impact-synth-konfai 1.4.7

Fast and lightweight CLI for synthetic CT generation using IMPACT-Synth models within the KonfAI framework.

IMPACT-Synth-KonfAI

Fast and lightweight CLI for synthetic CT generation using IMPACT-Synth models within the KonfAI framework.

---

🧩 Overview

IMPACT-Synth-KonfAI is the command-line interface (CLI) for performing inference and uncertainty estimation with the IMPACT-Synth models.
It provides a streamlined way to generate synthetic CT (sCT) images from MR or CBCT scans, leveraging the KonfAI framework for efficient inference, test-time augmentation (TTA), model ensembling, and uncertainty quantification.

The underlying IMPACT-Synth models are a family of supervised convolutional neural networks (CNNs) dedicated to sCT generation. They build upon the research presented in “Why Registration Quality Matters: Enhancing sCT Synthesis with IMPACT-Based Registration” (Boussot et al., 2025).
These models are trained on carefully aligned MR–CT pairs, where alignment is optimized through the IMPACT-Reg loss to minimize spatial bias. Their training further integrates the IMPACT-Synth loss, a perceptual loss derived from semantic representations of segmentation networks. Together, precise spatial alignment and semantic perceptual supervision reinforce anatomical fidelity and realistic tissue contrast in the synthesized CT images.

The official IMPACT-Synth models are available on Hugging Face and can be executed directly through this CLI.

---

🚀 Installation

From PyPI:

python -m pip install impact-synth-konfai

From source:

git clone https://github.com/vboussot/KonfAI.git
python -m pip install -e apps/impact_synth

---

⚙️ Usage

Perform image-to-sCT synthesis:

impact-synth-konfai MR -i path/to/input.nii.gz -o ./Output/

Optional arguments

Flag	Description	Default
MODEL	Input modality / model name on Hugging Face	MR or CBCT
-i, --input	Path to the input file	required
-o, --output	Path to save the synthetic CT	./Output/
--gt	Path to reference CT (ground truth), if available (enables evaluation workflows)	unset
--mask	Path to region-of-interest mask used for evaluation and uncertainty analysis	unset
--tta	Number of test-time augmentations (TTA)	2
--ensemble	Number of models to ensemble	5
--mc_dropout	Monte Carlo dropout samples for uncertainty	1
-uncertainty	Save uncertainty maps	False
--gpu	GPU list (e.g. 0 or 0,1)	CPU if unset
--cpu	Number of CPU cores (if no GPU)	1
-q, --quiet	Suppress console output	False

Example

impact-synth-konfai CBCT -i patient01.nii.gz -o patient01 --gpu 0 --tta 2 --ensemble 5 -uncertainty

---

🧠 Features

• ⚡ Fast inference powered by KonfAI
• 🤗 Automatic model download from Hugging Face
• 🧩 Multi-model ensembling and test-time augmentation (TTA)
• 🧠 Supports evaluation workflows with reference data, and uncertainty estimation without reference
• 🧾 Multi-format compatibility: supports all major medical image formats handled by ITK

---

📚 References

If you use IMPACT-Synth-KonfAI in your work, please cite:

• Boussot, V., Hémon, C., Nunes, J.-C., & Dillenseger, J.-L. (2025).
  Why Registration Quality Matters: Enhancing sCT Synthesis with IMPACT-Based Registration.
  arXiv preprint arXiv:2510.21358

• Boussot, V., & Dillenseger, J.-L. (2025).
  KonfAI: A Modular and Fully Configurable Framework for Deep Learning in Medical Imaging.
  arXiv preprint arXiv:2508.09823

---

🔗 Links

• 🤗 Model Hub: huggingface.co/VBoussot/IMPACT-Synth
• 📦 PyPI Package: pypi.org/project/impact_synth_konfai

---