Brain-MRI-Age-Classification-using-Deep-Learning

MATLAB example using deep learning to classify chronological age from brain MRI images

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

The MRI scans used in this example were obtained during a study [1] of social brain development conducted by researchers at the Massachusetts Institute of Technology (MIT). These data are available for download at the OpenNEURO platform [2] in NIfTI file format [3].

This example works with the 2D axial midslice images from the brain MRI scan volumes, and shows how these images can be classified 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:

1. Exploring a public brain MRI image dataset
2. Preparing the dataset for deep learning
3. Training a deep learning model to perform chronological age classification
4. Evaluating the trained model

RUNNING THE EXAMPLE
Open and run the live script BrainMRIAgeClassificationUsingDeepLearning.mlx

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://www.nature.com/articles/s41467-018-03399-2
[2] https://openneuro.org/datasets/ds000228/versions/1.1.0
[3] Cox, R. W., J. Ashburner, H. Breman, K. Fissell, C. Haselgrove, C. J. Holmes, J. L. Lancaster, D. E. Rex, S. M. Smith, J. B. Woodward, and S. C. Strother (2004). A (sort of) new image data format standard: NiFTI-1. 10th Annual Meeting of Organisation of Human Brain Mapping, Budapest, Hungary.