An objective structural and functional reference standard in glaucoma

Abstract

The current lack of consensus for diagnosing glaucoma makes it difficult to develop diagnostic tests derived from deep learning (DL) algorithms. In the present study, we propose an objective definition of glaucomatous optic neuropathy (GON) using clearly defined parameters from optical coherence tomography and standard automated perimetry. We then use the proposed objective definition as reference standard to develop a DL algorithm to detect GON on fundus photos. A DL algorithm was trained to detect GON on fundus photos, using the proposed objective definition as reference standard. The performance was evaluated on an independent test sample with sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and likelihood ratios (LR). The test sample had 2118 fundus photos from 585 eyes of 405 individuals. The AUC to discriminate between GON and normal was 0.92 with sensitivity of 77% at 95% specificity. LRs indicated that the DL algorithm provided large changes in the post-test probability of disease for the majority of eyes. A DL algorithm to evaluate fundus photos had high performance to discriminate GON from normal. The newly proposed objective definition of GON used as reference standard may increase the comparability of diagnostic studies of glaucoma across devices and populations.

The use of deep learning technology for the detection of optic neuropathy

“…In a recent study, Mariottoni et al (76) proposed a set of relatively uncomplicated structural and functional parameters which can be integrated in an objective approach as a reliable reference standard for the research and development of glaucoma AI diagnosis models. According to the RNFL evaluation of SD-OCT and the visual field evaluation of standard automatic visual field examination, the diagnostic criteria of glaucoma optic neuropathy should include the corresponding structural and functional damage.…”

Association Between Serum Vitamin D Level and Rates of Structural and Functional Glaucomatous Progression

“…To define subgroups of glaucoma and suspect eyes, we used a recently developed objective criteria for glaucomatous optic neuropathy based on both visual field and OCT data. 22 In contrast, the aforementioned large cross-sectional studies defined glaucoma based on clinician grading of a single fundus photo. 13,14 This is problematic given the poor interrater reliability of subjective optic disc gradings that has been widely documented in the literature.…”

“…12,29 While some others did incorporate both perimetry and structural data in classifying glaucoma patients, 11,27 they were still subjective in nature. By using a clearly outlined objective criteria 22 to define glaucoma and suspect eyes in our study, our design is more reproducible and may be free from biases arising from subjective gradings. However, it is possible that some of the eyes may have been classified differently had other proposed classification schemes been used.…”

Assessing glaucoma in retinal fundus photographs using Deep Feature Consistent Variational Autoencoders

“…Included eyes were classified into glaucoma or normal based on a structure and function objective reference standard previously described [22], applied to the tests at baseline. In brief, the objective criteria for glaucomatous optic neuropathy accounts for the presence and correspondence of structural and functional defects, defined from parameters from SDOCT and SAP.…”