Original articleClassification Algorithms Based on Anterior Segment Optical Coherence Tomography Measurements for Detection of Angle Closure
Section snippets
Methods
This was an analysis of prospectively collected data from a community-based study performed in Singapore.15 Approval for the study was granted by the Singapore Eye Research Institute institutional review board. The study was conducted in accordance with the Declaration of Helsinki, and written informed consent was obtained from all subjects before enrolment into the study. The study population consisted of subjects aged ≥50 years recruited from a government-run, community-based clinic facility
Results
We recruited 2047 subjects into the study, of whom 679 were excluded for the following reasons: 11 could not undergo gonioscopy; 97 had incomplete demographic or biometric measurements; 62 could not complete the ASOCT examination or had poor quality ASOCT images; 42 had software delineation errors; and 467 had scleral spurs that were not clearly visible on ASOCT images. Therefore, data from 1368 subjects (66.8%) were included in the analysis. Of these, 750 (54.8%) were female, and 1232 (90.0%)
Discussion
Classification algorithms looking only at a single horizontal scan of the anterior segment using the ASOCT were able to identify nearly all cases of gonioscopic angle closure with close to 80% specificity and an AUC of 0.95. The full variable set consisting of 4 biometric, demographic, and ASOCT-derived parameters, as well as the reduced set, which solely relied on 6 ASOCT parameters, performed similarly across the different classification algorithms and training validation data. Furthermore,
References (29)
- et al.
Visual field loss from primary angle-closure glaucoma: a comparative study of symptomatic and asymptomatic disease
Ophthalmology
(2004) - et al.
Biometry and primary angle-closure glaucoma among Chinese, white, and black populations
Ophthalmology
(1997) - et al.
Novel association of smaller anterior chamber width with angle closure in Singaporeans
Ophthalmology
(2010) - et al.
Quantitative iris parameters and association with narrow angles
Ophthalmology
(2010) - et al.
Lens vault, thickness and position in Chinese subjects with angle closure
Ophthalmology
(2011) - et al.
Determinants of angle width in Chinese Singaporeans
Ophthalmology
(2012) - et al.
Blindness and long-term progression of visual field defects in Chinese patients with primary angle-closure glaucoma
Am J Ophthalmol
(2011) - et al.
Optical coherence tomography quantitative analysis of iris volume changes after pharmacologic mydriasis
Ophthalmology
(2010) - et al.
The number of people with glaucoma worldwide in 2010 and 2020
Br J Ophthalmol
(2006) - et al.
Glaucoma in China: how big is the problem?
Br J Ophthalmol
(2001)
Ocular parameters in subgroups of angle closure glaucoma
Clin Experiment Ophthalmol
Anterior chamber depth and the risk of primary angle closure in 2 East Asian populations
Arch Ophthalmol
YAG laser iridotomy treatment for primary angle closure in East Asian eyes
Br J Ophthalmol
Detection of gonioscopically occludable angles and primary angle closure glaucoma by estimation of limbal chamber depth in Asians: modified grading scheme
Br J Ophthalmol
Cited by (70)
Anterior Segment OCT for Detection of Narrow Angles: A Community-Based Diagnostic Accuracy Study
2024, Ophthalmology GlaucomaAssessment of angle closure disease in the age of artificial intelligence: A review
2024, Progress in Retinal and Eye ResearchDeep Learning Classification of Angle Closure based on Anterior Segment OCT
2024, Ophthalmology GlaucomaAnterior segment optical coherence tomography (AS-OCT) image analysis methods and applications: A systematic review
2022, Computers in Biology and MedicineCitation Excerpt :In contrast to previous studies, Xu et al. [45]. proposed a new ML approach based on a SVM linear classifier [13,29]. In this study, two types of features were extracted: visual and clinical.
Evaluation of the Diagnostic Performance of Swept-Source Anterior Segment Optical Coherence Tomography in Primary Angle Closure Disease
2022, American Journal of OphthalmologyCitation Excerpt :With the addition of minimal clinical information, SS-OCT was able to distinguish PAC/PACG from PACS with 82.0% sensitivity and 62.8% specificity, confirmed through an independent validation dataset. Anterior segment imaging has demonstrated general agreement with gonioscopy,17,18 and SS-OCT in particular has the advantage of being able to rapidly image all 360° of the anterior chamber, enabling extraction of much more data than traditional AS-OCT. In this study, we obtained data from 8 scans per eye including horizontal, vertical, and oblique scans as the 80° to 260° scan was previously reported to have the highest correlation with gonioscopy.19
Manuscript no. 2012-322.
Financial Disclosure(s): The authors have no proprietary or commercial interest in any of the materials discussed in this article.
Supported by grants from the Biomedical Research Council Translational Clinical Research (TCR) Partnership (TCR0101674) Singapore and the National Medical Research Council Clinician Scientist Award (NMRC/CSA/004/2008), Singapore.