English

Geometric Convolutional Neural Network for Analyzing Surface-Based Neuroimaging Data

Neural and Evolutionary Computing 2017-08-03 v1 Machine Learning

Abstract

The conventional CNN, widely used for two-dimensional images, however, is not directly applicable to non-regular geometric surface, such as a cortical thickness. We propose Geometric CNN (gCNN) that deals with data representation over a spherical surface and renders pattern recognition in a multi-shell mesh structure. The classification accuracy for sex was significantly higher than that of SVM and image based CNN. It only uses MRI thickness data to classify gender but this method can expand to classify disease from other MRI or fMRI data

Keywords

Cite

@article{arxiv.1708.00587,
  title  = {Geometric Convolutional Neural Network for Analyzing Surface-Based Neuroimaging Data},
  author = {Si-Baek Seong and Chongwon Pae and Hae-Jeong Park},
  journal= {arXiv preprint arXiv:1708.00587},
  year   = {2017}
}

Comments

29 pages

R2 v1 2026-06-22T21:04:19.712Z