|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
library_name: atommic |
|
datasets: |
|
- AHEAD |
|
thumbnail: null |
|
tags: |
|
- quantitative-mri-mapping |
|
- qVarNet |
|
- ATOMMIC |
|
- pytorch |
|
model-index: |
|
- name: QMRI_qVarNet_AHEAD_gaussian2d_12x |
|
results: [] |
|
|
|
--- |
|
|
|
|
|
## Model Overview |
|
|
|
quantitative Variational Network (qVarNet) for 12x accelerated quantitative MRI mapping of R2*, S0, B0, phi maps on the AHEAD 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/qMRI/AHEAD/conf). |
|
|
|
|
|
### Automatically instantiate the model |
|
|
|
```base |
|
pretrained: true |
|
checkpoint: https://huggingface.co/wdika/QMRI_qVarNet_AHEAD_gaussian2d_12x/blob/main/QMRI_qVarNet_AHEAD_gaussian2d_12x.atommic |
|
mode: test |
|
``` |
|
|
|
### Usage |
|
|
|
You need to download the AHEAD dataset to effectively use this model. Check the [AHEAD](https://github.com/wdika/atommic/blob/main/projects/qMRI/AHEAD/README.md) page for more information. |
|
|
|
|
|
## Model Architecture |
|
```base |
|
model: |
|
model_name: qVN |
|
use_reconstruction_module: false |
|
quantitative_module_num_cascades: 8 |
|
quantitative_module_channels: 18 |
|
quantitative_module_pooling_layers: 4 |
|
quantitative_module_in_channels: 8 |
|
quantitative_module_out_channels: 8 |
|
quantitative_module_padding_size: 11 |
|
quantitative_module_normalize: true |
|
quantitative_module_no_dc: false |
|
quantitative_module_signal_forward_model_sequence: MEGRE |
|
quantitative_module_dimensionality: 2 |
|
quantitative_maps_scaling_factor: 1e-3 |
|
quantitative_maps_regularization_factors: |
|
- 150.0 |
|
- 150.0 |
|
- 1000.0 |
|
- 150.0 |
|
quantitative_loss: |
|
ssim: 1.0 |
|
kspace_quantitative_loss: false |
|
total_quantitative_loss_weight: 1.0 # balance between reconstruction and quantitative loss |
|
quantitative_parameters_regularization_factors: |
|
- R2star: 1.0 |
|
- S0: 1.0 |
|
- B0: 1.0 |
|
- phi: 1.0 |
|
``` |
|
|
|
## Training |
|
```base |
|
optim: |
|
name: adam |
|
lr: 1e-4 |
|
betas: |
|
- 0.9 |
|
- 0.98 |
|
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/qMRI/AHEAD/conf/targets) configuration files. |
|
|
|
Evaluation can be performed using the [evaluation](https://github.com/wdika/atommic/blob/main/tools/evaluation/qmapping.py) script for the qmri task, with --evaluation_type per_slice. |
|
|
|
Results |
|
------- |
|
|
|
Evaluation against R2*, S0, B0, phi targets |
|
------------------------------------------- |
|
12x: MSE = 0.005571 +/- 0.02725 NMSE = 0.192 +/- 0.3344 PSNR = 24.36 +/- 7.791 SSIM = 0.7838 +/- 0.2059 |
|
|
|
|
|
## 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](https://github.com/wdika/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. |
