---
language:
- en
license: apache-2.0
library_name: atommic
datasets:
- fastMRIBrainsMulticoil
thumbnail: null
tags:
- image-reconstruction
- XPDNet
- ATOMMIC
- pytorch
model-index:
- name: REC_XPDNet_fastMRIBrainsMulticoil_equispaced_4x_8x_GDCC_1_coil_NNEstimationCSM
  results: []

---


## Model Overview

XPDNet for 4x & 8x accelerated MRI Reconstruction on the fastMRIBrainsMulticoil dataset.


## ATOMMIC: Training

To train, fine-tune, or test the model you will need to install [ATOMMIC](https://github.com/wdika/atommic). We recommend you install it after you've installed latest Pytorch version.
```
pip install atommic['all']
```

## How to Use this Model

The model is available for use in ATOMMIC, and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.

Corresponding configuration YAML files can be found [here](https://github.com/wdika/atommic/tree/main/projects/REC/fastMRIBrainsMulticoil/conf).

### Automatically instantiate the model

```base
pretrained: true
checkpoint: https://huggingface.co/wdika/REC_XPDNet_fastMRIBrainsMulticoil_equispaced_4x_8x_GDCC_1_coil_NNEstimationCSM/blob/main/REC_XPDNet_fastMRIBrainsMulticoil_equispaced_4x_8x_GDCC_1_coil_NNEstimationCSM.atommic
mode: test
```

### Usage

You need to download the fastMRI Brains dataset to effectively use this model. Check the [fastMRIBrainsMulticoil](https://github.com/wdika/atommic/blob/main/projects/REC/fastMRIBrainsMulticoil/README.md) page for more information.


## Model Architecture
```base
model:
  model_name: XPDNet
  num_primal: 5
  num_dual: 1
  num_iter: 10
  use_primal_only: true
  kspace_model_architecture: CONV
  kspace_in_channels: 2
  kspace_out_channels: 2
  dual_conv_hidden_channels: 16
  dual_conv_num_dubs: 2
  dual_conv_batchnorm: false
  image_model_architecture: MWCNN
  imspace_in_channels: 2
  imspace_out_channels: 2
  mwcnn_hidden_channels: 16
  mwcnn_num_scales: 0
  mwcnn_bias: true
  mwcnn_batchnorm: false
  normalize_image: true
  dimensionality: 2
  reconstruction_loss:
    l1: 0.1
    ssim: 0.9
  estimate_coil_sensitivity_maps_with_nn: true
```

## Training
```base
  optim:
    name: adam
    lr: 1e-4
    betas:
      - 0.9
      - 0.999
    weight_decay: 0.0
    sched:
        name: InverseSquareRootAnnealing
        min_lr: 0.0
        last_epoch: -1
        warmup_ratio: 0.1

trainer:
  strategy: ddp_find_unused_parameters_false
  accelerator: gpu
  devices: 1
  num_nodes: 1
  max_epochs: 20
  precision: 16-mixed
  enable_checkpointing: false
  logger: false
  log_every_n_steps: 50
  check_val_every_n_epoch: -1
  max_steps: -1
```

## Performance

To compute the targets using the raw k-space and the chosen coil combination method, accompanied with the chosen coil sensitivity maps estimation method, you can use [targets](https://github.com/wdika/atommic/tree/main/projects/REC/fastMRIBrainsMulticoil/conf/targets) configuration files.

Evaluation can be performed using the [evaluation](https://github.com/wdika/atommic/blob/main/tools/evaluation/reconstruction.py) script for the reconstruction task, with --evaluation_type per_slice.

Results
-------

Evaluation against RSS targets
------------------------------
4x: MSE = 0.001292 +/- 0.006735 NMSE = 0.03317 +/- 0.1122 PSNR = 31.03 +/- 6.749 SSIM = 0.8543 +/- 0.2115

8x: MSE = 0.002671 +/- 0.00606 NMSE = 0.07137 +/- 0.1499 PSNR = 26.96 +/- 6.179 SSIM = 0.7881 +/- 0.2177


## Limitations

This model was trained on the fastMRIBrainsMulticoil batch0 dataset using a UNet coil sensitivity maps estimation and Geometric Decomposition Coil-Compressions to 1-coil, and might differ from the results reported on the challenge leaderboard.


## References

[1] [ATOMMIC](https://github.com/wdika/atommic)

[2] Muckley MJ, Riemenschneider B, Radmanesh A, Kim S, Jeong G, Ko J, Jun Y, Shin H, Hwang D, Mostapha M, Arberet S, Nickel D, Ramzi Z, Ciuciu P, Starck JL, Teuwen J, Karkalousos D, Zhang C, Sriram A, Huang Z, Yakubova N, Lui YW, Knoll F. Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction. IEEE Trans Med Imaging. 2021 Sep;40(9):2306-2317. doi: 10.1109/TMI.2021.3075856. Epub 2021 Aug 31. PMID: 33929957; PMCID: PMC8428775.