AxoNet: A deep learning-based tool to count retinal ganglion cell axons

Matthew D Ritch,C Ross Ethier,Grant A Cull,A Thomas Read,Bailey G Hannon,John C Morrison,Andrew J Feola,Juan Reynaud,Claude F Burgoyne,Machelle T Pardue

doi:10.1038/s41598-020-64898-1

Abstract

In this work, we develop a robust, extensible tool to automatically and accurately count retinal ganglion cell axons in optic nerve (ON) tissue images from various animal models of glaucoma. We adapted deep learning to regress pixelwise axon count density estimates, which were then integrated over the image area to determine axon counts. The tool, termed AxoNet, was trained and evaluated using a dataset containing images of ON regions randomly selected from whole cross sections of both control and damaged rat ONs and manually annotated for axon count and location. This rat-trained network was then applied to a separate dataset of non-human primate (NHP) ON images. AxoNet was compared to two existing automated axon counting tools, AxonMaster and AxonJ, using both datasets. AxoNet outperformed the existing tools on both the rat and NHP ON datasets as judged by mean absolute error, R2 values when regressing automated vs. manual counts, and Bland-Altman analysis. AxoNet does not rely on hand-crafted image features for axon recognition and is robust to variations in the extent of ON tissue damage, image quality, and species of mammal. Therefore, AxoNet is not species-specific and can be extended to quantify additional ON characteristics in glaucoma and potentially other neurodegenerative diseases.

Highlights

In this work, we develop a robust, extensible tool to automatically and accurately count retinal ganglion cell axons in optic nerve (ON) tissue images from various animal models of glaucoma
In the healthy nerve, most axons are characterized by a clear central axoplasmic core and a darker myelin sheath; following previous work[5,8], we will refer to such an appearance as “normal”
We first applied the three automated counting tools to the validation subset of the rat dataset to determine correction equations that accounted for linear bias, as described above (Fig. 3)

Summary

Introduction

We develop a robust, extensible tool to automatically and accurately count retinal ganglion cell axons in optic nerve (ON) tissue images from various animal models of glaucoma. Semi-automated axon counting methods use algorithmic axon segmentation techniques involving hyperparameters, such as intensity thresholds which are manually tuned for individual sub-images[11] These methods are faster than manual counting and more thorough than qualitative or sub-sampling methods, but still require extensive human direction and time. Both tools are designed to count “normal”-appearing axons, i.e. axons with a clear cytoplasmic core and a dark myelin sheath[5,8] They use dynamic thresholding techniques to segment axonal interiors from myelin and other optic nerve features. While these tools are faster and provide more detail than sub-sampling methods, they suffer limitations. Our preliminary testing using these packages suggested that they are sensitive to image quality, tissue staining intensity, and nerve damage extent in images of rat optic nerves (see Results)

Objectives

Methods

Results

Discussion

Conclusion