---
language:
- en
license: apache-2.0
library_name: atommic
datasets:
- SKMTEA
thumbnail: null
tags:
- multitask-image-reconstruction-image-segmentation
- MTLRS
- ATOMMIC
- pytorch
model-index:
- name: MTL_MTLRS_SKMTEA_poisson2d_4x
  results: []

---


## Model Overview

ulti-Task Learning for MRI Reconstruction and Segmentation (MTLRS) 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/MTL/rs/SKMTEA/conf).

### Automatically instantiate the model

```base
pretrained: true
checkpoint: https://huggingface.co/wdika/MTL_MTLRS_SKMTEA_poisson2d_4x/blob/main/MTL_MTLRS_SKMTEA_poisson2d_4x.atommic
mode: test
```

### Usage

You need to download the SKMTEA dataset to effectively use this model. Check the [SKMTEA](https://github.com/wdika/atommic/blob/main/projects/MTL/rs/SKMTEA/README.md) page for more information.


## Model Architecture
```base
model:
  model_name: MTLRS
  joint_reconstruction_segmentation_module_cascades: 5
  task_adaption_type: multi_task_learning
  use_reconstruction_module: true
  reconstruction_module_recurrent_layer: IndRNN
  reconstruction_module_conv_filters:
    - 64
    - 64
    - 2
  reconstruction_module_conv_kernels:
    - 5
    - 3
    - 3
  reconstruction_module_conv_dilations:
    - 1
    - 2
    - 1
  reconstruction_module_conv_bias:
    - true
    - true
    - false
  reconstruction_module_recurrent_filters:
    - 64
    - 64
    - 0
  reconstruction_module_recurrent_kernels:
    - 1
    - 1
    - 0
  reconstruction_module_recurrent_dilations:
    - 1
    - 1
    - 0
  reconstruction_module_recurrent_bias:
    - true
    - true
    - false
  reconstruction_module_depth: 2
  reconstruction_module_time_steps: 8
  reconstruction_module_conv_dim: 2
  reconstruction_module_num_cascades: 1
  reconstruction_module_dimensionality: 2
  reconstruction_module_no_dc: true
  reconstruction_module_keep_prediction: true
  reconstruction_module_accumulate_predictions: true
  segmentation_module: AttentionUNet
  segmentation_module_input_channels: 1
  segmentation_module_output_channels: 4
  segmentation_module_channels: 64
  segmentation_module_pooling_layers: 2
  segmentation_module_dropout: 0.0
  segmentation_loss:
    dice: 1.0
  dice_loss_include_background: true  # always set to true if the background is removed
  dice_loss_to_onehot_y: false
  dice_loss_sigmoid: false
  dice_loss_softmax: false
  dice_loss_other_act: none
  dice_loss_squared_pred: false
  dice_loss_jaccard: false
  dice_loss_flatten: false
  dice_loss_reduction: mean_batch
  dice_loss_smooth_nr: 1e-5
  dice_loss_smooth_dr: 1e-5
  dice_loss_batch: true
  dice_metric_include_background: true  # always set to true if the background is removed
  dice_metric_to_onehot_y: false
  dice_metric_sigmoid: false
  dice_metric_softmax: false
  dice_metric_other_act: none
  dice_metric_squared_pred: false
  dice_metric_jaccard: false
  dice_metric_flatten: false
  dice_metric_reduction: mean_batch
  dice_metric_smooth_nr: 1e-5
  dice_metric_smooth_dr: 1e-5
  dice_metric_batch: true
  segmentation_classes_thresholds: [0.5, 0.5, 0.5, 0.5]
  segmentation_activation: sigmoid
  reconstruction_loss:
    l1: 1.0
  kspace_reconstruction_loss: false
  total_reconstruction_loss_weight: 0.5
  total_segmentation_loss_weight: 0.5
```

## 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
  accelerator: gpu
  devices: 1
  num_nodes: 1
  max_epochs: 10
  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/MTL/rs/SKMTEA/conf/targets) configuration files.

Evaluation can be performed using the reconstruction [evaluation](https://github.com/wdika/atommic/blob/main/tools/evaluation/reconstruction.py) and [segmentation](https://github.com/wdika/atommic/blob/main/tools/evaluation/segmentation.py) scripts for the reconstruction and the segmentation tasks, with --evaluation_type per_slice.

Results
-------

Evaluation against SENSE targets
--------------------------------
4x: MSE = 0.001105 +/- 0.001758 NMSE = 0.0211 +/- 0.02706 PSNR = 30.48 +/- 5.296 SSIM = 0.8324 +/- 0.1064 DICE = 0.8889 +/- 0.1177 F1 = 0.2471 +/- 0.203 HD95 = 7.594 +/- 3.673 IOU = 0.2182 +/- 0.1944


## Limitations

This model was trained on the SKM-TEA dataset for 4x accelerated MRI reconstruction and MRI segmentation with MultiTask Learning (MTL) of the axial plane.


## References

[1] [ATOMMIC](https://github.com/wdika/atommic)

[2] Desai AD, Schmidt AM, Rubin EB, et al. SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation. 2022