Abstract
Deep learning has become an effective tool for classifying biological sex based on functional magnetic resonance imaging (fMRI), but research on what features within the brain are most relevant to this classification is still lacking. Model interpretability has become a powerful way to understand “black box” deep-learning models and select features within the input data that are most relevant to the correct classification. However, very little work has been done employing these methods to understand the relationship between the temporal dimension of functional imaging signals and classification of biological sex, nor has there been attention paid to rectifying problems and limitations associated with feature explanation models, e.g. underspecification and instability. We provide a methodology to limit the impact of underspecification on the stability of the measured feature importance, and then, using intrinsic connectivity networks (ICNs) from fMRI data, we provide a deep exploration of sex differences among functional brain networks. We report numerous conclusions, including activity differences in the visual and cognitive domains, as well as major connectivity differences.
Competing Interest Statement
The authors have declared no competing interest.
