Recent developments in the use of artificial intelligence in the diagnosis and monitoring of glaucoma are discussed. To set the context and fix terminology, a brief historic overview of artificial intelligence is provided, along with some fundamentals of statistical modeling. Next, recent applications of artificial intelligence techniques in glaucoma diagnosis and the monitoring of glaucoma progression are reviewed, including the classification of visual field images and the detection of glaucomatous change in retinal nerve fiber layer thickness. Current challenges in the direct application of artificial intelligence to further our understating of this disease are also outlined. The article also discusses how the combined use of mathematical modeling and artificial intelligence may help to address these challenges, along with stronger communication between data scientists and clinicians.
Ocular surface disease is characterized by tear film instability and histopathologic and clinical changes of
the ocular surface. Glaucoma patients often suffer from ocular surface disease caused by the chronic use of
preserved medical treatment to reduce intraocular pressure. Benzalkonium chloride is the preservative most
frequently used in glaucoma medications. Its effect on tear film, conjunctiva and cornea and the consequences in
glaucoma management are discussed in this mini-review.
Purpose:
To describe new software tools for quantifying optic nerve head drusen volume using 3-dimensional (3D) swept-source optical coherence tomography (SS-OCT) volumetric scans.
Materials and Methods:
SS-OCT was used to acquire raster volume scans of 8 eyes of 4 patients with bilateral optic nerve head drusen. The scans were manually segmented by 3 graders to identify the drusen borders, and thereafter total drusen volumes were calculated. Linear regression was performed to study the relationships between drusen volume, retinal nerve fiber layer thickness, and Humphrey visual field mean deviation.
Results:
In the 8 study eyes, drusen volumes ranged between 0.24 to 1.05 mm3. Visual field mean deviation decreased by ∼20 dB per cubic millimeter increase in drusen volume, and the coefficient of correlation of the linear regression was 0.92. In this small patient series, visual field defects were detected when drusen volume was larger than about 0.2 mm3.
Conclusions:
Software tools have been developed to quantify the size of OHND using SS-OCT volume scans.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.