Contrastive Representation Learning for Whole Brain Cytoarchitectonic Mapping in Histological Human Brain Sections

TL;DR

This paper introduces a contrastive learning approach to improve automatic cytoarchitectonic mapping of the human brain from histological images, enabling more accurate and comprehensive brain parcellation.

Contribution

It presents a novel contrastive learning method for encoding microscopic brain tissue images, enhancing the classification of cytoarchitectonic areas across the entire brain.

Findings

Pre-trained models outperform models trained from scratch.

Learned features form meaningful anatomical clusters.

Contrastive learning improves microstructural feature robustness.

Abstract

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.