Macular Diagnostic Ability in OCT for Assessing Glaucoma in High Myopia

Deep Learning Evaluation of Glaucoma Detection Using Fundus Photographs in Highly Myopic Populations

OBJECTIVES

This study aimed to use deep learning to identify glaucoma and normal eyes in groups with high myopia using fundus photographs.

METHODS

Patients who visited Tri-Services General Hospital from 1 November 2018 to 31 October 2022 were retrospectively reviewed. Patients with high myopia (spherical equivalent refraction of ≤-6.0 D) were included in the current analysis. Meanwhile, patients with pathological myopia were excluded. The participants were then divided into the high myopia group and high myopia glaucoma group. We used two classification models with the convolutional block attention module (CBAM), an attention mechanism module that enhances the performance of convolutional neural networks (CNNs), to investigate glaucoma cases. The learning data of this experiment were evaluated through fivefold cross-validation. The images were categorized into training, validation, and test sets in a ratio of 6:2:2. Grad-CAM visual visualization improved the interpretability of the CNN results. The performance indicators for evaluating the model include the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity.

RESULTS

A total of 3088 fundus photographs were used for the deep-learning model, including 1540 and 1548 fundus photographs for the high myopia glaucoma and high myopia groups, respectively. The average refractive power of the high myopia glaucoma group and the high myopia group were -8.83 ± 2.9 D and -8.73 ± 2.6 D, respectively (p = 0.30). Based on a fivefold cross-validation assessment, the ConvNeXt_Base+CBAM architecture had the best performance, with an AUC of 0.894, accuracy of 82.16%, sensitivity of 81.04%, specificity of 83.27%, and F1 score of 81.92%.

CONCLUSIONS

Glaucoma in individuals with high myopia was identified from their fundus photographs.

Optical Coherence Tomography (OCT): A Brief Look at the Uses and Technological Evolution of Ophthalmology

Medical imaging is the mainstay of clinical diagnosis and management. Optical coherence tomography (OCT) is a non-invasive imaging technology that has revolutionized the field of ophthalmology. Since its introduction, OCT has undergone significant improvements in image quality, speed, and resolution, making it an essential diagnostic tool for various ocular pathologies. OCT has not only improved the diagnosis and management of ocular diseases but has also found applications in other fields of medicine. In this manuscript, we provide a brief overview of the history of OCT, its current uses and diagnostic capabilities to assess the posterior segment of the eye, and the evolution of this technology from time-domain (TD) to spectral-domain (SD) and swept-source (SS). This brief review will also discuss the limitations, advantages, disadvantages, and future perspectives of this technology in the field of ophthalmology.

Macula structural and vascular differences in glaucoma eyes with and without high axial myopia

AIMS

To identify clinically relevant parameters for identifying glaucoma in highly myopic eyes, an investigation was conducted of the relationship between the thickness of various retinal layers and the superficial vessel density (sVD) of the macula with axial length (AL) and visual field mean deviation (VFMD).

METHODS

270 glaucoma patients (438 eyes) participating in the Diagnostic Innovations in Glaucoma cross-sectional study representing three axial myopia groups (non-myopia: n=163 eyes; mild myopia: n=218 eyes; high myopia (AL>26 mm): n=57 eyes) who completed macular optical coherence tomography (OCT) and OCT-angiography imaging were included. Associations of AL and VFMD with the thickness of the ganglion cell inner plexiform layer (GCIPL), macular retinal nerve fibre layer (mRNFL), ganglion cell complex (GCC), macular choroidal thickness (mCT) and sVD were evaluated.

RESULTS

Thinner Global GCIPL and GCC were significantly associated with worse VFMD (R2=34.5% and R2=32.9%; respectively p<0.001), but not with AL (all p>0.1). Thicker mRNFL showed a weak association with increasing AL (R2=2.4%; p=0.005) and a positive association with VFMD (global R2=19.2%; p<0.001). Lower sVD was weakly associated with increasing AL (R2=1.8%; p=0.028) and more strongly associated with more severe glaucoma VFMD (R2=29.6%; p<0.001). Thinner mCT was associated with increasing AL (R2=15.5% p<0.001) and not associated with VFMD (p=0.194). mRNFL was thickest while mCT was thinnest in all sectors of high myopic eyes.

CONCLUSIONS

As thinner GCIPL and GCC were associated with increasing severity of glaucoma but were not significantly associated with AL, they may be useful for monitoring glaucoma in highly myopic eyes.

Consistency between optical coherence tomography and humphrey visual field for evaluating glaucomatous defects in high myopic eyes

Background

The study is to investigate the influence of high myopia on the consistency between optical coherence tomography (OCT) and visual field in primary open-angle glaucoma (POAG).

Methods

We enrolled 37 patients with POAG with high myopia (POAG-HM group), 27 patients with POAG without high myopia (POAG group), and 29 controls with high myopia (HM group). All subjects underwent Humphrey perimetry (30–2 and 10–2 algorithms). The peripapillary retinal nerve fiber layer (RNFL) and macular ganglion cell-inner plexiform layer (GCIPL) thicknesses were measured using Cirrus HD-OCT. Spearman’s rank correlation analysis was used to determine correlations between OCT and perimetric parameters. Agreement was analyzed by cross-classification and weighted κ statistics.

Results

In POAG group, the cross-classification analysis showed strong agreement between the inferior temporal GCIPL thickness and the mean sensitivity (MS) of 10–2 algorithms (κ = 0.5447, P = 0.0048), and good agreement between the superior and inferior RNFL thicknesses and 30–2 MS (κ = 0.4407 and 0.4815; P < 0.05). In the POAG-HM group, only the inferior temporal GCIPL thickness showed good agreement with 10–2 MS (κ = 0.3155, P = 0.0289) and none of the RNFL sectors were in good agreement with the corresponding MS.

Conclusions

In POAG patients with high myopia, changes in macular measurements were in accordance with visual field defects, and RNFL thickness did not consistently decline with visual field defects due to the effects of high myopia. This study suggests that during diagnosis and follow-up of glaucoma with high myopia, more attention need to be focused on structure and functional defects in macular areas.

Macular imaging with optical coherence tomography in glaucoma

With the advent of spectral-domain optical coherence tomography, imaging of the posterior segment of the eye can be carried out rapidly at multiple anatomical locations, including the optic nerve head, circumpapillary retinal nerve fiber layer, and macula. There is now ample evidence to support the role of spectral-domain optical coherence tomography imaging of the macula for detection of early glaucoma. Macular spectral-domain optical coherence tomography measurements demonstrate high reproducibility, and evidence on its utility for detection of glaucoma progression is accumulating. We present a comprehensive review of macular spectral-domain optical coherence tomography imaging emerging as an essential diagnostic tool in glaucoma.

Early diagnostic parameters of glaucoma in high myopes

PURPOSE

The goal of this study was to assess changes in OCT parameters occurring in high myopic glaucoma patients, so as to enable early diagnosis and prevention of progressive glaucomatous damage. It was performed at the department of ophthalmology, Kasr Alainy Hospital, Cairo University, over a twenty-month period.

METHODS

This study was a cross-sectional randomized single blinded study. It included 62 eyes of highly myopic individuals. Patients were divided into 2 groups: Group A included myopic non-glaucomatous individuals, and Group B included the myopic glaucoma patients. All patients had a full ophthalmological examination, as well as OCT assessment of the RNFL, GCC and ONH parameters. The VF was tested as well as AXL and CCT. Correlation of the data was performed.

RESULTS

Regarding the GLV, its mean in group A was 11.88±6.71% versus 19.69±9.69% in group B; the difference between both groups was statistically significant (P=0.001). Regarding the cup area, the mean in group A was 0.51±0.41mm², while that in group B was 1.25±0.72mm²; the difference between both groups was statistically significant (P<0.001).

CONCLUSION

The ONH parameter, cup area, and the GCC parameter, GLV, are key parameters in supporting the diagnosis of glaucoma in myopic patients. Other parameters measured by OCT, such as inferior RNFL thickness, FLV, and C/D ratio, could aid in diagnosis as well.

Imaging in myopia: potential biomarkers, current challenges and future developments

Myopia is rapidly increasing in Asia and around the world, while it is recognised that complications from high myopia may cause significant visual impairment. Thus, imaging the myopic eye is important for the diagnosis of sight-threatening complications, monitoring of disease progression and evaluation of treatments. For example, recent advances in high-resolution imaging using optical coherence tomography may delineate early myopic macula pathology, optical coherence tomography angiography may aid early choroidal neovascularisation detection, while multimodal imaging is important for monitoring treatment response. However, imaging the eye with high myopia accurately has its challenges and limitations, which are important for clinicians to understand in order to choose the best imaging modality and interpret the images accurately. In this review, we present the current imaging modalities available from the anterior to posterior segment of the myopic eye, including the optic nerve. We summarise the clinical indications, image interpretation and future developments that may overcome current technological limitations. We also discuss potential biomarkers for myopic progression or development of complications, including basement membrane defects, and choroidal atrophy or choroidal thickness measurements. Finally, we present future developments in the field of myopia imaging, such as photoacoustic imaging and corneal or scleral biomechanics, which may lead to innovative treatment modalities for myopia.

Optical coherence tomography for glaucoma diagnosis: An evidence based meta-analysis

Purpose

Early detection, monitoring and understanding of changes in the retina are central to the diagnosis of glaucomatous optic neuropathy, and vital to reduce visual loss from this progressive condition. The main objective of this investigation was to compare glaucoma diagnostic accuracy of commercially available optical coherence tomography (OCT) devices (Zeiss Stratus, Zeiss Cirrus, Heidelberg Spectralis and Optovue RTVue, and Topcon 3D-OCT).

Patients

16,104 glaucomatous and 11,543 normal eyes reported in 150 studies.

Methods

Between Jan. 2017 and Feb 2017, MEDLINE^®, EMBASE^®, CINAHL^®, Cochrane Library^®, Web of Science^®, and BIOSIS^® were searched for studies assessing glaucoma diagnostic accuracy of the aforementioned OCT devices. Meta-analysis was performed pooling area under the receiver operating characteristic curve (AUROC) estimates for all devices, stratified by OCT type (RNFL, macula), and area imaged.

Results

150 studies with 16,104 glaucomatous and 11,543 normal control eyes were included. Key findings: AUROC of glaucoma diagnosis for RNFL average for all glaucoma patients was 0.897 (0.887–0.906, n = 16,782 patient eyes), for macula ganglion cell complex (GCC) was 0.885 (0.869–0.901, n = 4841 eyes), for macula ganglion cell inner plexiform layer (GCIPL) was 0.858 (0.835–0.880, n = 4211 eyes), and for total macular thickness was 0.795 (0.754–0.834, n = 1063 eyes).

Conclusion

The classification capability was similar across all 5 OCT devices. More diagnostically favorable AUROCs were demonstrated in patients with increased glaucoma severity. Diagnostic accuracy of RNFL and segmented macular regions (GCIPL, GCC) scans were similar and higher than total macular thickness. This study provides a synthesis of contemporary evidence with features of robust inclusion criteria and large sample size. These findings may provide guidance to clinicians when navigating this rapidly evolving diagnostic area characterized by numerous options.

A sloped piecemeal Gaussian model for characterising foveal pit shape

PURPOSE

High-quality optical coherence tomography (OCT) macular scans make it possible to distinguish a range of normal and diseased states by characterising foveal pit shape. Existing mathematical models lack the flexibility to capture all known pit variations and thus characterise the pit with limited accuracy. This study aimed to develop a new model that provides a more robust characterisation of individual foveal pit variations.

METHODS

A Sloped Piecemeal Gaussian (SPG) model, consisting of a linear combination of a tilted line and a piecemeal Gaussian function (two halves of a Gaussian connected by a separate straight line), was developed to fit retinal thickness data with the flexibility to characterise different degrees of pit asymmetry and pit bottom flatness. It fitted the raw pit data between the two rims of the fovea to improve accuracy. The model was tested on 3488 macular scans from both eyes of 581 young adults (376 myopes and 206 non-myopes, mean (S.D.) age 21.9 (1.4) years). Estimates for retinal thickness, wall height and slope, pit depth and width were derived from the best-fitting model curve. Ten variations of Gaussian and Difference of Gaussian models were fitted to the same scans and compared with the SPG model for goodness of fit (by Root mean square error, RMSE), model complexity (by the Bayesian Information Criteria) and model fidelity.

RESULTS

The SPG model produced excellent goodness of fit (mean RMSE = 4.25 and 3.89 μm; 95% CI: 4.20, 4.30 and 3.86, 3.93 for fitting horizontal and vertical profiles respectively). The SPG model showed pit asymmetry, with average nasal walls 17.6 (11.6) μm higher and 0.96 (0.61)^° steeper than temporal walls and average superior walls 7.0 (12.2) μm higher and 0.41 (0.65)^° steeper than the inferior walls. The SPG model also revealed a continuum of human foveal shapes, from round bottoms to extended flat bottoms (up to 563 μm). 49.1% of foveal profiles were best fitted with a flat bottom >30 μm wide. Compared with the other tested models, the SPG was the preferred model overall based on the Bayesian Information Criteria.

CONCLUSIONS

The SPG is a new parsimonious mathematical model that improves upon other models by accounting for wall asymmetry and flat pit bottoms, providing an excellent fit and more faithful characterisation of typical foveal pit shapes and their known variations. This new model may be helpful in distinguishing normal foveal shape variations by refractive status as well by other characteristics such as sex, ethnicity and age.