The Medical Imaging Segmentation Toolkit (MIST) is a simple, fully automated 3D medical imaging segmentation framework for PyTorch and TensorFlow. MIST allows researchers to quickly set up, train, and test various deep learning models for 3D medical imaging segmentation.

For documentation on how to run either the PyTorch or TensorFlow implementations, please see the following

• MIST PyTorch
• MIST TensorFlow

Please cite the following if you use this code for your work:

A. Celaya et al., "PocketNet: A Smaller Neural Network For Medical Image Analysis," in IEEE Transactions on Medical Imaging, doi: 10.1109/TMI.2022.3224873.