MIScnn: A Python Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning

The increased need for automatic medical image segmentation has been created due to the enormous usage of modern medical imaging in technology. Despite this large need, the current medical image segmentation platforms do not provide required functionalities for the plain setup of medical image segmentation pipelines. Therefore this paper introduces the open-source Python library MIScnn.

MIScnn is an opensource framework with intuitive APIs allowing the fast setup of medical image segmentation pipelines with Convolutional Neural Network and DeepLearning models in just a few lines of code. The objective of MIScnn according to paper is to provide a framework API that can be allowing the fast building of medical image segmentation pipelines including data I/O, preprocessing, data augmentation, patch-wise analysis, metrics, a library with state-of-the-art deep learning models and model utilization like training, prediction, as well as fully automatic evaluation (e.g. cross-validation). 

Core Features

• MIScnn is a very intuitive framework/API designed for fast execution.
• 2D/3D medical image segmentation for binary and multi-class problems
• Data I/O, pre-/postprocessing functions, metrics, and model architectures are standalone interfaces that you can easily switch.
• Patch-wise and full image analysis
• New interfaces are simple to integrate into the MIScnn pipeline.
• State-of-the-art deep learning model and metric library
• Intuitive and fast model utilization (training, prediction)
• Multiple automatic evaluation techniques (e.g., cross-validation)
• Tensorflow as backend and based on Keras.

Installation

Two ways to install

1. Install MIScnn from PyPI (recommended):

sudo pip install miscnn

2. Alternatively: install MIScnn from the GitHub source:

git clone https://github.com/frankkramer-lab/MIScnn

Then, cd to the MIScnn folder and run the install command:

cd MIScnn
sudo python setup.py install

Github: https://github.com/frankkramer-lab/MIScnn

Paper: https://arxiv.org/abs/1910.09308

Documentation: https://github.com/frankkramer-lab/MIScnn/wiki

MIScnn Examples:  https://github.com/frankkramer-lab/MIScnn/wiki/Examples

MIScnn Tutorials: https://github.com/frankkramer-lab/MIScnn/wiki/Tutorials