Is Texture Predictive for Age and Sex in Brain MRI?

Nick Pawlowski, Ben Glocker

Keywords: Age and Sex Prediction, Brain MRI, Neural Networks

TL;DR: We show that brain MRI texture information is predictive about age and sex.

Abstract: Deep learning builds the foundation for many medical image analysis tasks where neural networks are often designed to have a large receptive field to incorporate long spatial dependencies. Recent work has shown that large receptive fields are not always necessary for computer vision tasks on natural images. We explore whether this translates to certain medical imaging tasks such as age and sex prediction from a T1-weighted brain MRI scans.

Code Of Conduct: I have read and accept the code of conduct.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1907.10961/code)