3D Brain MRI Classification for Alzheimer Diagnosis Using CNN with Data Augmentation
This work addresses Alzheimer's diagnosis for medical imaging applications, but it is incremental as it builds on prior methods with simple data augmentation.
The authors tackled Alzheimer's disease diagnosis by developing a 3D CNN for classifying brain MRI scans, achieving a test accuracy of 0.912 and an AUC of 0.961, with sensitivity and specificity over 0.90.
A three-dimensional convolutional neural network was developed to classify T1-weighted brain MRI scans as healthy or Alzheimer. The network comprises 3D convolution, pooling, batch normalization, dense ReLU layers, and a sigmoid output. Using stochastic noise injection and five-fold cross-validation, the model achieved test set accuracy of 0.912 and area under the ROC curve of 0.961, an improvement of approximately 0.027 over resizing alone. Sensitivity and specificity both exceeded 0.90. These results align with prior work reporting up to 0.10 gain via synthetic augmentation. The findings demonstrate the effectiveness of simple augmentation for 3D MRI classification and motivate future exploration of advanced augmentation methods and architectures such as 3D U-Net and vision transformers.