An Out-of-Domain Synapse Detection Challenge for Microwasp Brain Connectomes

TL;DR

This paper introduces an out-of-domain synapse detection challenge for microwasp brain connectomes, addressing the difficulty of generalizing neural structure annotation across diverse brain regions with limited training data.

Contribution

It presents a novel benchmark for evaluating domain adaptation methods in connectomics, highlighting the challenges of out-of-domain generalization in large-scale neural imaging.

Findings

Limited training data hampers synapse detection accuracy.

Domain adaptation techniques show potential but need further development.

Benchmark datasets reveal significant domain shifts in connectomics.

Abstract

The size of image stacks in connectomics studies now reaches the terabyte and often petabyte scales with a great diversity of appearance across brain regions and samples. However, manual annotation of neural structures, e.g., synapses, is time-consuming, which leads to limited training data often smaller than 0.001\% of the test data in size. Domain adaptation and generalization approaches were proposed to address similar issues for natural images, which were less evaluated on connectomics data due to a lack of out-of-domain benchmarks.