Dynamic Image for 3D MRI Image Alzheimer's Disease Classification

Xin Xing, Gongbo Liang, Hunter Blanton, Muhammad Usman Rafique, Chris Wang, Ai-Ling Lin, Nathan Jacobs

ECCVW 2020 pp. 355-364

doi:10.1007/978-3-030-66415-2_23 /eccvw/2020/xing2020eccvw-dynamic/

Abstract

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.

PDF ECCVW Semantic Scholar

Cite

Text

Xing et al. "Dynamic Image for 3D MRI Image Alzheimer's Disease Classification." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-66415-2_23

Markdown

[Xing et al. "Dynamic Image for 3D MRI Image Alzheimer's Disease Classification." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/xing2020eccvw-dynamic/) doi:10.1007/978-3-030-66415-2_23

BibTeX

@inproceedings{xing2020eccvw-dynamic,
  title     = {{Dynamic Image for 3D MRI Image Alzheimer's Disease Classification}},
  author    = {Xing, Xin and Liang, Gongbo and Blanton, Hunter and Rafique, Muhammad Usman and Wang, Chris and Lin, Ai-Ling and Jacobs, Nathan},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2020},
  pages     = {355-364},
  doi       = {10.1007/978-3-030-66415-2_23},
  url       = {https://mlanthology.org/eccvw/2020/xing2020eccvw-dynamic/}
}