Self-Supervised Learning of Synapse Types from EM Images

TL;DR

This paper introduces a self-supervised method to classify synapse types in EM images without prior labels, leveraging local similarity assumptions, and applies it to Drosophila data.

Contribution

It presents a novel self-supervised approach for synapse classification that does not require pre-defined class labels or counts.

Findings

Effective separation of synapse types based on local similarity

No need for pre-specified number of classes

Applicable to Drosophila EM data

Abstract

Separating synapses into different classes based on their appearance in EM images has many applications in biology. Examples may include assigning a neurotransmitter to a particular class, or separating synapses whose strength can be modulated from those whose strength is fixed. Traditionally, this has been done in a supervised manner, giving the classification algorithm examples of the different classes. Here we instead separate synapses into classes based only on the observation that nearby synapses in the same neuron are likely more similar than synapses chosen randomly from different cells. We apply our methodology to data from {\it Drosophila}. Our approach has the advantage that the number of synapse types does not need to be known in advance. It may also provide a principled way to select ground-truth that spans the range of synapse structure.