A Tensorflow implementation of SegNet to segments CMR images
- Switched to using the SELU activation function - no more batch norm and is_training hassle - a self-normalising neural network!!!!
- To support the above - input images are rescaled from -1 to 1: (2/255.0) * image - 1.
- Now updates the results more often and saves the checkpoint less often - this is faster. Also, doesn't flush the results after every write.
- A demonstration of a more complete Tensorflow program including saving state and resuming.
- Provide an ready-to-go example of medical segmentation with sufficient training and validation data, in a usable format (PNGs).
You must have a GPU and install the tensorflow-gpu version as the cpu version does not have tf.nn.max_pool_with_argmax()
- Python >=3.6: Best to use the Conda distribution
- tensorflow-gpu >=0.11
- Add code to run on your own data (currently there is only the training code present)
Make sure you have conda and tensorflow installed
conda install tensorflow-gpu
python
Python 3.6.1 | packaged by conda-forge | (default, Sep 8 2016, 14:36:38)
The git clone this repository
git clone https://github.com/mshunshin/SegNetCMR.git
And start the training from the folder
cd /path/to/SegNetCMR
python train.py
And in another terminal window start tensorboard
tensorboard --logdir ./Output
Then in your webbrowser go to http://localhost:6006
Many thanks to the Sunnybrook Health Sciences Centre for providing a set of CMR data with associated contours. Unfortunately, in the latest release the filenames have become a little mangled, and don't match up with the contours. I have gone through the files and matched them up; exported the DICOMS as PNGs and converted the list of coordinates of the contours to PNGs as well.
The first two sets of CMRs are included as training data, the last set as test data.
andreaazzini/segnet: A Tensorflow SegNet translation
pydicom: A pure python dicom library
StackOverflow Tensorflow batch_norm thread
GitHub Tensorflow unpool thread
- The original SegNet uses max_pool_with_argmax, and requires an unpool_with_argmax. Unfortunately, Tensorflow does not provide an unpool_with_argmax. Fortunately there is code in the github thread above to make your own.
- This version of unpool_with_argmax runs on the CPU not GPU so is a little slower.
- Tensorflow does not provide a CPU version of max_pool_with_argmax, so if you don't have a GPU you can't run this.
- Tensorflow forgot to include a function for gradients for maxpoolwithargmax, so it is included at the bottom of train.py
- The name mangling of the Sunnybrook CMR data - I have fixed this and the data is included in the download.
- SegNet works better with a version of softmax that is inversely weighted by class frequency.
- Now using SELU as the activation funciton - this allows us to get rid of the Batch Norm (and the associated is_training hassle).
SegNetCMR: MIT license
SunnyBrook Cardiac Data: Public Domain
pydicom: MIT license
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent