Model Overview
Cascades of Independently Recurrent Inference Machines (CIRIM) for 12x accelerated MRI Reconstruction on the AHEAD 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_CIRIM_AHEAD_gaussian2d_12x/blob/main/REC_CIRIM_AHEAD_gaussian2d_12x.atommic
mode: test
Usage
You need to download the AHEAD dataset to effectively use this model. Check the AHEAD page for more information.
Model Architecture
model:
model_name: CIRIM
recurrent_layer: IndRNN
conv_filters:
- 64
- 64
- 2
conv_kernels:
- 5
- 3
- 3
conv_dilations:
- 1
- 2
- 1
conv_bias:
- true
- true
- false
recurrent_filters:
- 64
- 64
- 0
recurrent_kernels:
- 1
- 1
- 0
recurrent_dilations:
- 1
- 1
- 0
recurrent_bias:
- true
- true
- false
depth: 2
time_steps: 8
conv_dim: 2
num_cascades: 5
no_dc: true
keep_prediction: true
accumulate_predictions: true
dimensionality: 2
num_echoes: 4
reconstruction_loss:
ssim: 1.0
Training
optim:
name: adamw
lr: 1e-4
betas:
- 0.9
- 0.999
weight_decay: 0.0
sched:
name: PolynomialHoldDecayAnnealing
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 SENSE targets
12x: MSE = 0.0009594 +/- 0.003039 NMSE = 0.04406 +/- 0.07482 PSNR = 32.89 +/- 8.596 SSIM = 0.909 +/- 0.08273
Limitations
This model was trained on very few subjects on the AHEAD dataset. It is not guaranteed to generalize to other datasets.
References
[1] ATOMMIC
[2] Alkemade A, Mulder MJ, Groot JM, et al. The Amsterdam Ultra-high field adult lifespan database (AHEAD): A freely available multimodal 7 Tesla submillimeter magnetic resonance imaging database. NeuroImage 2020;221.