language:
- en
license: apache-2.0
library_name: atommic
datasets:
- fastMRIBrainsMulticoil
thumbnail: null
tags:
- image-reconstruction
- KIKINet
- ATOMMIC
- pytorch
model-index:
- name: >-
REC_KIKINet_fastMRIBrainsMulticoil_equispaced_4x_8x_GDCC_1_coil_NNEstimationCSM
results: []
Model Overview
KIKINet 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
pretrained: true
checkpoint: https://huggingface.co/wdika/REC_KIKINet_fastMRIBrainsMulticoil_equispaced_4x_8x_GDCC_1_coil_NNEstimationCSM/blob/main/REC_KIKINet_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
model:
model_name: KIKINet
num_iter: 2
kspace_model_architecture: UNET
kspace_in_channels: 2
kspace_out_channels: 2
kspace_unet_num_filters: 16
kspace_unet_num_pool_layers: 2
kspace_unet_dropout_probability: 0.0
kspace_unet_padding_size: 11
kspace_unet_normalize: true
imspace_model_architecture: UNET
imspace_in_channels: 2
imspace_unet_num_filters: 16
imspace_unet_num_pool_layers: 2
imspace_unet_dropout_probability: 0.0
imspace_unet_padding_size: 11
imspace_unet_normalize: true
dimensionality: 2
reconstruction_loss:
l1: 0.1
ssim: 0.9
estimate_coil_sensitivity_maps_with_nn: true
Training
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 = 0.00109 +/- 0.003836 NMSE = 0.02942 +/- 0.08896 PSNR = 31.02 +/- 5.678 SSIM = 0.8556 +/- 0.2009
8x: MSE = 0.002183 +/- 0.005025 NMSE = 0.05946 +/- 0.1484 PSNR = 27.78 +/- 5.821 SSIM = 0.8049 +/- 0.2074
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.