Automatic Annotation of Axoplasmic Reticula in Pursuit of Connectomes using High-Resolution Neural EM Data

TL;DR

This paper presents a novel automated method for identifying and annotating axoplasmic reticula in high-resolution neural EM data to facilitate accurate connectome reconstruction.

Contribution

The proposed approach automatically detects axoplasmic reticula in 3D EM data, enhancing segmentation accuracy and aiding connectome mapping.

Findings

High precision annotation of axoplasmic reticula achieved

Improved segmentation seed generation demonstrated

Facilitates more accurate connectome reconstruction

Abstract

Accurately estimating the wiring diagram of a brain, known as a connectome, at an ultrastructure level is an open research problem. Specifically, precisely tracking neural processes is difficult, especially across many image slices. Here, we propose a novel method to automatically identify and annotate small subcellular structures present in axons, known as axoplasmic reticula, through a 3D volume of high-resolution neural electron microscopy data. Our method produces high precision annotations, which can help improve automatic segmentation by using our results as seeds for segmentation, and as cues to aid segment merging.