Contrastive Representation Learning for Whole Brain Cytoarchitectonic Mapping in Histological Human Brain Sections
This work is significant for neuroscientists and anatomists by providing a more efficient and accurate method for whole-brain cytoarchitectonic mapping, an incremental improvement over existing methods.
This paper addresses the challenge of automatically segmenting cytoarchitectonic areas in histological human brain sections, aiming for whole-brain mapping. They propose a contrastive learning objective to encode microscopic image patches into robust microstructural features, which are then used for cytoarchitectonic area classification. The pre-trained model outperforms models trained from scratch and those pre-trained on an auxiliary task.
Cytoarchitectonic maps provide microstructural reference parcellations of the brain, describing its organization in terms of the spatial arrangement of neuronal cell bodies as measured from histological tissue sections. Recent work provided the first automatic segmentations of cytoarchitectonic areas in the visual system using Convolutional Neural Networks. We aim to extend this approach to become applicable to a wider range of brain areas, envisioning a solution for mapping the complete human brain. Inspired by recent success in image classification, we propose a contrastive learning objective for encoding microscopic image patches into robust microstructural features, which are efficient for cytoarchitectonic area classification. We show that a model pre-trained using this learning task outperforms a model trained from scratch, as well as a model pre-trained on a recently proposed auxiliary task. We perform cluster analysis in the feature space to show that the learned representations form anatomically meaningful groups.