 | None |
| SAM2.1 | General segmentation (natural images) | Ravi et al., 2023 | 29 | Apache 2.0 | Normalize intensities to [0, 1], then standardize with mean 0.485 and std 0.229 |
| TS Models | CT/MRI segmentation | Wasserthal et al., 2022 | 2^l + 3 (l: layer number) |
Apache 2.0 | Canonical orientation for all models. For MRI models (e.g., TS/M730–M733), standardize intensities to zero mean and unit variance. For CT models (e.g., TS/M258, TS/M291), clip intensities to [-1024, 276] HU, then normalize by centering at -370 HU and scaling by 436.6. |
| Anatomix | Anatomy-aware transformer encoder | Dey et al., 2024 | Global(Static mode) | MIT | Normalize intensities to [0, 1] |
| DINOv2 | Self-supervised vision transformer | Oquab et al., 2023 | 14 | Apache 2.0 | Normalize intensities to [0, 1], then standardize with mean 0.485 and std 0.229 |
🔍 TS Model Variants
TS Models refer to the following TotalSegmentator-derived TorchScript models:M258, M291, M293, M294, M295, M297, M298, M730, M731, M732, M733, M850, M851
Each model is specialized for a specific anatomical structure or resolution (e.g., 3mm / 6mm) and shares the same encoder-decoder architecture.