Brain MRI Age Classification Using Deep Learning

This example shows how to work with an MRI brain image dataset and how to use transfer learning to modify and retrain ResNet-18, a pretrained convolutional neural network, to perform image classification on that dataset.

👀 View the example ▶️ Run the example

About the Data

The MRI scans used in this example were obtained during a study [1] of social brain development conducted by researchers at the Massachussets Institute of Technology (MIT), and are available for download via the OpenNEURO platform: https://openneuro.org/datasets/ds000228/versions/1.1.0

About the Workflow

This example uses the horizontal midslice images from the brain MRI scan volumes and classifies them into 3 categories according to the chronological age of the participant:

1. Participants Aged 3-5
2. Participants Aged 7-12
3. Participants older than 18, classified as Adults

This example works though multiple steps of a deep learning workflow:

• Exploring a public brain MRI image dataset
• Preparing the dataset for deep learning
• Training a deep learning model to perform chronological age classification
• Evaluating the trained model

Running the Example

to run the example in your web browser with no installation required.

To run on your local machine or cloud instance, open & run the live script BrainMRIAgeClassificationUsingDeepLearning.mlx.

Requires:

• MATLAB (version R2019b or later)
• Deep Learning Toolbox
• Image Processing Toolbox

References

[1] Richardson, H., Lisandrelli, G., Riobueno-Naylor, A., & Saxe, R. (2018). Development of the social brain from age three to twelve years. Nature Communications, 9(1), 1027. https://doi.org/10.1038/s41467-018-03399-2

Copyright 2020 The MathWorks, Inc.