Original Author: Paras Lakhani, paras.lakhani@jefferson.edu
This repository has been forked and modified from the original.
Contributors to this repository:
- Walter Wiggins (Contact: wwiggins@bwh.harvard.edu)
- Travis Caton
- Kirti Magudia
- Andreas Rauschecker
- James Condon
This work is adapted from Lakhani et al. "Hello World Deep Learning in Medical Imaging." Journal of Digital Imaging. 2018 Jun;31(3):283-289 (link to article).
The code and the directory structure have been modified to match the format from the article. Additional modifications have been made with the intent to increase readability and facilitate understanding for participants at all levels of coding skill and experience.
This is a high-level introduction into practical machine learning for purposes of medical image classification.
In this tutorial, the Tensorflow backend is used with the Keras framework, which is a high-level application programming interface (API) that simplifies working with Tensorflow.
If you would like to run the code in an established environment please proceed to Walter's Kaggle kernel and follow the instructions there.
As with the original authors, we hope this tutorial fosters interest in machine learning for medical imaging. In addition, we hope our modifications lower the barriers to entry for those of all experience levels.