Literature Review on Artificial Intelligence Methods for Glaucoma Screening, Segmentation, and Classification

Abstract

Artificial intelligence techniques are now being applied in different medical solutions ranging from disease screening to activity recognition and computer-aided diagnosis. The combination of computer science methods and medical knowledge facilitates and improves the accuracy of the different processes and tools. Inspired by these advances, this paper performs a literature review focused on state-of-the-art glaucoma screening, segmentation, and classification based on images of the papilla and excavation using deep learning techniques. These techniques have been shown to have high sensitivity and specificity in glaucoma screening based on papilla and excavation images. The automatic segmentation of the contours of the optic disc and the excavation then allows the identification and assessment of the glaucomatous disease’s progression. As a result, we verified whether deep learning techniques may be helpful in performing accurate and low-cost measurements related to glaucoma, which may promote patient empowerment and help medical doctors better monitor patients.

Applications of Artificial Intelligence and Deep Learning in Glaucoma

“…There are 17 publicly available data sets with glaucoma data globally, the majority of which contain fundus photos 140. Several of these publicly available data sets have been used in the literature for training and external validation for segmentation and classification tasks for optic discs from fundus photos 26,36,141,142. For example, DRISHTI-GS, a publicly available retinal image data set, is comprised of 50 training images and 51 test images of normal and glaucomatous eyes that includes manual segmentation of ONH parameters performed by 4 specialists 36.…”

“…Especially in such instances, image resolution becomes a key limiting factor to analysis and can affect preprocessing steps such as image channel selection, illumination normalization, contrast enhancement, and the extraction of blood vessels. 36 High-quality images from eyes with media opacities, with movement artifacts, or anterior segment pathology can be difficult to obtain. Another fundamental challenge is that clinical glaucoma evaluation generally requires integrated analysis of multiple modalities (eg, clinical examination, ONH imaging, and VF testing) to determine the glaucoma subtypes and any progression, not only fundus photo findings.…”

“…140 Several of these publicly available data sets have been used in the literature for training and external validation for segmentation and classification tasks for optic discs from fundus photos. 26,36,141,142 For example, DRISHTI-GS, a publicly available retinal image data set, is comprised of 50 training images and 51 test images of normal and glaucomatous eyes that includes manual segmentation of ONH parameters performed by 4 specialists. 36 Other commonly used data sets of fundus photos include ACRIMA, RIM-ONE, High-Resolution Fundus, the Optic Nerve Head Segmentation Data Set, ORIGA database, and the Singapore Chinese and Indian Eye Studies.…”

Clinical pharmacology and pharmacogenetics of prostaglandin analogues in glaucoma

“…Glaucoma is classified into open-angle glaucomas (OAGs), angle-closure glaucoma (ACGs) based on the anatomic status of the anterior chamber angle ( Kang and Tanna, 2021 ). The most frequent type may differ from one region of the world to another ( Schuster et al, 2020 ; Camara et al, 2022 ). For instance, ACGs is more prevalent in certain regions of Asia, whereas OAGs is more equally distributed throughout the world.…”

Accuracy and feasibility with AI-assisted OCT in retinal disorder community screening

“…The application of DL in medicine has fulfilled the function of automated lesion recognition and prognosis prediction in various diseases ( Gulshan et al, 2016 ; Zhang Q. et al, 2021 ). In the field of ophthalmology, different AI algorithms have been developed and applied for auto-detection of diverse diseases like glaucoma ( Keel et al, 2019 ; Camara et al, 2022 ), ocular surface diseases ( Zhang Y. Y. et al, 2021 ), and multiple retinal disorders, like DR, AMD, and myopic retinopathy, and have exhibited relatively high accuracy and reliable performance in clinical diagnosis as well as the pre-hospital community screening, providing a promising solution for the challenge mentioned previously ( Rajalakshmi et al, 2018 ; He et al, 2020 ; Xie et al, 2020 ; Cen et al, 2021 ).…”