|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
library_name: atommic |
|
datasets: |
|
- CC359 |
|
thumbnail: null |
|
tags: |
|
- image-reconstruction |
|
- VSNet |
|
- ATOMMIC |
|
- pytorch |
|
model-index: |
|
- name: REC_VSNet_CC359_12_channel_poisson2d_5x_10x_NNEstimationCSM |
|
results: [] |
|
|
|
--- |
|
|
|
|
|
## Model Overview |
|
|
|
Variable-Splitting Net (VSNet) for 5x & 10x accelerated MRI Reconstruction on the CC359 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/CC359/conf). |
|
|
|
### Automatically instantiate the model |
|
|
|
```base |
|
pretrained: true |
|
checkpoint: https://huggingface.co/wdika/REC_VSNet_CC359_12_channel_poisson2d_5x_10x_NNEstimationCSM/blob/main/REC_VSNet_CC359_12_channel_poisson2d_5x_10x_NNEstimationCSM.atommic |
|
mode: test |
|
``` |
|
|
|
### Usage |
|
|
|
You need to download the CC359 dataset to effectively use this model. Check the [CC359](https://github.com/wdika/atommic/blob/main/projects/REC/CC359/README.md) page for more information. |
|
|
|
|
|
## Model Architecture |
|
```base |
|
model: |
|
model_name: VSNet |
|
num_cascades: 10 |
|
imspace_model_architecture: CONV |
|
imspace_in_channels: 2 |
|
imspace_out_channels: 2 |
|
imspace_conv_hidden_channels: 64 |
|
imspace_conv_n_convs: 4 |
|
imspace_conv_batchnorm: false |
|
dimensionality: 2 |
|
reconstruction_loss: |
|
l1: 0.1 |
|
ssim: 0.9 |
|
estimate_coil_sensitivity_maps_with_nn: true |
|
``` |
|
|
|
## Training |
|
```base |
|
optim: |
|
name: adamw |
|
lr: 1e-4 |
|
betas: |
|
- 0.9 |
|
- 0.999 |
|
weight_decay: 0.0 |
|
sched: |
|
name: CosineAnnealing |
|
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/CC359/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 |
|
------------------------------ |
|
5x: MSE = 0.003044 +/- 0.002908 NMSE = 0.04603 +/- 0.04055 PSNR = 25.51 +/- 3.913 SSIM = 0.788 +/- 0.0789 |
|
|
|
10x: MSE = 0.00402 +/- 0.003273 NMSE = 0.06327 +/- 0.06061 PSNR = 24.19 +/- 3.266 SSIM = 0.74 +/- 0.08881 |
|
|
|
|
|
## Limitations |
|
|
|
This model was trained on the CC359 using a UNet coil sensitivity maps estimation and might differ from the results reported on the challenge leaderboard. |
|
|
|
|
|
## References |
|
|
|
[1] [ATOMMIC](https://github.com/wdika/atommic) |
|
|
|
[2] Beauferris, Y., Teuwen, J., Karkalousos, D., Moriakov, N., Caan, M., Yiasemis, G., Rodrigues, L., Lopes, A., Pedrini, H., Rittner, L., Dannecker, M., Studenyak, V., Gröger, F., Vyas, D., Faghih-Roohi, S., Kumar Jethi, A., Chandra Raju, J., Sivaprakasam, M., Lasby, M., … Souza, R. (2022). Multi-Coil MRI Reconstruction Challenge—Assessing Brain MRI Reconstruction Models and Their Generalizability to Varying Coil Configurations. Frontiers in Neuroscience, 16. https://doi.org/10.3389/fnins.2022.919186 |
