Skip to content

multimodallearning/PrIINeR

Repository files navigation

PrIINeR: Towards Prior-Informed Implicit Neural Representations for Accelerated MRI

This repository contains the official PyTorch implementation of our BMVC 2025 paper:
"PrIINeR: Towards Prior-Informed Implicit Neural Representations for Accelerated MRI"
Ziad Al-Haj Hemidi, Eytan Kats, Mattias P. Heinrich
📍 To appear at British Machine Vision Conference (BMVC) 2025, Sheffield, UK


🧠 Abstract

Acceleration in Magnetic Resonance Imaging (MRI) is essential to reduce acquisition time but typically degrades image quality due to undersampling artifacts. Implicit Neural Representations (INRs) have recently emerged as a promising instance-specific alternative for image reconstruction. However, their performance deteriorates under high acceleration factors due to limited structural priors and a lack of generalizability.

PrIINeR addresses this limitation by integrating population-level prior knowledge from pre-trained deep learning models into the INR-based reconstruction process. Specifically, we propose a hybrid framework that performs instance-specific INR optimization, guided by global anatomical priors, while enforcing dual data consistency with both the acquired k-space and prior-based reconstructions. The proposed approach significantly improves structural fidelity, reduces artifacts, and outperforms existing INR-based baselines on the NYU fastMRI dataset.

Method overview


🧬 Methodology

The PrIINeR framework consists of three key components:

  1. Prior-Guided Supervision: Incorporation of deep priors extracted from pre-trained models (e.g., UNet, Transformer-based, or generative INR models).
  2. Instance-Level INR Optimization: An implicit network parameterized over spatial coordinates and optimized per subject using only the undersampled k-space and deep priors if available.
  3. Dual Data Consistency Constraints: Enforced both in the k-space domain of the acquired measurements and the deep prior-based reconstructions, promoting reconstructions with high structural fidelity and reduced artifacts.

This formulation allows PrIINeR to act as a plug-and-play framework with interchangeable priors, adaptable across different prior architectures and acceleration scenarios.


📁 Repository Structure

.
├── create_env.sh                 # Environment setup script
├── data/                         # Example k-space file
│   └── kspace_knee_slice.h5
├── models/                       # Pre-trained prior models
│   ├── unet.pth
│   ├── genINR.pth
│   └── reconFormer.pth
├── src/                          # Core implementation
│   ├── priiner.py
│   ├── genINR.py
│   ├── Recurrent_Transformer.py
│   ├── RS_attention.py
│   ├── configs.py
│   └── utils.py
├── run_piiner_no_prior.py       # INR-only baseline
├── run_piiner_unet.py           # UNet-based prior integration
├── run_piiner_genINR.py         # genINR-based prior integration
├── run_piiner_reconFormer.py    # Transformer-based prior integration
└── README.md

⚙️ Installation

We recommend using Mamba for faster dependency resolution. To set up the environment:

# Clone the repository
git clone https://github.com/multimodallearning/PrIINeR.git
# Navigate to the repository
cd PrIINeR
# Create and activate the environment
bash create_env.sh

This script will create a new environment named priiner and install all required packages.

Dependencies • Python ≥ 3.11 • PyTorch • MONAI • torchmetrics • timm • tinycudann (requires an NVIDIA GPU with CUDA support)

💡 If you don’t have mamba, replace mamba with conda in the script.


🧪 Usage

We provide four scripts corresponding to different variants of the PrIINeR reconstruction method. Choose according to whether or not prior models are used:

🔹 INR-only baseline (no prior)

python run_piiner_no_prior.py

🔹 UNet-based prior

python run_piiner_unet.py

🔹 Generative INR-based prior

python run_piiner_genINR.py

🔹 Transformer-based prior (ReconFormer)

python run_piiner_reconFormer.py

Each script will: • Load the undersampled k-space slice. • Instantiate the INR and (if applicable) the prior model. • Optimize the INR with dual constraints. • Save reconstructed images and performance metrics.


📜 Citation

If you use this work in your research, please cite:

@inproceedings{priiner2025,
  title     = {PrIINeR: Towards Prior-Informed Implicit Neural Representations for Accelerated MRI},
  author    = {Ziad Al-Haj Hemidi and Eytan Kats and Mattias P. Heinrich},
  booktitle = {British Machine Vision Conference (BMVC)},
  year      = {2025}
}

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.


✉️ Contact

For questions or collaborations, please contact:

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published