Is Texture Predictive for Age and Sex in Brain MRI?
This addresses the efficiency and design of neural networks for medical imaging tasks, potentially reducing computational costs for researchers and clinicians.
The paper investigates whether large receptive fields, which are commonly used in deep learning for medical image analysis, are necessary for predicting age and sex from T1-weighted brain MRI scans, based on findings from natural image tasks.
Deep learning builds the foundation for many medical image analysis tasks where neuralnetworks are often designed to have a large receptive field to incorporate long spatialdependencies. Recent work has shown that large receptive fields are not always necessaryfor computer vision tasks on natural images. We explore whether this translates to certainmedical imaging tasks such as age and sex prediction from a T1-weighted brain MRI scans.