(Georgia Institute of Technology, 2020-05)
Ritch, Matthew D.
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.
(Georgia Institute of Technology, 2019-05)
Hardie, Rebecca
Affecting more than 70 million people worldwide, glaucoma is one of the leading causes of vision loss and blindness. Although the exact origins of glaucoma are still unknown, elevated intraocular pressure is a well-established risk factor. Intraocular pressure is primarily regulated by the trabecular meshwork, a tissue located in the anterior segment of the eye which drains aqueous humor. The cellularity of the trabecular meshwork is shown to be significantly reduced in glaucoma. This loss of cellularity presumably leads to reduced trabecular meshwork function and increased outflow resistance, which in turn leads to elevated intraocular pressure. In order to assess regenerative medicine therapies for glaucoma, the damage to the trabecular meshwork observed in glaucoma must be properly modeled. This study demonstrates that oxidative stress caused by hydrogen peroxide can reduce trabecular meshwork cellularity to glaucomatous levels in a porcine anterior chamber organ culture model. The diminished trabecular meshwork cellularity resulted in a loss of intraocular pressure homeostasis and the hydrogen peroxide treatment did not permanently damage the trabecular meshwork. This porcine organ culture model provides a platform for evaluating trabecular meshwork regenerative medicine therapies that could be possibly used to treat glaucoma.