Deep Learning-Based Model for Automatic Assessment of Anterior Angle Chamber in Ultrasound Biomicroscopy.

OBJECTIVE: The goal of the work described here was to develop and assess a deep learning-based model that could automatically segment anterior chamber angle (ACA) tissues; classify iris curvature (I-Curv), iris root insertion (IRI), and angle closure (AC); automatically locate scleral spur; and measure ACA parameters in ultrasound biomicroscopy (UBM) images. METHODS: A total of 11,006 UBM images were obtained from 1538 patients with primary angle-closure glaucoma who were admitted to the Eye Center of Renmin Hospital of Wuhan University (Wuhan, China) to develop an imaging database. The UNet++ network was used to segment ACA tissues automatically. In addition, two support vector machine (SVM) algorithms were developed to classify I-Curv and AC, and a logistic regression (LR) algorithm was developed to classify IRI. Meanwhile, an algorithm was developed to automatically locate the scleral spur and measure ACA parameters. An external data set of 1,658 images from Huangshi Aier Eye Hospital was used to evaluate the performance of the model under different conditions. An additional 439 images were collected to compare the performance of the model with experts. RESULTS: The model achieved accuracies of 95.2%, 88.9% and 85.6% in classification of AC, I-Curv and IRI, respectively. Compared with ophthalmologists, the model achieved an accuracy of 0.765 in classifying AC, I-Curv and IRI, indicating that its high accuracy was as high as that of the ophthalmologists (p > 0.05). The average relative errors (AREs) of ACA parameters were smaller than 15% in the internal data sets. Intraclass correlation coefficients (ICCs) of all the angle-related parameters were greater than 0.911. ICC values of all iris thickness parameters were greater than 0.884. The accurate measurement of ACA parameters partly depended on accurate localization of the scleral spur (p < 0.001). CONCLUSION: The model could effectively and accurately evaluate the ACA automatically based on fully automated analysis of UBM images, and it can potentially be a promising tool to assist ophthalmologists. The present study suggested that the deep learning model can be extensively applied to the evaluation of ACA and AC-related biometric risk factors, and it may broaden the application of UBM imaging in the clinical research of primary angle-closure glaucoma.

Hybrid Variation-Aware Network for Angle-Closure Assessment in AS-OCT.

Automatic angle-closure assessment in Anterior Segment OCT (AS-OCT) images is an important task for the screening and diagnosis of glaucoma, and the most recent computer-aided models focus on a binary classification of anterior chamber angles (ACA) in AS-OCT, i.e., open-angle and angle-closure. In order to assist clinicians who seek better to understand the development of the spectrum of glaucoma types, a more discriminating three-class classification scheme was suggested, i.e., the classification of ACA was expended to include open-, appositional- and synechial angles. However, appositional and synechial angles display similar appearances in an AS-OCT image, which makes classification models struggle to differentiate angle-closure subtypes based on static AS-OCT images. In order to tackle this issue, we propose a 2D-3D Hybrid Variation-aware Network (HV-Net) for open-appositional-synechial ACA classification from AS-OCT imagery. Specifically, taking into account clinical priors, we first reconstruct the 3D iris surface from an AS-OCT sequence, and obtain the geometrical characteristics necessary to provide global shape information. 2D AS-OCT slices and 3D iris representations are then fed into our HV-Net to extract cross-sectional appearance features and iris morphological features, respectively. To achieve similar results to those of dynamic gonioscopy examination, which is the current gold standard for diagnostic angle assessment, the paired AS-OCT images acquired in dark and light illumination conditions are used to obtain an accurate characterization of configurational changes in ACAs and iris shapes, using a Variation-aware Block. In addition, an annealing loss function was introduced to optimize our model, so as to encourage the sub-networks to map the inputs into the more conducive spaces to extract dark-to-light variation representations, while retaining the discriminative power of the learned features. The proposed model is evaluated across 1584 paired AS-OCT samples, and it has demonstrated its superiority in classifying open-, appositional- and synechial angles.

SD-OCT assessment and visual field changes 1 year or more after a single episode of unilateral acute primary angle closure / Avaliação do SD-OCT e mudanças do campo visual 1 ano ou mais após episódio único de fechamento angular primário agudo unilateral

ABSTRACT Objective: To evaluate structural and visual field (VF) changes after ≥1 year of a single acute primary angle closure (APAC) attack using spectral-domain optical coherence tomography (SD-OCT) and standard automated perimetry (SAP). Methods: Patients with a single unilateral APAC crisis at least 1 year ago were included consecutively from 2013 to 2016. Contralateral eye was used as control. All patients underwent ophthalmic examination, RNFL imaging by SD-OCT, and SAP using Octopus 1-2-3. Results: 54 eyes (27 patients) were enrolled. Male-to-female ratio was 1:2. Mean time for the SD-OCT and SAP assessment after the crisis was 5.0±5.1 (1.0-23.5) years, and IOP was 52.5±9.8 mmHg. In APAC eyes, the thicknesses of all quadrants of peripapillary RNFL (36.3%; P<0.001) and some macular sections (from 2.1% to 4.7%; P<0.01) were reduced compared to contralateral eyes. Additionally, in APAC eyes, the mean defect on VF was negatively and statistically correlated with the reduction of all quadrants of peripapillary RNFL thickness. Conclusion: A single episode of APAC was associated with peripapillary RNFL and macular thickness and with VF defects after ≥1 year of the crisis in the affected eye. Statistically meaningful correlations were found between structural and functional damage.

RESUMO Objetivo: Avaliar alterações estruturais e do campo visual 1 ano ou mais após uma crise única de fechamento angular primário agudo utilizando tomografia de coerência óptica de domínio espectral e perimetria automatizada padronizada. Métodos: Pacientes que apresentaram crise unilateral única de fechamento angular primário agudo há pelo menos 1 ano foram consecutivamente incluídos entre 2013 e 2016. Os olhos contralaterais foram utilizados como controles. Todos os pacientes foram submetidos a exame oftalmológico, avaliação das camadas de fibras nervosas da retina utilizando tomografia de coerência óptica de domínio espectral e perimetria automatizada padronizada com o Octopus 1-2-3. Resultados: Foram incluídos 54 olhos (27 pacientes) com razão homem:mulher de 1:2. O tempo médio após a crise foi de 5,0±5,1 anos (1,0 a 23,5) e a pressão intraocular na crise foi 52,5±9,8mmHg. Nos olhos com fechamento angular primário agudo, todas as espessuras das camadas de fibras nervosas da retina peripapilares (36,3%; p<0,001) e de algumas seções maculares (de 2,1 a 4,7%; p<0,01) estavam reduzidas em comparação aos olhos contralaterais. Além do mais, nos olhos submetidos a fechamento angular primário agudo, o mean defect do campo visual foi estatisticamente e negativamente correlacionado com a redução da espessura de todos os quadrantes peripapilares da camada de fibras nervosas da retina. Conclusão: Um único episódio de fechamento angular primário agudo foi associado com redução na espessura da camada de fibras nervosas da retina peripapilar e da espessura macular e com defeitos de campo visual 1 ano ou mais após a crise no olho afetado. Correlações estatisticamente significativas foram identificadas entre danos estruturais e funcionais.

Ultrasound biomicroscopy in glaucoma assessment.

Ultrasound biomicroscopy (UBM) is an important tool in the diagnosis, evaluation and follow up of glaucoma patients. Even if we are dealing with a primary angle closure glaucoma (PACG) or a primary open angle glaucoma (POAG) patient, the mechanism of angle closure can be revealed by performing an UBM. The device can help differentiate between the two types of glaucoma even in patients with opaque corneas when gonioscopy cannot be performed. Knowing the type of glaucoma is vital, especially regarding an individualized treatment, since each patient is unique and needs to be treated accordingly, in order to prevent glaucomatous optic neuropathy and visual field loss. Abbreviations: AC = anterior chamber, ICE = iridocorneal endothelial syndrome, IOP = intraocular pressure, NTG = normal tension glaucoma, PACG = primary angle closure glaucoma, PC = posterior chamber, PEX = pseudoexfoliation syndrome, POAG = primary open angle glaucoma, UBM = ultrasound biomicroscopy.

Angle-closure assessment in anterior segment OCT images via deep learning.

Precise characterization and analysis of anterior chamber angle (ACA) are of great importance in facilitating clinical examination and diagnosis of angle-closure disease. Currently, the gold standard for diagnostic angle assessment is observation of ACA by gonioscopy. However, gonioscopy requires direct contact between the gonioscope and patients' eye, which is uncomfortable for patients and may deform the ACA, leading to false results. To this end, in this paper, we explore a potential way for grading ACAs into open-, appositional- and synechial angles by Anterior Segment Optical Coherence Tomography (AS-OCT), rather than the conventional gonioscopic examination. The proposed classification schema can be beneficial to clinicians who seek to better understand the progression of the spectrum of angle-closure disease types, so as to further assist the assessment and required treatment at different stages of angle-closure disease. To be more specific, we first use an image alignment method to generate sequences of AS-OCT images. The ACA region is then localized automatically by segmenting an important biomarker - the iris - as this is a primary structural cue in identifying angle-closure disease. Finally, the AS-OCT images acquired in both dark and bright illumination conditions are fed into our Multi-Sequence Deep Network (MSDN) architecture, in which a convolutional neural network (CNN) module is applied to extract feature representations, and a novel ConvLSTM-TC module is employed to study the spatial state of these representations. In addition, a novel time-weighted cross-entropy loss (TC) is proposed to optimize the output of the ConvLSTM, and the extracted features are further aggregated for the purposes of classification. The proposed method is evaluated across 66 eyes, which include 1584 AS-OCT sequences, and a total of 16,896 images. The experimental results show that the proposed method outperforms existing state-of-the-art methods in applicability, effectiveness, and accuracy.

Iridocorneal Angle Assessment After Laser Iridotomy With Swept-source Optical Coherence Tomography.

AIM: To investigate the reliability of anterior chamber angle (ACA) measurements in narrow angles and assess the effect of laser peripheral iridotomy (LPI) on these measurements using novel swept-source optical coherence tomography (SS-OCT) technology. MATERIALS AND METHODS: In this prospective observational study, patients with gonioscopically narrow angles were enrolled and scheduled for prophylactic LPI. Twelve ACA sections were obtained in each eye using SS-OCT (ANTERION, Heidelberg Engineering, Germany) before and after Nd:YAG LPI. A built-in algorithm calculated ACA measurements after manual identification of the scleral spur and ACA recess. Eight ACA parameters were evaluated: ACA (ACA 500, ACA 750); scleral spur angle (SSA 500, SSA 750); angle opening distance (AOD 500, AOD 750); and trabecular iris space area (TISA 500, TISA 750). The effect of LPI was assessed for each parameter, both nasally and temporally. RESULTS: Ten patients (18 eyes) were enrolled (mean age, 61.8±13.6 y; 60.0% female individuals). On average, the ACA was wider nasally than temporally (P=0.004). LPI significantly widened the ACA (range, 26.7-29.4%; P<0.05). ACA 500 increased by 29.4% (P<0.001), ACA 750 by 29.2% (P=0.002), SSA 500 by 27.3% (P=0.003), SSA 750 by 28.1% (P=0.001), AOD 500 by 28.6% (P=0.009), AOD 750 by 28.6% (P=0.003), TISA 500 by 27.3% (P=0.004), and TISA 750 by 26.7% (P=0.200). CONCLUSIONS: SS-OCT ANTERION imaging can be used to reliably measure ACA before and after LPI. ACA, AOD, SSA, and TISA are all valid ACA measurement methods.

Assessment of Schlemm's canal in acute primary angle closure: an anterior segment optical coherence tomography study.

PURPOSE: To image and quantitatively evaluate the Schlemm's canal (SC) dimensions in the eyes with acute primary angle closure (APAC) with anterior segment optical coherence tomography (AS-OCT), and compare it with the SC measurements taken after the control of intraocular pressure (IOP) and in the normal age-matched controls. MATERIALS AND METHODS: Seventeen eyes of 14 patients with the newly diagnosed APAC and 59 age-matched normal subjects underwent AS-OCT to image SC. SC cross-sectional area, SC meridional and coronal diameters were measured in the temporal and nasal regions at 3 and 9 o'clock position. After laser iridotomy and control of the IOP, all SC parameters were measured again at a week later, in APAC eyes. Intrasession intraobserver reliability of the SC measurements was assessed with intraclass correlation coefficient. RESULTS: Mean SC-SCA (10,600 ± 2691 µm2), SC meridional (682 ± 125 µm) and coronal diameters (21.2 ± 8.2 µm) showed a significant increase in the APAC eyes at presentation, when compared to the SC parameters measured at a week later (6499 ± 1754 µm2, 450 ± 169 µm and 15.75 ± 8.6 µm, p = < 0.0001, < 0.0001 and 0.01, respectively) and in the normal controls (7192 ± 1022 µm2, 499.2 ± 179.8 µm, 15.43 ± 4.35 µm, p = 0.02, < 0.0001, 0.01, respectively). There was no difference in the measured SC parameters between the normal controls and APAC eyes, when the parameters were measured at a week, after resolution of the acute attack (all p > 0.05). CONCLUSION: A significant expansion of SC was observed in the APAC eyes at presentation, when compared to the normal controls and after the acute attack resolved. SC parameters may provide a useful research tool for evaluating morphological changes in the SC in APAC eyes, during an acute attack.

Assessment of Circumferential Angle Closure with Swept-Source Optical Coherence Tomography: a Community Based Study.

PURPOSE: To evaluate the diagnostic performance of swept-source optical coherence tomography (SS-OCT, CASIA SS-1000; Tomey Corporation, Nagoya, Japan) for angle closure detection, in comparison with gonioscopy, in a community setting. DESIGN: Reliability analysis. METHODS: A total of 2027 phakic subjects aged ≥50 years, with no previous history of glaucoma, laser (including peripheral iridotomy), intraocular surgery, or ocular trauma, were consecutively recruited from a community polyclinic in Singapore. Gonioscopy was performed by a single trained ophthalmologist. SS-OCT angle scans, which obtain radial scans for the entire circumference of the angle, were analyzed by a single examiner, masked to the subject's clinical details. On SS-OCT images, angle closure was defined as contact between the iris and any part of the angle wall anterior to the scleral spur. Different cutoff values of the degree of circumferential angle closure (≥35%, ≥50%, and ≥75%) were taken for analysis to assess SS-OCT performance in detecting angle closure. RESULTS: A total of 1857 subjects (91.6%) were included in the final analysis after excluding poor-quality SS-OCT scans. Almost 90% of the subjects were Chinese, with a mean age of 61.8 ± 6.7 years, and more than half were women (63.5%). The overall AUC of SS-OCT manual grading against gonioscopy was 0.84 (95% confidence interval, 0.81-0.88). The prevalence of angle closure on SS-OCT was 26.1% for the ≥35% definition, with an area under the curve of 0.80 (0.77-0.84), sensitivity of 82.5% (75.3%-88.4%), and specificity of 78.5% (76.5%-80.4%). The first-order agreement coefficient statistics for the 2-quadrant gonioscopic definition of angle-closure with corresponding ≥35%, ≥50%, and ≥75% angle closure definitions for SS-OCT were good at 0.89 (0.83-0.93), 0.88 (0.842-0.93), and 0.88 (0.831-0.99), respectively. CONCLUSIONS: In this large community-based study, SS-OCT exhibited moderate performance for angle closure detection compared to gonioscopy as the reference standard.

Ultrasound biomicroscopic assessment of angle parameters in patients with primary angle closure glaucoma undergoing phacoemulsification.

PURPOSE: To evaluate the effect of phacoemulsification and foldable intraocular lens (IOL) implantation on biometric determinants of the anterior chamber angle in primary angle closure glaucoma (PACG) using ultrasound biomicroscopy (UBM). METHODS: Forty-six eyes of 46 patients with chronic PACG and cataract having a patent laser iridotomy were included in this prospective, interventional case series. Angle parameters were measured using UBM before surgery and 3 months after phacoemulsification with IOL implantation. Intraocular pressure (IOP) was measured by applanation tonometer and records of glaucoma medication administered were maintained. Main outcome measures were IOP, central anterior chamber depth (ACD), trabecular iris angle (TIA), and angle opening distance at 250 and 500 µm from scleral spur (AOD250 and AOD500). RESULTS: The mean age of study participants was 56.5 ± 9.9 years (range 44-75). The preoperative mean IOP was 25.0 ± 5.4 mmHg on maximum antiglaucoma medication, which was reduced to 15.8 ± 3.8 mmHg (p = 0.0001) at 3 months. Number of antiglaucoma medications also decreased from 2.4 ± 1.1 to 0.4 ± 1.1 (p = 0.0001). There was a significant widening of the anterior chamber angle with the TIA increasing significantly after phacoemulsification (p<0.001) with an associated increase in AOD250, AOD500, and ACD (p<0.001). CONCLUSIONS: Phacoemulsification in eyes with PACG results in significant widening of the anterior chamber angle. This results in better IOP control after surgery and decreases the need for glaucoma medications. These findings are of clinical significance in obviating the need for simultaneous filtering surgery in eyes with PACG undergoing phacoemulsification cataract surgery.

Qualitative assessment of ultrasound biomicroscopic images using standard photographs: the liwan eye study.

Objective. To classify anatomic features related to anterior chamber angles by a qualitative assessment system based on ultrasound biomicroscopy (UBM) images. Methods. Cases of primary angle-closure suspect (PACS), defined by pigmented trabecular meshwork that is not visible in two or more quadrants on static gonioscopy (cases) and systematically selected subjects (1 of every 10) who did not meet this criterion (controls) were enrolled during a population-based survey in Guangzhou, China. All subjects underwent UBM examination. A set of standard UBM images was used to qualitatively classify anatomic features related to the angle configuration, including iris thickness, iris convexity, iris angulation, ciliary body size, and ciliary process position. All analysis was conducted on right eye images. Results. Based on the qualitative grades, the difference in overall iris thickness between gonioscopically narrow eyes (n = 117) and control eyes (n = 57) was not statistically significant. The peripheral one third of the iris tended to be thicker in all quadrants of the PACS eyes, although the difference was statistically significant only in the superior quadrant (P = 0.008). No significant differences were found in the qualitative classifications of iris insertion, iris angulation, ciliary body size, and ciliary process position. The findings were similar when compared with the control group of eyes with wide angles in all quadrants. Conclusions. Basal iris thickness seems to be more relevant to narrow angle configuration than to overall iris thickness. Otherwise, the anterior rotation and size of the ciliary body, the iris insertion, and the overall iris thickness are comparable in narrow- and wide-angle eyes.