Harnessing spatial homogeneity of neuroimaging data: patch individual filter layers for CNNs

Item Type:	Preprint
Title:	Harnessing spatial homogeneity of neuroimaging data: patch individual filter layers for CNNs
Creators Name:	Eitel, F. and Albrecht, J.P. and Weygandt, M. and Paul, F. and Ritter, K.
Abstract:	Neuroimaging data, e.g. obtained from magnetic resonance imaging (MRI), is comparably homogeneous due to (1) the uniform structure of the brain and (2) additional efforts to spatially normalize the data to a standard template using linear and non-linear transformations. Convolutional neural networks (CNNs), in contrast, have been specifically designed for highly heterogeneous data, such as natural images, by sliding convolutional filters over different positions in an image. Here, we suggest a new CNN architecture that combines the idea of hierarchical abstraction in neural networks with a prior on the spatial homogeneity of neuroimaging data: Whereas early layers are trained globally using standard convolutional layers, we introduce for higher, more abstract layers patch individual filters (PIF). By learning filters in individual image regions (patches) without sharing weights, PIF layers can learn abstract features faster and with fewer samples. We thoroughly evaluated PIF layers for three different tasks and data sets, namely sex classification on UK Biobank data, Alzheimer's disease detection on ADNI data and multiple sclerosis detection on private hospital data. We demonstrate that CNNs using PIF layers result in higher accuracies, especially in low sample size settings, and need fewer training epochs for convergence. To the best of our knowledge, this is the first study which introduces a prior on brain MRI for CNN learning.
Keywords:	Convolutional Neural Networks (CNNs), Patch Individual Filters, Neuroimaging, Magnetic Resonance Imaging (MRI), Small Sample Size, Alzheimer's Disease, Multiple Sclerosis, Sex Classification
Source:	arXiv
Publisher:	Cornell University
Article Number:	2007.11899
Date:	23 July 2020
Official Publication:	https://arxiv.org/abs/2007.11899

Repository Staff Only: item control page