You can deploy this model and start earning money today!

wdika/
REC_RVN_fastMRIBrainsMulticoil_equispaced_4x_8x_GDCC_1_coil_NNEstimationCSM

Name: REC_RVN_fastMRIBrainsMulticoil_equispaced_4x_8x_GDCC_1_coil_NNEstimationCSM
Availability: InStock

fastMRIBrainsMulticoil

apache-2.0

Views

No views yet

Model Overview

Recurrent Variational Network (RVN) 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. 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.

Automatically instantiate the model

base

pretrained: true
checkpoint: https://huggingface.co/wdika/REC_RVN_fastMRIBrainsMulticoil_equispaced_4x_8x_GDCC_1_coil_NNEstimationCSM/blob/main/REC_RVN_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 page for more information.

Model Architecture

base

model:
  model_name: RVN
  in_channels: 2
  recurrent_hidden_channels: 64
  recurrent_num_layers: 4
  num_steps: 8
  no_parameter_sharing: true
  learned_initializer: true
  initializer_initialization: "sense"
  initializer_channels:
    - 32
    - 32
    - 64
    - 64
  initializer_dilations:
    - 1
    - 1
    - 2
    - 4
  initializer_multiscale: 1
  accumulate_predictions: false
  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 configuration files.

Evaluation can be performed using the evaluation script for the reconstruction task, with --evaluation_type per_slice.

Results

Evaluation against RSS targets

4x: MSE = 0.0005725 +/- 0.002891 NMSE = 0.0151 +/- 0.05895 PSNR = 34.23 +/- 5.967 SSIM = 0.8935 +/- 0.1797

8x: MSE = 0.001295 +/- 0.003645 NMSE = 0.0334 +/- 0.08907 PSNR = 30.08 +/- 5.678 SSIM = 0.8434 +/- 0.1949

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

[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.