Browse
Submit Data
Databases
API
Help

Dataset Information

14 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

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

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.

SUBMITTER: Ritch MD

PROVIDER: S-EPMC7228952 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

AxoNet 2.0: A Deep Learning-Based Tool for Morphometric Analysis of Retinal Ganglion Cell Axons.

Project description:PurposeAssessment of glaucomatous damage in animal models is facilitated by rapid and accurate quantification of retinal ganglion cell (RGC) axonal loss and morphologic change. However, manual assessment is extremely time- and labor-intensive. Here, we developed AxoNet 2.0, an automated deep learning (DL) tool that (i) counts normal-appearing RGC axons and (ii) quantifies their morphometry from light micrographs.MethodsA DL algorithm was trained to segment the axoplasm and myelin sheath of normal-appearing axons using manually-annotated rat optic nerve (ON) cross-sectional micrographs. Performance was quantified by various metrics (e.g., soft-Dice coefficient between predicted and ground-truth segmentations). We also quantified axon counts, axon density, and axon size distributions between hypertensive and control eyes and compared to literature reports.ResultsAxoNet 2.0 performed very well when compared to manual annotations of rat ON (R2 = 0.92 for automated vs. manual counts, soft-Dice coefficient = 0.81 ± 0.02, mean absolute percentage error in axonal morphometric outcomes < 15%). AxoNet 2.0 also showed promise for generalization, performing well on other animal models (R2 = 0.97 between automated versus manual counts for mice and 0.98 for non-human primates). As expected, the algorithm detected decreased in axon density in hypertensive rat eyes (P ≪ 0.001) with preferential loss of large axons (P < 0.001).ConclusionsAxoNet 2.0 provides a fast and nonsubjective tool to quantify both RGC axon counts and morphological features, thus assisting with assessing axonal damage in animal models of glaucomatous optic neuropathy.Translational relevanceThis deep learning approach will increase rigor of basic science studies designed to investigate RGC axon protection and regeneration.

| S-EPMC10020950 | biostudies-literature

A novel retinal ganglion cell quantification tool based on deep learning.

Project description:Glaucoma is a disease associated with the loss of retinal ganglion cells (RGCs), and remains one of the primary causes of blindness worldwide. Major research efforts are presently directed towards the understanding of disease pathogenesis and the development of new therapies, with the help of rodent models as an important preclinical research tool. The ultimate goal is reaching neuroprotection of the RGCs, which requires a tool to reliably quantify RGC survival. Hence, we demonstrate a novel deep learning pipeline that enables fully automated RGC quantification in the entire murine retina. This software, called RGCode (Retinal Ganglion Cell quantification based On DEep learning), provides a user-friendly interface that requires the input of RBPMS-immunostained flatmounts and returns the total RGC count, retinal area and density, together with output images showing the computed counts and isodensity maps. The counting model was trained on RBPMS-stained healthy and glaucomatous retinas, obtained from mice subjected to microbead-induced ocular hypertension and optic nerve crush injury paradigms. RGCode demonstrates excellent performance in RGC quantification as compared to manual counts. Furthermore, we convincingly show that RGCode has potential for wider application, by retraining the model with a minimal set of training data to count FluoroGold-traced RGCs.

| S-EPMC7804414 | biostudies-literature

Slit2 is a repellent for retinal ganglion cell axons.

Project description:We set out to isolate inhibitory guidance cues that affect retinal ganglion cell (RGC) axons in vitro and that could potentially be involved in RGC pathfinding decisions. Here we describe the biochemical purification of an RGC growth cone collapsing factor from bovine brain membranes and its identification as Slit2. Recombinant human Slit2 collapses and repels RGC growth cones from all quadrants of the chick retina. In the developing mouse visual system, slit2 is expressed in the eye, in the optic stalk, and in the ventral diencephalon. Slit2 expression is strong in anterior ventral diencephalic structures but is absent from the ventral midline where the optic chiasm forms. The putative receptors for Slits, robo1 and robo2, are expressed in the inner retinal layer in which RGCs are located. A comparison of the expression patterns of Slit2 and retinal axon trajectories suggests that slit2 acts as a short range repellent for retinal ganglion cell axons.

| S-EPMC6772294 | biostudies-literature

CXCL12 promotes the crossing of retinal ganglion cell axons at the optic chiasm.

Project description:Binocular vision requires the segregation of retinal ganglion cell (RGC) axons extending from the retina into the ipsilateral and contralateral optic tracts. RGC axon segregation occurs at the optic chiasm, which forms at the ventral diencephalon midline. Using expression analyses, retinal explants and genetically modified mice, we demonstrate that CXCL12 (SDF1) is required for axon segregation at the optic chiasm. CXCL12 is expressed by the meninges bordering the optic pathway, and CXCR4 by both ipsilaterally and contralaterally projecting RGCs. CXCL12 or ventral diencephalon meninges potently promoted axon outgrowth from both ipsilaterally and contralaterally projecting RGCs. Further, a higher proportion of axons projected ipsilaterally in mice lacking CXCL12 or its receptor CXCR4 compared with wild-type mice as a result of misrouting of presumptive contralaterally specified RGC axons. Although RGCs also expressed the alternative CXCL12 receptor ACKR3, the optic chiasm developed normally in mice lacking ACKR3. Our data support a model whereby meningeal-derived CXCL12 helps drive axon growth from CXCR4-expressing RGCs towards the diencephalon midline, enabling contralateral axon growth. These findings further our understanding of the molecular and cellular mechanisms controlling optic pathway development.

| S-EPMC10820821 | biostudies-literature

DeepTFactor, a deep learning-based tool for the identification of transcription factors

Project description:We report the development of a deep learning-based tool, DeepTFactor, that predicts whether a protein of question is a transcription factor. DeepTFactor uses a convolutional neural network to extract features of protein sequences. We characterized the genome-wide binding sites of three TFs (i.e., YqhC, YiaU, and YahB), which are predicted by DeepTFactor

2020-10-09 | GSE158683 | GEO

3D Visualization of Individual Regenerating Retinal Ganglion Cell Axons Reveals Surprisingly Complex Growth Paths.

Project description:Retinal ganglion cells (RGCs), the sole output cells of the retina, are a heterogeneous population of neurons that project axons to visual targets in the brain. Like most CNS neurons, RGCs are considered incapable of mounting long distance axon regeneration. Using immunolabeling-enabled 3D imaging of solvent-cleared organs (iDISCO) in transgenic mice, we tracked the entire paths of individual RGC axons and show that adult RGCs are highly capable of spontaneous long-distance regeneration, even without any treatment. Our results show that the Thy1-H-YFP mouse sparsely labels RGCs, consisting predominantly of regeneration-competent α-type RGCs (αRGCs). Following optic nerve crush, many of the YFP-labeled RGC axons extend considerable distances proximal to the injury site with only a few penetrating through the lesion. This tortuous axon growth proximal to the lesion site is even more striking with intravitreal ciliary neurotrophic factor (CNTF) treatment. We further demonstrate that despite traveling more than 5 mm (i.e., a distance equal to the length of mouse optic nerve), many of these circuitous axons are confined to the injury area and fail to reach the brain. Our results re-evaluate the view that RGCs are naturally incapable of re-extending long axons, and shift the focus from promoting axon elongation, to understanding factors that prevent direct growth of axons through the lesion and the injured nerve.

| S-EPMC5575138 | biostudies-literature

Weak electric fields serve as guidance cues that direct retinal ganglion cell axons in vitro.

Project description:Growing axons are directed by an extracellular electric field in a process known as galvanotropism. The electric field is a predominant guidance cue directing retinal ganglion cell (RGC) axons to the future optic disc during embryonic development. Specifically, the axons of newborn RGCs grow along the extracellular voltage gradient that exists endogenously in the embryonic retina (Yamashita, 2013 [8]). To investigate the molecular mechanisms underlying galvanotropic behaviour, the quantification of the electric effect on axon orientation must be examined. In the present study, a culture system was built to apply a constant, uniform direct current (DC) electric field by supplying an electrical current to the culture medium, and this system also continuously recorded the voltage difference between the two points in the medium. A negative feedback circuit was designed to regulate the supplied current to maintain the voltage difference at the desired value. A chick embryo retinal strip was placed between the two points and cultured for 24 h in an electric field in the opposite direction to the endogenous field, and growing axons were fluorescently labelled for live cell imaging (calcein-AM). The strength of the exogenous field varied from 0.0005 mV/mm to 10.0 mV/mm. The results showed that RGC axons grew in the reverse direction towards the cathode at voltage gradients of ≥0.0005 mV/mm, and straightforward extensions were found in fields of ≥0.2-0.5 mV/mm, which were far weaker than the endogenous voltage gradient (15 mV/mm). These findings suggest that the endogenous electric field is sufficient to guide RGC axons in vivo.

| S-EPMC5668898 | biostudies-literature

Topoisomerase IIbeta is required for lamina-specific targeting of retinal ganglion cell axons and dendrites.

Project description:The specific partnering of synaptically connected neurons is central to nervous system function. Proper wiring requires the interchange of signals between a postmitotic neuron and its environment, a distinct pattern of transcription in the nucleus, and deployment of guidance and adhesion cues to the cell surface. To identify genes involved in neurite targeting by retinal ganglion cells (GCs), their presynaptic partners in the retina, and their postsynaptic targets in the optic tectum, we undertook a forward genetic screen for mutations disrupting visual responses in zebrafish. This rapid primary screen was subsequently refined by immunohistochemical labeling of retinal and tectal neurites to detect patterning errors. From this unbiased screen, the notorious (noto) mutant exhibited the most specific phenotypes: intact retinal and tectal differentiation but multiple neurite targeting defects in the retinal inner plexiform layer (IPL) and tectal neuropil. Positional cloning and morpholino phenocopy revealed that the mutation disrupts Topoisomerase IIβ (Top2b), a broadly distributed nuclear protein involved in chromatin modifications during postmitotic differentiation. Top2b-DNA interactions are known to regulate transcription of developmentally important genes, including axon guidance factors and cell adhesion molecules, but a specific role in local synaptic targeting has not been previously described. The neurite targeting defects among GC axons are largely restricted to crossovers between sublaminae of a specific layer, SFGS, and were shown by mosaic analysis to be autonomous to the GC axons. The noto mutant provides the first example of the importance of an epigenetic regulator, Top2b, in the intricate series of events that lead to a properly wired visual system.

| S-EPMC3100707 | biostudies-literature

Microtubule Imaging Reveals Cytoskeletal Deficit Predisposing the Retinal Ganglion Cell Axons to Atrophy in DBA/2J.

Project description:PurposeGlaucoma is characterized by progressive loss of the retinal ganglion cells (RGCs) and their axons. Here we test an outstanding notion that microtubules (MTs) within RGC axons degrade before the loss of morphology ("MT hypothesis").MethodsThe integrity of axonal MTs was interrogated by intrinsic second-harmonic generation (SHG) microscopy. Using DBA/2J mice as a model of glaucoma and DBA/2J-Gpnmb+ as a nonglaucomatous control, the relationship between MT disruption and morphology was quantitatively examined as a function of age and sex in the fresh retinal wholemounts.ResultsThe mean SHG density (i.e., the mean SHG intensity per thickness) was significantly lower in DBA/2J than in DBA/2J-Gpnmb+ and also depended on sex and age. The loss of SHG density, indicating MT disruption within intact RGC axons, occurred in a sectorial manner near the loss of the retinal nerve fiber bundles. The decay rate of SHG density was approximately 97% higher than that of thickness.ConclusionsCollectively, the results indicate that the breakdown of MTs is pathology of glaucoma and likely a precursor of morphological atrophy. Based on a new finding that SHG density is highly variable and spatially discrete, a new model of RGC degeneration is proposed. This study validates SHG retinal imaging for elucidating the role and mechanism of MT deficiency in the course of glaucoma pathogenesis.

| S-EPMC6218151 | biostudies-literature

Morphometric Analysis of Retinal Ganglion Cell Axons in Normal and Glaucomatous Brown Norway Rats Optic Nerves.

Project description:PurposeA reference atlas of optic nerve (ON) retinal ganglion cell (RGC) axons could facilitate studies of neuro-ophthalmic diseases by detecting subtle RGC axonal changes. Here we construct an RGC axonal atlas for normotensive eyes in Brown Norway rats, widely used in glaucoma research, and also develop/evaluate several novel metrics of axonal damage in hypertensive eyes.MethodsLight micrographs of entire ON cross-sections from hypertensive and normotensive eyes were processed through a deep learning-based algorithm, AxoNet2.0, to determine axonal morphological properties and were semiquantitatively scored using the Morrison grading scale (MGS) to provide a damage score independent of AxoNet2.0 outcomes. To construct atlases, ONs were conformally mapped onto an ON "template," and axonal morphometric data was computed for each region. We also developed damage metrics based on myelin morphometry.ResultsIn normotensive eyes, average axon density was ∼0.3 axons/µm2 (i.e., ∼80,000 axons in an ON). We measured axoplasm diameter, eccentricity, cross-sectional area, and myelin g-ratio and thickness. Most morphological parameters exhibited a wide range of coefficients of variation (CoV); however, myelin thickness CoV was only ∼2% in normotensive eyes. In hypertensive eyes, increased myelin thickness correlated strongly with MGS (P < 0.0001).ConclusionsWe present the first comprehensive normative RGC axon morphometric atlas for Brown Norway rat eyes. We suggest objective, repeatable damage metrics based on RGC axon myelin thickness for hypertensive eyes.Translational relevanceThese tools can evaluate regional changes in RGCs and overall levels of damage in glaucoma studies using Brown Norway rats.

| S-EPMC10020949 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data