Conference Program

A Novel Architecture Combining Central-Peripheral Deviation with Convolutional Neural Networks for Diffusion Tensor Imaging Studies (310087)

Presentation

*Soyun Park, University at Buffalo 
Jihnhee Yu, University at Buffalo 

Keywords: Concentric Circle Pooling, Convolutional Neural Network, Diffusion Tensor Imaging, Classification, Multi-Layer Perceptron

DTI research is a very challenging topic due to com- plicity and implicitness. In this regard, developing classification methods to improve clinical diagnosis becomes crucial. This paper proposes a classification method for DTI data based on a novel neural network strategy that combines a convolutional neural network (CNN) with a multilayer neural network using central-peripheral deviation (CPD), which reflects diffusion dynamics in the white matter by spatially evaluating the deviation of diffusion coefficients between the inner and outer parts of the brain.