We propose to apply a 2D CNN architecture to 3D MRI image Alzheimer's disease classification. Training a 3D convolutional neural network (CNN) is time-consuming and computationally expensive. We make use of approximate rank pooling to transform the 3D MRI image volume into a 2D image to use as input to a 2D CNN. We show our proposed CNN model achieves 9.5% better Alzheimer's disease classification accuracy than the baseline 3D models. We also show that our method allows for efficient training, requiring only 20% of the training time compared to 3D CNN models. The code is available online: https://github.com/UkyVision/alzheimer-project.
@article{arxiv.2012.00119,
title = {Dynamic Image for 3D MRI Image Alzheimer's Disease Classification},
author = {Xin Xing and Gongbo Liang and Hunter Blanton and Muhammad Usman Rafique and Chris Wang and Ai-Ling Lin and Nathan Jacobs},
journal= {arXiv preprint arXiv:2012.00119},
year = {2021}
}
Comments
Accepted to ECCV2020 Workshop on BioImage Computing