/3d-mri-brain-tumor-segmentation-using-autoencoder-regularization

Keras implementation of the paper "3D MRI brain tumor segmentation using autoencoder regularization" by Myronenko A. (https://arxiv.org/abs/1810.11654).

Primary LanguagePython

3D MRI Brain Tumor Segmentation Using Autoencoder Regularization

PWC Keras

The model architecture

The Model Architecture
Source: https://arxiv.org/pdf/1810.11654.pdf

Keras implementation of the paper 3D MRI brain tumor segmentation using autoencoder regularization by Myronenko A. (https://arxiv.org/abs/1810.11654). The author (team name: NVDLMED) ranked #1 on the BraTS 2018 leaderboard using the model described in the paper.

This repository contains the model complete with the loss function, all implemented end-to-end in Keras. The usage is described in the next section.

Usage

  1. Download the file model.py and keep in the same folder as your project notebook/script.

  2. In your python script, import build_model function from model.py.

    from model import build_model

    It will automatically download an additional script needed for the implementation, group_norm.py, which contains keras implementation for the group normalization layer.

  3. Note that the input MRI scans you are going to feed need to have 4 dimensions, with channels-first format. i.e., the shape should look like (c, H, W, D), where:

  • c, the no.of channels are divisible by 4.
  • H, W, D, which are height, width and depth, respectively, are all divisible by 24, i.e., 16. This is to get correct output shape according to the model.

  1. Now to create the model, simply run:

    model = build_model(input_shape, output_channels)

    where, input_shape is a 4-tuple (channels, Height, Width, Depth) and output_channels is the no. of channels in the output of the model. The output of the model will be the segmentation map generated by the model with the shape (output_channels, Height, Width, Depth), where Height, Width and Depth will same as that of the input.

Issues

If you encounter any issue or have a feedback, don't hesitate to raise an issue.

Updates

  • Added a minus term before loss_dice in the loss function. From discussion in #7 with @woodywff and @doc78.
  • Thanks to @doc78 , the NaN loss problem has been permanently fixed.
  • The NaN loss problem has now been fixed (clipping the activations for now).
  • Added an argument in the build_model function to allow for different no. of channels in the output.