Magnetic resonance imaging (MRI) is crucial for diagnosing and monitoring various diseases. Many emerging MRI techniques use machine learning to generate microstructural maps—representations of small-scale tissue properties such as axon diameter, cell size, and blood flow. Self-supervised machine learning is proving to be a promising approach for producing these maps [1,2]. This project will contribute to the development of MicroTorch, an open-source self-supervised machine learning package for MRI processing. While MicroTorch is already in development, it currently lacks step-by-step examples for many microstructural models. This project will involve implementing Jupyter notebook examples for multiple models and adding new microstructural models to the package. 1. Barbieri et al. Deep learning how to fit an intravoxel incoherent motion model to diffusion-weighted MRI. Magnetic Resonance in Medicine 2019. https://doi.org/10.1002/mrm.27910, 2.https://github.com/sebbarb/deep_ivim