Global Search

Search articles, concepts, and chapters

Br J OphthalmolApril 202126 citations

Towards 'automated gonioscopy': a deep learning algorithm for 360° angle assessment by swept-source optical coherence tomography.

Porporato Natalia, Tun Tin A, Baskaran Mani, Wong Damon W K, Husain Rahat, Fu Huazhu, Sultana Rehena, Perera Shamira, Schmetterer Leopold, Aung Tin


AI Summary

A deep learning algorithm accurately detected gonioscopic angle closure from SS-OCT scans, offering a promising foundation for future automated, non-contact glaucoma screening.

Abstract

Aims

To validate a deep learning (DL) algorithm (DLA) for 360° angle assessment on swept-source optical coherence tomography (SS-OCT) (CASIA SS-1000, Tomey Corporation, Nagoya, Japan).

Methods

This was a reliability analysis from a cross-sectional study. An independent test set of 39 936 SS-OCT scans from 312 phakic subjects (128 SS-OCT meridional scans per eye) was analysed. Participants above 50 years with no previous history of intraocular surgery were consecutively recruited from glaucoma clinics. Indentation gonioscopy and dark room SS-OCT were performed. Gonioscopic angle closure was defined as non-visibility of the posterior trabecular meshwork in ≥180° of the angle. For each subject, all images were analysed by a DL-based network based on the VGG-16 architecture, for gonioscopic angle-closure detection. Area under receiver operating characteristic curves (AUCs) and other diagnostic performance indicators were calculated for the DLA (index test) against gonioscopy (reference standard).

Results

Approximately 80% of the participants were Chinese, and more than half were women (57.4%). The prevalence of gonioscopic angle closure in this hospital-based sample was 20.2%. After analysing a total of 39 936 SS-OCT scans, the AUC of the DLA was 0.85 (95% CI:0.80 to 0.90, with sensitivity of 83% and a specificity of 87%) to classify gonioscopic angle closure with the optimal cut-off value of >35% of circumferential angle closure.

Conclusions

The DLA exhibited good diagnostic performance for detection of gonioscopic angle closure on 360° SS-OCT scans in a glaucoma clinic setting. Such an algorithm, independent of the identification of the scleral spur, may be the foundation for a non-contact, fast and reproducible 'automated gonioscopy' in future.


MeSH Terms

AlgorithmsAnterior Eye SegmentCross-Sectional StudiesDeep LearningFemaleGlaucoma, Angle-ClosureGonioscopyHumansIntraocular PressureMaleReproducibility of ResultsTomography, Optical Coherence

Key Concepts5

The deep learning algorithm (DLA) demonstrated an Area Under Receiver Operating Characteristic Curve (AUC) of 0.85 (95% CI: 0.80 to 0.90) for classifying gonioscopic angle closure with an optimal cut-off value of >35% of circumferential angle closure, achieving a sensitivity of 83% and a specificity of 87% when compared against gonioscopy as the reference standard.

DiagnosisCross-sectionalReliability Analysis from Cross-sectional Studyn=39,936 SS-OCT scans from 312 phakic s…Ch4

The deep learning algorithm (DLA) exhibited good diagnostic performance for detection of gonioscopic angle closure on 360° SS-OCT scans in a glaucoma clinic setting, suggesting it may be the foundation for a non-contact, fast and reproducible 'automated gonioscopy' independent of scleral spur identification.

DiagnosisCross-sectionalReliability Analysis from Cross-sectional Studyn=39,936 SS-OCT scans from 312 phakic s…Ch4

A deep learning algorithm (DLA) based on the VGG-16 architecture was validated for 360° angle assessment on swept-source optical coherence tomography (SS-OCT) (CASIA SS-1000, Tomey Corporation, Nagoya, Japan).

MethodologyCross-sectionalReliability Analysis from Cross-sectional Studyn=39,936 SS-OCT scans from 312 phakic s…Ch4

The independent test set for validating the deep learning algorithm consisted of 39,936 SS-OCT scans from 312 phakic subjects (128 SS-OCT meridional scans per eye) who were above 50 years with no previous history of intraocular surgery and were consecutively recruited from glaucoma clinics.

MethodologyCross-sectionalReliability Analysis from Cross-sectional Studyn=39,936 SS-OCT scans from 312 phakic s…Ch4Ch10

The prevalence of gonioscopic angle closure in this hospital-based sample of 312 phakic subjects was 20.2%.

EpidemiologyCross-sectionalReliability Analysis from Cross-sectional Studyn=312 phakic subjectsCh4Ch10

Is this article assigned to the wrong chapter(s)? Let us know.