RGCode

RGCode quantifies retinal ganglion cells from RBPMS-immunostained murine retinal flatmount images to support glaucoma research and neuroprotection studies.

Key Features:

• Automated quantification: Employs a deep learning pipeline that automates RGC quantification across entire murine retinas.
• Input data: Accepts RBPMS-immunostained retinal flatmount images as the primary input for analysis.
• Output metrics: Provides total RGC count, retinal area and density measurements, visualized computed counts, and isodensity maps.
• Training data: Model trained on datasets of RBPMS-stained healthy and glaucomatous retinas from mice subjected to microbead-induced ocular hypertension and optic nerve crush injury paradigms.
• Performance validation: Demonstrated superior performance in RGC quantification compared to manual counting in rodent models.
• Adaptability: Model can be retrained with minimal additional data to count FluoroGold-traced RGCs.

Scientific Applications:

• Glaucoma research: Quantifies RGC survival and loss in murine models to inform studies of glaucoma pathogenesis.
• Therapeutic evaluation: Enables quantitative assessment of neuroprotective interventions by measuring changes in RGC counts and densities.
• Preclinical rodent studies: Supports comparative analysis across injury paradigms such as microbead-induced ocular hypertension and optic nerve crush.

Methodology:

Uses a deep learning pipeline/model trained on RBPMS-stained retinal images from healthy and glaucomatous murine retinas (microbead-induced ocular hypertension and optic nerve crush paradigms) and supports retraining for FluoroGold-traced RGCs.