Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks

TL;DR

This paper introduces a self-supervised Siamese network approach to improve the automatic segmentation of human brain areas, addressing data scarcity and variability issues in cytoarchitectonic mapping.

Contribution

It proposes a novel self-supervised pre-training method that enhances neural network performance for brain area segmentation without extensive labeled data.

Findings

Pre-training with the auxiliary task improves segmentation accuracy.

The model implicitly learns to distinguish cortical brain areas.

Self-supervised approach outperforms random initialization.

Abstract

Cytoarchitectonic parcellations of the human brain serve as anatomical references in multimodal atlas frameworks. They are based on analysis of cell-body stained histological sections and the identification of borders between brain areas. The de-facto standard involves a semi-automatic, reproducible border detection, but does not scale with high-throughput imaging in large series of sections at microscopical resolution. Automatic parcellation, however, is extremely challenging due to high variation in the data, and the need for a large field of view at microscopic resolution. The performance of a recently proposed Convolutional Neural Network model that addresses this problem especially suffers from the naturally limited amount of expert annotations for training. To circumvent this limitation, we propose to pre-train neural networks on a self-supervised auxiliary task, predicting the 3D distance between two patches sampled from the same brain. Compared to a random initialization, fine-tuning from these networks results in significantly better segmentations. We show that the self-supervised model has implicitly learned to distinguish several cortical brain areas -- a strong indicator that the proposed auxiliary task is appropriate for cytoarchitectonic mapping.