Deep learning and cross-species analysis identify the influences of sex and cannabinoidsignaling on cerebellar vermis morphology

Abstract

The cerebellum is the only folded cortical structure present in both rodents and humans, allowing mechanistic studies of gyrification across species. In mice, the extent of anterior vermis folding and the shapes of white matter exhibit sex-dependent differences. We trained a deep convolutional neural network to predict biological sex from midline cerebellar MRI images, showing that human cerebellar midvermis contains sex-dependent anatomical features. Our comparative cross-species analysis shows that in both species, sex and anterior vermis folding patterns are not enough to predict an individuals behavior because the variability in performance between individuals is far greater than the differences between conditions. Finally, utilizing constitutive cannabinoid receptor 1 (CB1) knockout (KO) mice, we identify developmental cannabinoid signaling as a novel molecular mechanism limiting secondary fissure formation. TeaserMales and females display differences in the architecture of cerebellar folding shaped by cannabinoid signaling during development.