OCT-Based Diagnostic Criteria for Different Stages of Myopic Maculopathy

Self-supervised learning-enhanced deep learning method for identifying myopic maculopathy in high myopia patients

Accurate detection and timely care for patients with high myopia present significant challenges. We developed a deep learning (DL) system enhanced by a self-supervised learning (SSL) approach to improve the automatic diagnosis of myopic maculopathy (MM). Using a dataset of 7,906 images from the Shanghai High Myopia Screening Project and a public validation set of 1,391 images from MMAC2023, our method significantly outperformed conventional techniques. Internally, it achieved 96.8% accuracy, 83.1% sensitivity, and 95.6% specificity, with AUC values of 0.982 and 0.999. Externally, it maintained 89.0% accuracy, 71.7% sensitivity, and 87.8% specificity, with AUC values of 0.978 and 0.973. The model's Cohen's kappa values exceeded 0.8, indicating substantial agreement with retinal experts. Our SSL-enhanced DL approach offers high accuracy and potential to enhance large-scale myopia screenings, demonstrating broader significance in improving early detection and treatment of MM.

Assessment of optic disc morphological characteristics and related factors of highly myopic eyes in Chinese school-aged children

CLINICAL RELEVANCE

The morphological characteristics of the optic nerve head (ONH) in myopic eyes are a clinically significant issue, especially for high myopia in school-aged children, and this can be monitored using optical coherence tomography.

BACKGROUND

The purpose of this study is to investigate the morphological characteristics of ONH, and the factors associated with peripapillary choroidal thickness in Chinese school-aged high myopia children.

METHODS

A total of 48 patients, possessing 48 high myopia eyes and 48 contralateral low myopia eyes were enrolled. The ONH characteristic parameters, including peripapillary retinal nerve fibre layer thickness, peripapillary choroidal thickness, peripapillary choroidal blood flow density, Bruch's membrane opening (BMO) characteristic parameters were measured on optical coherence tomography scans.

RESULTS

Eyes with high myopia had a larger disc size, higher peripapillary atrophy area proportion, larger peripapillary atrophy area, larger BMO minimum rim width, lower peripapillary choroidal thickness compared with those contralateral low myopia eyes (all P < 0.001). The BMO distance and border length were longer, and border tissue angle was smaller in the high myopia eyes. The multivariate regression analysis revealed that border length, axial length, and border tissue angle were independently associated with peripapillary choroidal thickness (all P < 0.05); axial length was associated with peripapillary retinal nerve fibre layer thickness (P = 0.007).

CONCLUSION

The peripapillary atrophy area, BMO area, border length, BMO distance, and BMO minimum rim width increased, but peripapillary choroidal thickness, retinal nerve fibre layer thickness decreased with axial elongation of the globe in young myopia children. Longer axial length and border length were positively correlated with lower peripapillary choroidal thickness, and a smaller border tissue angle was positively correlated with lower peripapillary choroidal thickness were found in this study. Monitoring of border length and border tissue angle is essential in the early stages of myopia in children.

Comparative analysis of macular characteristics in mCNV and contralateral eyes

Purpose

To illustrate the characteristics of perforating scleral vessels in macular regions between mCNV eyes and contralateral eyes in unilateral mCNV patients.

Methods

This was a retrospective study that included patients with unilateral naive mCNV. The study aimed to identify and analyze the distribution of perforating scleral vessels (PSVs) in the macular region of mCNV eyes and contralateral eyes. The central macular choroidal thicknesses (mChT) were measured using optical coherence tomography angiography (OCTA). The grades of myopic atrophic maculopathy (MAM) and macular myopic diffuse chorioretinal atrophy (DCA) were evaluated within groups. The number of PSVs and mChT were compared between contralateral and mCNV eyes based on the grade of DCA. The ROC curves were utilized to explore the diagnostic indexes for mCNV.

Results

A total of 102 eyes from 51 patients with unilateral mCNV were included. There was no significance in the severity of MAM or the grade of DCA between mCNV eyes and contralateral eyes (p = 0.074, p = 0.054, respectively). The mean number of PSVs in mCNV eyes was fewer than the contralateral eyes [1.00 (1.00-2.00) vs. 2.00 (0.75-3.00), p = 0.030]. The mChT in mCNV eyes was thinner than the contralateral eyes [36.00 (25.00-53.75) μm vs. 46.00 (31.00-75.25) μm, p = 0.001]. The mean grade of DCA in mCNV eyes was higher than that in contralateral eyes [3.00 (3.00-3.00) vs. 3.00 (2.00-3.00), p = 0.004]. When DCA involved the macular region, there were more PSVs in contralateral eyes than in mCNV eyes [1.50 (1.00-2.00) vs. 2.00 (1.00-3.00), p = 0.042]. Similarly, when DCA involved the foveal region, there were more PSVs in contralateral eyes than in mCNV eyes [1.50 (1.00-2.00) vs. 3.00 (2.00-4.00), p = 0.004]. The grade of DCA and mChT were valuable factors for predicting mCNV eyes (AUC = 0.6566, p = 0.021; AUC = 0.6304, p = 0.029; respectively). When the extent of DCA exceeded the foveal region, the count of PSVs was a good diagnostic factor for predicting mCNV (AUC = 0.7430, p = 0.003).

Conclusion

The mean amount of PSVs was significantly lower in the mCNV eyes compared to the contralateral eyes. When the extent of DCA exceeded the foveal region, the count of PSVs was a good diagnostic factor for predicting mCNV. Myopic eyes with a higher grade of DCA and a thinner mChT were more likely to develop mCNV.

Choroidal vascularity features of fundus tessellation in adults with high myopia

BACKGROUND

To investigate alterations in choroidal vascularity index among highly myopic adults with fundus tessellation, utilizing optical coherence tomography.

METHODS

Total of 143 highly myopic adults (234 eyes) with fundus tessellation were collected in this cross-sectional study, which was stratified into different lesion groups based on the novel tessellated fundus classification. Subfoveal choroidal thickness (SFCT), choroidal luminal area (LA), stromal area (SA), total choroidal area (TCA), and choroidal vascularity index (CVI) were analyzed utilizing optical coherence tomography (OCT) with enhanced depth imaging (EDI) mode, enabling precise quantification of these parameters.

RESULTS

Comparison analysis demonstrated notable distinctions in spherical equivalent (SE), axial length (AL), and SFCT across the four tessellation grades (p < 0.001). Analysis of the choroidal vascularity parameters, including LA, TCA, and CVI, demonstrated notable disparities across the four groups (p < 0.001), while no significant variations were observed in SA when comparing Grade 1 versus Grade 2, as well as Grade 2 versus Grade 3 (p > 0.05). Logistic regression analyses illustrated that the higher grade of tessellated exhibited a positive association with AL (OR = 1.701, p = 0.027), while negatively associated with SFCT (OR = 0.416, p = 0.007), LA (OR = 0.438, p = 0.010) and CVI (OR = 0.529, p = 0.004). Multiple regression analyses demonstrated a significant negative association between CVI and both SE and AL after adjusting for age, while positively associated with SFCT (p < 0.05).

CONCLUSION

Subtle choroidal vascularity changes may have a meaningful contribution to the development and progression of fundus tessellation. CVI and LA dramatically decreased during the early stages of tessellation development and maintained a relatively stable status when in the severe tessellated grades.

Bruch's Membrane Opening Changes in Eyes With Myopic Macular Degeneration: AIER-SERI Adult High Myopia Study

Purpose

The purpose of this study was to assess the choroidal thickness and the Bruch's membrane opening size and their relationship to visual acuity in eyes with myopic macular degeneration (MMD).

Methods

This was a population-based, cross-sectional study. Patients over the age of 30 years with high myopia (spherical equivalent ≤-5 diopters [D]) were recruited. The eyes were grouped according to the International Meta-Analysis for Pathologic Myopia (META-PM) classification based on fundus photographs and diffuse atrophy was subdivided into peripapillary diffuse choroidal atrophy (PDCA) or macular diffuse choroidal atrophy (MDCA). Swept-source optical coherence tomography imaging was performed and then the subfoveal choroidal thickness (SFCT) and Bruch's membrane opening diameter (BMOD) were measured.

Results

Of the 470 study participants recruited, 373 patients (691 eyes), with a mean age of 42.8 ± 7.2 years, were eligible for the study and included in the analysis. There was no significant difference in SFCT between MDCA and patchy atrophy (M3) groups (P = 1.000), and the BMOD enlarged significantly from no myopic macular lesions to M3 (the P values of multiple comparison tests were all <0.005). Simple linear regression analysis showed that BMOD correlated positively with age (P < 0.001) and axial length (P < 0.001). Multiple linear regression analysis showed that best corrected visual acuity (BCVA) was significantly correlated with age (P = 0.041), axial length (P = 0.001), and BMOD (P = 0.017), but not with SFCT (P = 0.231).

Conclusions

The significant variation of BMOD among MMD groups and the correlation between BMOD and BCVA in MMD eyes suggest that BMOD may be an imaging biomarker for monitoring MMD.

Characteristics and Prognostic Factors Associated With the Progression of Myopic Traction Maculopathy in Mexican Patients

Background In this study, the characteristics and prognostic factors associated with the progression of myopic traction maculopathy (MTM) were evaluated in a Mexican population. Methods This is a retrospective observational study that analyzed patients with MTM who underwent optical coherence tomography (OCT). Clinical-ocular information, the MTM classification, and initial and final visual acuity (VA) were recorded. Results In total, 101 eyes of 84 patients (mean age 63.5 ± 10.7 years) were included (88.1% female and 11.9% male). The mean spherical equivalent was -16.8 ± 6.4 D, axial length was 29.6 ± 2.1 mm, and mean initial VA was 0.8 ± 0.5 logMAR. The mean follow-up time was 25.7 ± 27.6 months. The change in final VA from diagnosis to the last follow-up was +0.1 (0.2) (p = 0.001). Overall, 24.8% of patients progressed, 72.3% did not progress, and 3% showed regression. The patient-year progression rate was 0.20 ± 0.44. Factors associated with progression were initial logMAR VA (p= 0.012) and staphyloma (p= 0.001). Conclusions One in four patients with MTM progressed, and the patient-year progression rate was 0.5. The factors associated with disease progression were initial VA and the presence of staphyloma. The characteristics of Mexican patients with MTM are similar to those described in other populations.

Comparison of manual and artificial intelligence-automated choroidal thickness segmentation of optical coherence tomography imaging in myopic adults

BACKGROUND

Myopia affects 1.4 billion individuals worldwide. Notably, there is increasing evidence that choroidal thickness plays an important role in myopia and risk of developing myopia-related conditions. With the advancements in artificial intelligence (AI), choroidal thickness segmentation can now be automated, offering inherent advantages such as better repeatability, reduced grader variability, and less reliance for manpower. Hence, we aimed to evaluate the agreement between AI-automated and manual segmented measurements of subfoveal choroidal thickness (SFCT) using two swept-source optical coherence tomography (OCT) systems.

METHODS

Subjects aged ≥ 16 years, with myopia of ≥ 0.50 diopters in both eyes, were recruited from the Prospective Myopia Cohort Study in Singapore (PROMYSE). OCT scans were acquired using Triton DRI-OCT and PLEX Elite 9000. OCT images were segmented both automatically with an established SA-Net architecture and manually using a standard technique with adjudication by two independent graders. SFCT was subsequently determined based on the segmentation. The Bland-Altman plot and intraclass correlation coefficient (ICC) were used to evaluate the agreement.

RESULTS

A total of 229 subjects (456 eyes) with mean [± standard deviation (SD)] age of 34.1 (10.4) years were included. The overall SFCT (mean ± SD) based on manual segmentation was 216.9 ± 82.7 µm with Triton DRI-OCT and 239.3 ± 84.3 µm with PLEX Elite 9000. ICC values demonstrated excellent agreement between AI-automated and manual segmented SFCT measurements (PLEX Elite 9000: ICC = 0.937, 95% CI: 0.922 to 0.949, P < 0.001; Triton DRI-OCT: ICC = 0.887, 95% CI: 0.608 to 0.950, P < 0.001). For PLEX Elite 9000, manual segmented measurements were generally thicker when compared to AI-automated segmented measurements, with a fixed bias of 6.3 µm (95% CI: 3.8 to 8.9, P < 0.001) and proportional bias of 0.120 (P < 0.001). On the other hand, manual segmented measurements were comparatively thinner than AI-automated segmented measurements for Triton DRI-OCT, with a fixed bias of - 26.7 µm (95% CI: - 29.7 to - 23.7, P < 0.001) and proportional bias of - 0.090 (P < 0.001).

CONCLUSION

We observed an excellent agreement in choroidal segmentation measurements when comparing manual with AI-automated techniques, using images from two SS-OCT systems. Given its edge over manual segmentation, automated segmentation may potentially emerge as the primary method of choroidal thickness measurement in the future.

Forecasting Myopic Maculopathy Risk Over a Decade: Development and Validation of an Interpretable Machine Learning Algorithm

Purpose

The purpose of this study was to develop and validate prediction model for myopic macular degeneration (MMD) progression in patients with high myopia.

Methods

The Zhongshan High Myopia Cohort for model development included 660 patients aged 7 to 70 years with a bilateral sphere of ≤-6.00 diopters (D). Two hundred twelve participants with an axial length (AL) ≥25.5 mm from the Chinese Ocular Imaging Project were used for external validation. Thirty-four clinical variables, including demographics, lifestyle, myopia history, and swept source optical coherence tomography data, were analyzed. Sequential forward selection was used for predictor selection, and binary classification models were created using five machine learning algorithms to forecast the risk of MMD progression over 10 years.

Results

Over a median follow-up of 10.9 years, 133 patients (20.2%) showed MMD progression in the development cohort. Among them, 69 (51.9%) developed newly-onset MMD, 11 (8.3%) developed patchy atrophy from diffuse atrophy, 54 (40.6%) showed an enlargement of lesions, and 9 (6.8%) developed plus signs. Top six predictors for MMD progression included thinner subfoveal choroidal thickness, longer AL, worse best-corrected visual acuity, older age, female gender, and shallower anterior chamber depth. The eXtreme Gradient Boosting algorithm yielded the best discriminative performance (area under the receiver operating characteristic curve [AUROC] = 0.87 ± 0.02) with good calibration in the training cohort. In a less myopic external validation group (median -5.38 D), 48 patients (22.6%) developed MMD progression over 4 years, with the model's AUROC validated at 0.80 ± 0.008.

Conclusions

Machine learning model effectively predicts MMD progression a decade ahead using clinical and imaging indicators. This tool shows promise for identifying "at-risk" high myopes for timely intervention and vision protection.

Risk factors and patterns for progression of fellow-eye myopic traction maculopathy: a 3-year retrospective cohort study

AIMS

To investigate the effect of preretinal tractional structures (PTS) and posterior scleral structures (PSS) on myopic traction maculopathy (MTM) progression.

METHODS

This retrospective cohort study included 185 fellow highly myopic eyes of 185 participants who underwent surgery for MTM. PTS included epiretinal membrane, incomplete posterior vitreous detachment and their combination. PSS included posterior staphyloma and dome-shaped macula (DSM). The MTM stage was graded according to the Myopic Traction Maculopathy Staging System. Optical coherence tomography was used to identify MTM progression, defined as an upgrade of MTM. The Kaplan-Meier method with log-rank test was used to assess MTM progression over the 3-year follow-up period. Risk factors for progression were identified using Cox regression analysis.

RESULTS

MTM progression was observed in 48 (25.9%) eyes. Three-year progression-free survival (PFS) rates for eyes with PTS, staphyloma and DSM were 53.7%, 58.2% and 90.7%, respectively. Eyes with PTS and staphyloma exhibited lower 3-year PFS rates than those without PTS or staphyloma (P log-rank test =0.002 and <0.001), while eyes with DSM had a higher 3-year PFS rate than eyes without DSM (P log-rank test=0.01). Multivariate Cox regression analysis showed that PTS (HR, 3.23; p<0.001) and staphyloma (HR, 7.91; p<0.001) were associated with MTM progression, whereas DSM (HR, 0.23; p=0.046) was a protective factor.

CONCLUSION

Both PTS and PSS play a critical role in the progression of MTM. Addressing these factors can aid in the management of MTM.

Myopic maculopathy among Chinese children with high myopia and its association with choroidal and retinal changes: the SCALE-HM study

AIMS

To investigate myopic maculopathy in Chinese children with high myopia and its association with choroidal and retinal changes.

METHODS

This cross-sectional study included Chinese children aged 4-18 years with high myopia. Myopic maculopathy was classified by fundus photography and retinal thickness (RT) and choroidal thickness (ChT) in the posterior pole were measured by swept-source optical coherence tomography. A receiver operation curve was used to determine the efficacy of fundus factors in classifying myopic maculopathy.

RESULTS

In total, 579 children aged 12.8±3.2 years with a mean spherical equivalent of -8.44±2.20 D were included. The proportions of tessellated fundus and diffuse chorioretinal atrophy were 43.52% (N=252) and 8.64% (N=50), respectively. Tessellated fundus was associated with a thinner macular ChT (OR=0.968, 95% CI: 0.961 to 0.975, p<0.001) and RT (OR=0.977, 95% CI: 0.959 to 0.996, p=0.016), longer axial length (OR=1.545, 95% CI: 1.198 to 1.991, p=0.001) and older age (OR=1.134, 95% CI: 1.047 to 1.228, p=0.002) and less associated with male children (OR=0.564, 95% CI: 0.348 to 0.914, p=0.020). Only a thinner macular ChT (OR=0.942, 95% CI: 0.926 to 0.959, p<0.001) was independently associated with diffuse chorioretinal atrophy. When using nasal macular ChT for classifying myopic maculopathy, the optimal cut-off value was 129.00 µm (area under the curve (AUC)=0.801) and 83.85 µm (AUC=0.910) for tessellated fundus and diffuse chorioretinal atrophy, respectively.

CONCLUSION

A large proportion of highly myopic Chinese children suffer from myopic maculopathy. Nasal macular ChT may serve as a useful index for classifying and assessing paediatric myopic maculopathy.

TRIAL REGISTRATION NUMBER

NCT03666052.

A Novel Grading System for Diffuse Chorioretinal Atrophy in Pathologic Myopia

INTRODUCTION

This study aims to quantitatively assess diffuse chorioretinal atrophy (DCA) in pathologic myopia and establish a standardized classification system utilizing artificial intelligence.

METHODS

A total of 202 patients underwent comprehensive examinations, and 338 eyes were included in the study. The methodology involved image preprocessing, sample labeling, employing deep learning segmentation models, measuring and calculating the area and density of DCA lesions. Lesion severity of DCA was graded using statistical methods, and grades were assigned to describe the morphology of corresponding fundus photographs. Hierarchical clustering was employed to categorize diffuse atrophy fundus into three groups based on the area and density of diffuse atrophy (G1, G2, G3), while high myopic fundus without diffuse atrophy was designated as G0. One-way analysis of variance (ANOVA) and nonparametric tests were conducted to assess the statistical association with different grades of DCA.

RESULTS

On the basis of the area and density of DCA, the condition was classified into four grades: G0, G1 (0 < density ≤ 0.093), G2 (0.093 < density ≤ 0.245), and G3 (0.245 < density ≤ 0.712). Fundus photographs depicted a progressive enlargement of atrophic lesions, evolving from punctate-shaped to patchy with indistinct boundaries. DCA atrophy lesions exhibited a gradual shift in color from brown-yellow to yellow-white, originating from the temporal side of the optic disc and extending towards the macula, with severe cases exhibiting widespread distribution throughout the posterior pole. Patients with DCA were significantly older [34.00 (27.00, 48.00) vs 29.00 (26.00, 34.00) years], possessed a longer axial length (28.85 ± 1.57 vs 27.11 ± 1.01 mm), and exhibited a more myopic spherical equivalent [- 13.00 (- 16.00, - 10.50) vs - 9.09 ± 2.41 D] compared to those without DCA (G0) (all P < 0.001). In eyes with DCA, a trend emerged as grades increased from G1 to G3, showing associations with older age, longer axial length, deeper myopic spherical equivalent, larger area of parapapillary atrophy, and increased fundus tessellated density (all P < 0.001).

CONCLUSIONS

The novel grading system for DCA, based on assessments of area and density, serves as a reliable measure for evaluating the severity of this condition, making it suitable for widespread application in the screening of pathologic myopia.

Inter-Individual Topographic Variation of Choroidal Thickness in Healthy Eyes on Swept-Source Optical Coherence Tomography

Purpose

To investigate the topographic characters of inter-individual variations of the macular choroidal thickness (CT).

Methods

This was a retrospective study. Macular CT data for 900 0.2 × 0.2-mm grids from 410 healthy eyes were collected from swept-source optical coherence tomography. Following the analysis of factors associated with mean CT, the β-coefficients of the included associated factors in each grid were summarized for choroidal thickness changes analysis. Additionally, the coefficient of variance (CoV), coefficient of determination (CoD), and coefficient of variance unexplained (CoVU) for CT were calculated in each individual grid to investigate the inter-individual choroidal variations pattern.

Results

Sex (β = -17.26, female vs. male), age (β = -1.61, per 1 year), and axial length (β = -18.62, per 1 mm) were associated with mean macular CT. Females had a thinner choroid in all 900 grids (0.5-26.9 µm). As age increased, the CT noticeably decreased (8.74-19.87 µm per 10 years) in the temporal regions. With axial length elongation, the thinning (7.94-24.91 µm per 1 mm) was more evident in subfoveal and nasal regions. Both the CoV (34.69%-58.00%) and CoVU (23.05%-40.78%) were lower in the temporal regions, whereas the CoD (18.41%-39.66%) was higher in the temporal regions.

Conclusions

Choroidal thinning is more predominant in the subfoveal and nasal regions with axial length elongation, but in the temporal region with aging. The inter-individual variation of CT is higher and less determined by sex, age, or axial length in the nasal regions.

Translational Relevance

Topographic variation should be considered when interpreting choroidal thickness.

Polarization-Sensitive OCT Imaging of Scleral Abnormalities in Eyes With High Myopia and Dome-Shaped Macula

Importance

The relevance of visualizing scleral fiber orientation may offer insights into the pathogenesis of pathologic myopia, including dome-shaped maculopathy (DSM).

Objective

To investigate the orientation and density of scleral collagen fibers in highly myopic eyes with and without DSM by polarization-sensitive optical coherence tomography (PS-OCT).

Design, Setting, and Participants

This case series included patients with highly myopic eyes (defined as a refractive error ≥6 diopters or an axial length ≥26.5 mm) with and without a DSM examined at a single site in May and June 2019. Analysis was performed from September 2019 to October 2023.

Exposures

The PS-OCT was used to study the birefringence and optic axis of the scleral collagen fibers.

Main Outcomes and Measures

The orientation and optic axis of scleral fibers in inner and outer layers of highly myopic eyes were assessed, and the results were compared between eyes with and without a DSM.

Results

A total of 72 patients (51 [70.8%] female; mean [SD] age, 61.5 [12.8] years) were included, and 89 highly myopic eyes were examined (mean [SD] axial length, 30.4 [1.7] mm); 52 (58.4%) did not have a DSM and 37 (41.6%) had a DSM (10 bidirectional [27.0%] and 27 horizontal [73.0%]). Among the 52 eyes without DSM, the 13 eyes with simple high myopia had primarily inner sclera visible, displaying radially oriented fibers in optic axis images. In contrast, the entire thickness of the sclera was visible in 39 eyes with pathologic myopia. In these eyes, the optic axis images showed vertically oriented fibers within the outer sclera. Eyes presenting with both horizontal and bidirectional DSMs had clusters of fibers with low birefringence at the site of the DSM. In the optic axis images, horizontally or obliquely oriented scleral fibers were aggregated in the inner layer at the DSM. The vertical fibers located posterior to the inner fiber aggregation were not thickened and appeared thin compared with the surrounding areas.

Conclusions and Relevance

This study using PS-OCT revealed inner scleral fiber aggregation without outer scleral thickening at the site of the DSM in highly myopic eyes. Given the common occurrence of scleral pathologies, such as DSM, and staphylomas in eyes with pathologic myopia, recognizing these fiber patterns could be important. These insights may be relevant to developing targeted therapies to address scleral abnormalities early and, thus, mitigate potential damage to the overlying neural tissue.

LONGITUDINAL CHANGES OF POSTERIOR VORTEX VEINS IN HIGHLY MYOPIC EYES DETERMINED BY RETROSPECTIVE ANALYSES OF INDOCYANINE GREEN ANGIOGRAMS

PURPOSE

To assess the longitudinal changes of the posterior vortex veins (VVs) in highly myopic (HM) eyes.

METHODS

The medical records of 1,730 consecutive HM eyes that had undergone indocyanine green angiography were studied. Eyes that had posterior VVs and had undergone at least two indocyanine green angiography examinations with a minimum interval of 3 years were selected from this group.

RESULTS

Ninety-one eyes of 78 patients met the inclusion criteria. A total of 124 posterior VVs were identified. Over an average interval of 7.8 ± 5.0 years, 41 (33.1%) of the 124 posterior VVs had marked changes consisting mainly of an attenuation of vessels in 36 posterior VVs (87.8%) and alterations in the drainage course in 16 posterior VVs (39.0%). Fifteen posterior VVs had both types of changes. Most of the attenuations of the vessels occurred for smaller branches, but a complete loss of the entire trunk was seen in three eyes. Additionally, four eyes had posterior VV changes in association with changes of peripheral VVs.

CONCLUSION

Posterior VV in highly myopic eyes can undergo changes with increasing time. The associated factors included the development and progression of myopic maculopathy lesions. In some cases, the blood drainage shifted from posterior VV to peripheral VV by forming anastomotic channels.

Clinical Features of Fundus Tessellation and Its Relationship with Myopia: A Systematic Review and Meta-analysis

INTRODUCTION

This study aims to assess the existing literature on fundus tessellation (FT), focusing on its prevalence, associated factors, distribution, and progression.

METHODS

Systemic methods were employed to search and gather published literature on FT from databases such as the National Library of Medicine (PubMed), Web of Science (WOS), and Elsevier on July 1, 2023. The quality of the studies was evaluated using the Newcastle-Ottawa Scale (NOS) and the Healthcare Research and Quality (AHRQ) criteria. A meta-analysis was conducted to compare tessellated and normal fundus with respect to age, gender, axial length, and spherical equivalent.

RESULTS

The systematic review included 23 articles, encompassing a total of 3053 eyes in the meta-analysis. The prevalence of FT varied from 43.00 to 94.35%. The severity of FT was significantly associated with older age, male sex, lower body weight index, longer axial length, larger peripapillary atrophy, thinner choroid, thinner sclera, and larger corneal radius of curvature, suggesting a potential progression pattern. Notably, FT was observed predominantly in the macular and peripapillary regions. The meta-analysis revealed that tessellated fundus tended to be associated with older age (mean difference [MD] 4.76, 95% confidence interval [CI] 1.71-7.80, P < 0.01), longer axial length (MD 0.86, 95% CI 0.70-1.02, P < 0.01), and a lower spherical equivalent (MD - 1.16, 95% CI - 1.68 to 0.65, P < 0.01) compared to normal fundus. However, there was no significant difference in the proportion of males between individuals with tessellated and normal fundus (odds ratio [OR] 1.12, 95% CI 0.89-1.42, P = 0.32).

CONCLUSIONS

Overall, this systematic review and meta-analysis shed light on the prevalence, characteristics, and factors associated with FT, offering valuable insights for clinicians and researchers in the field of ophthalmology.

STUDY REGISTRATION

The study protocol was registered on the International Prospective Register of Systematic Reviews (PROSPERO) (CRD42023442486).

Association Between Choroidal Thickness and Myopic Maculopathy in a Japanese Population: The Hisayama Study

Purpose

To examine the association between choroidal thickness and myopic maculopathy in a general Japanese population.

Design

Population-based cross-sectional study.

Participants

A total of 2841 residents of a Japanese community aged ≥ 40 years, who consented to participate and had available data of choroidal thickness and fundus photographs, were enrolled in this study.

Methods

The choroidal thickness was measured by swept-source OCT. Participants were divided into quartiles of choroidal thickness. Myopic maculopathy was defined according to the classification system of the Meta-analysis of Pathologic Myopia Study Group. Main outcome measures were odds ratios (ORs) of choroidal thickness for prevalent myopic maculopathy. The ORs and 95% confidence intervals (CIs) were estimated using a logistic regression model.

Main Outcome Measures

Prevalent myopic maculopathy.

Results

Eighty-one participants had myopic maculopathy (45 diffuse chorioretinal atrophy, 31 patchy chorioretinal atrophy, and 5 macular atrophy). Individuals in the lowest quartile of choroidal thickness had a significantly greater OR for the presence of myopic maculopathy than those in the highest quartile of choroidal thickness (OR: 4.78 [95% CI: 1.78-16.72]) after adjusting for confounders, including axial length. The sensitivity analysis among the 1176 myopic individuals with axial length of ≥ 24.0 mm also showed that thinner choroidal thickness was significantly associated with prevalent myopic maculopathy.

Conclusions

The present study demonstrated the significant inverse association between choroidal thickness and the likelihood of myopic maculopathy, suggesting that the measurement of choroidal thickness in addition to axial length would be useful for assessing the risk of myopic maculopathy and elucidating its pathogenesis.

Financial Disclosures

Proprietary or commercial disclosure may be found after the references.

Fundus Tessellated Density of Pathologic Myopia

PURPOSE

The study aimed to quantitatively evaluate the fundus tessellated density (FTD) in different categories of pathologic myopia (PM) using fundus photographs with the application of artificial intelligence.

METHODS

A retrospective review of 407 PM (META-PM, Category 2-Category 4) eyes was conducted, employing a biomimetic mechanism of human vision and integrated image processing technologies for FTD extraction and calculation. Different regions of interest were analyzed, including circle O4.5 (optic disc centered, diameter of 4.5 mm) and circle M1.0, M3.0, M6.0 (macular centered, diameter of 1.0, 3.0, and 6.0 mm), using 2 partitioning methods ("X" and "+"). The density of patchy (Category 3) or macular atrophy (Category 4) areas was quantified. Univariate and multivariate linear regression analyses were performed to assess the association with FTD.

RESULTS

The mean FTD of total PM eyes was 0.283, ranging from 0.002 to 0.500, and demonstrating a negative correlation with the PM category. In multivariate analysis, age was found to be significantly associated with FTD ( P <0.05), while axial length did not show a significant association. Fundus tessellation of circle O4.5 and circle M6.0 displayed associations with the FTD across different PM categories. The "X" partitioning method better fit the circle M6.0 region, while both methods were suitable for the circle O4.5 region. After excluding the patchy and macular atrophic areas, the mean FTD values were 0.346 in Category 2, 0.261 in Category 3, and 0.186 in Category 4.

CONCLUSIONS

The study revealed a decreasing trend in FTD values across different categories of PM, regardless of the presence or absence of patchy or macular atrophic areas. Quantifying FTD in PM could be a valuable tool for improving the existing PM classification system and gaining insights into the origin of posterior staphyloma and visual field defects in high myopia.

Effects of posterior staphyloma on choroidal structure in myopic adults: a retrospective study

BACKGROUND

Studies on the choroid of myopic eyes with posterior staphyloma have shown that choroidal thickness decreased. This retrospective study further analysed the effects of posterior scleral staphyloma on choroidal blood vessels and matrix components compared to non-pathological myopia.

METHODS

In this cross-sectional study, ninety-one eyes were divided into pathological (posterior staphyloma) and non-pathological myopia. The latter was further divided into three groups (Group 1: 26 mm ≤ axial length; Group 2: 24 mm ≤ axial length < 26 mm; Group 3: 22 mm ≤ axial length < 24 mm). Choroidal thickness, total choroidal area, luminal area, stromal area, and choroidal vascularity index were calculated.

RESULTS

The CVI in N1, N2, I1, S2 of the posterior staphyloma group were lower than those of group 1 (both P < 0.05). The mean height of posterior staphyloma was associated with mean CT (Pearson correlation: r = -0.578, P = 0.039) but not with the mean CVI in posterior staphyloma group. In all groups, the mean choroidal thickness, total choroidal area, luminal area, and stromal area were significantly associated with axial length (P < 0.001), and the mean choroidal vascularity index was significantly associated with the mean choroidal thickness (P < 0.001).

CONCLUSION

The choroidal structure of pathological myopia with posterior staphyloma and non-pathological myopia with longer axial length demonstrates alterations in which choroidal vessels are more impaired than the stroma. A lower choroidal vascularity index should be alert to pathological changes for myopia with axial length > 26 mm.

Lesion detection with fine-grained image categorization for myopic traction maculopathy (MTM) using optical coherence tomography

BACKGROUND

Myopic traction maculopathy (MTM) are retinal disorder caused by traction force on the macula, which can lead to varying degrees of vision loss in eyes with high myopia. Optical coherence tomography (OCT) is an effective imaging technique for diagnosing, detecting and classifying retinopathy. MTM has been classified into different patterns by OCT, corresponding to different clinical strategies.

PURPOSE

We aimed to engineer a deep learning model that can automatically identify MTM in highly myopic (HM) eyes using OCT images.

METHODS

A five-class classification model was developed using 2837 OCT images from 958 HM patients. We adopted a ResNet-34 architecture to train the model to identify MTM: no MTM (class 0), extra-foveal maculoschisis (class 1), inner lamellar macular hole (class 2), outer foveoschisis (class 3), and discontinuity or detachment of foveal outer hyperreflective layers (class 4). An independent test set of 604 images from 173 HM patients was used to evaluate the model's performance. Classification performance was assessed according to the area under the curve (AUC), accuracy, sensitivity, specificity.

RESULTS

Our model exhibited a high training performance for classification (F1-score of 0.953; AUCs of 0.961 to 0.998). In test set, it achieved sensitivities (91.67%-97.78 %) and specificities (98.33%-99.17%) as good as, or better than, those of experienced clinicians. Heatmaps were generated to provide visual explanations.

CONCLUSIONS

We established a deep learning model for MTM classification using OCT images. This model performed equally well or better than retinal specialists and is suitable for large-scale screening and identifying MTM in HM eyes.

Using a combination of peripapillary atrophy area and choroidal thickness for the prediction of different types of myopic maculopathy

PURPOSE

To analyse the topographic characteristics in macular choroidal thickness (mChT) and ocular biometry in myopic maculopathy and to explore the potential cut-off value for prediction of myopic maculopathy (MM).

METHODS

All participants underwent detailed ocular examinations. MM was subdivided into thin choroid, Bruch's membrane (BM) defects, choroidal neovascularization (CNV), and myopic tractional maculopathy (MTM) according to OCT-based classification system. Peripapillary atrophy area (PPA), tilt ratio, torsion, and mChT were individually measured.

RESULTS

A total of 1947 participants were included. In multivariate logistics models, older age, longer axial length, larger PPA area, and thinner average mChT were more likely to have MM and different type of MM. Female participants were more likely to have MM and BM defects. A lower tilt ratio was more likely to be associated with CNV and MTM. The area under the curve (AUC) of single tilt ratio, PPA area, torsion, and topographic of mChT for MM, thin choroid, BM Defects, CNV, and MTM were 0.6581 to 0.9423, 0.6564 to 0.9335, 0.6120 to 0.9554, 0.5734 to 0.9312, 0.6415 to 0.9382, respectively. After combining PPA area and average mChT for predicting MM, thin choroid, BM defects, CNV, and MTM, the AUC of the combination were 0.9678, 0.9279, 0.9531, 0.9213, 0.9317, respectively.

CONCLUSION

Progressive and continuous PPA area expanding and thin choroid play a role in the development of myopic maculopathy. The present study showed that a combination of peripapillary atrophy area and the choroidal thickness could be used to predict MM and each type of MM.

Correlation of Visual Acuity and Outer Retinal Thickness in Myopic Atrophic Maculopathy: A Retrospective Review

INTRODUCTION

Myopic atrophic maculopathy is prevalent among patients with pathologic myopia and frequently leads to relentless vision loss. Several grading systems were established to facilitate the understanding of myopic atrophic maculopathy. However, the anatomical details in different stages of myopic maculopathy are so far not clearly elucidated. This study aims to investigate the visual acuity and retinal sublayer features in highly myopic eyes with varying severities of myopic atrophic maculopathy (MAM).

METHODS

The clinical records of 111 consecutive patients (158 eyes) with high myopia (refractive error ≤ -6.0 D and axial length ≥ 26.0 mm) were reviewed. Fundus photography, optical coherence tomography (OCT), and best-corrected visual acuity (BCVA) were measured. MAM was graded according to the META-analysis for Pathologic Myopia (META-PM) classification system. Myopic choroidal neovascularization (mCNV) and dome-shaped macula (DSM) were also investigated.

RESULTS

Among the 158 eyes, 18 (11%), 21(13%), 24 (15%), 25 (16%), 23 (15%), and 24 (15%) had tessellated fundus, diffuse chorioretinal atrophy, diffuse chorioretinal atrophy with DSM, patchy atrophy, patchy atrophy with DSM, and MAM with mCNV, respectively. A total of 23 (15%) eyes had macular atrophy without mCNV. Progressive thinning in the Henle's fiber and outer nuclear layers, myoid and ellipsoid zone (MEZ), outer segment (OS), and interdigitation zone and retinal pigmented epithelium based on the severity of MAM (p-value < 0.001) was found. MEZ and OS were most significantly reduced in thickness (p-value < 0.001). The presence of mCNV demonstrated significant outer retinal layer thinning compared with that of the tessellated fundus (p-value = 0.031). Patchy atrophy with DSM showed statistically poorer BCVA compared with that without (p-value = 0.008).

CONCLUSION

Visual acuity and outer retinal sublayer characteristics were correlated with the severity of MAM. Outer retinal sublayer analysis by spectrum-domain OCT shed some light on the mechanisms of MAM progression.

COMPLEX HEMODYNAMICS OF INTERVORTEX VEIN ANASTOMOSES IN HIGHLY MYOPIC EYES

PURPOSE

To analyze the complex pattern of filling of the intervortex vein (IVV) anastomoses through large trunks in highly myopic eyes based on indocyanine green angiographic (ICGA) videos.

METHODS

The medical records of 1,060 consecutive highly myopic eyes that had undergone ICGA were studied. IVV anastomoses were identified in the ICGA images, and the ICGA images and videos were analyzed comprehensively to characterize their hemodynamic features.

RESULTS

Seven eyes with IVV anastomoses through large trunks were analyzed. In the ICGA videos of six eyes, laminar flow was observed in the IVV anastomotic vessels. The laminar flow started in the arterial phase in two eyes, with pulsatile fashion in 1 of them. The flow began in the early arteriovenous transition phase in four eyes. The laminar flow continued for a mean of 12.17 ± 3.06 seconds, and the remaining section was gradually filled slower than the surrounding veins. The anastomotic trunk for the remaining one eye was too narrow to be analyzed. Four eyes had longitudinal ICGA records, and two had significant attenuation and narrowing of the anastomotic vessels.

CONCLUSION

The very early filling of part of the IVV anastomoses suggests that arteriovenous anastomoses are involved in the IVV of highly myopic eyes. However, this suggestion needs further study. There may be similar pathogenesis for IVV anastomoses either in thick or thin sclera.

Blood flow perfusion in visual pathway detected by arterial spin labeling magnetic resonance imaging for differential diagnosis of ocular ischemic syndrome

Background

Ocular ischemic syndrome (OIS), attributable to chronic hypoperfusion caused by marked carotid stenosis, is one of the important factors that cause ocular neurodegenerative diseases such as optic atrophy. The current study aimed to detect blood flow perfusion in a visual pathway by arterial spin labeling (ASL) and magnetic resonance imaging (MRI) for the differential diagnosis of OIS.

Methods

This diagnostic, cross-sectional study at a single institution was performed to detect blood flow perfusion in a visual pathway based on 3D pseudocontinuous ASL (3D-pCASL) using 3.0T MRI. A total of 91 participants (91 eyes) consisting of 30 eyes with OIS and 61 eyes with noncarotid artery stenosis-related retinal vascular diseases (39 eyes with diabetic retinopathy and 22 eyes with high myopic retinopathy) were consecutively included. Blood flow perfusion values in visual pathways derived from regions of interest in ASL images, including the retinal-choroidal complex, the intraorbital segments of the optic nerve, the tractus optics, and the visual center, were obtained and compared with arm-retinal circulation time and retinal circulation time derived from fundus fluorescein angiography (FFA). Receiver operating characteristic (ROC) curve analyses and the intraclass correlation coefficient (ICC) were performed to evaluate the accuracy and consistency.

Results

Patients with OIS had the lowest blood flow perfusion values in the visual pathway (all p < 0.05). The relative intraorbital segments of optic nerve blood flow values at post-labeling delays (PLDs) of 1.5 s (area under the curve, AUC = 0.832) and the relative retinal-choroidal complex blood flow values at PLDs of 2.5 s (AUC = 0.805) were effective for the differential diagnosis of OIS. The ICC of the blood flow values derived from the retinal-choroidal complex and the intraorbital segments of the optic nerve between the two observers showed satisfactory concordance (all ICC > 0.932, p < 0.001). The adverse reaction rates of ASL and FFA were 2.20 and 3.30%, respectively.

Conclusion

3D-pCASL showed that the participants with OIS had lower blood flow perfusion values in the visual pathway, which presented satisfactory accuracy, reproducibility, and safety. It is a noninvasive and comprehensive differential diagnostic tool to assess blood flow perfusion in a visual pathway for the differential diagnosis of OIS.

Perforating scleral vessels adjacent to myopic choroidal neovascularization achieved a poor outcome after intravitreal anti-VEGF therapy

Background

This study aimed to summarize the features of perforating scleral vessels (PSVs) in patients with myopic choroidal neovascularization (CNV) (mCNV) using optical coherence tomography angiography (OCTA) and to identify the associations with the response after intravitreal anti-vascular endothelial growth factor (anti-VEGF) therapy.

Methods

A consecutive series of naïve patients who had mCNV and received intravitreal anti-VEGF therapy with a follow-up duration of 12 months or more were enrolled. The prevalence, location, and branches of PSVs were analyzed. Projection-resolved OCTA (PR-OCTA) was used to analyze the neovascular signals between CNV and PSVs. Best corrected visual acuity (BCVA) and central macular thickness (CMT) were measured. The proportion of CMT change relative to baseline was used to assess therapeutic response.

Results

A total of 44 eyes from 42 patients with mCNV were enrolled. PSVs were identified in 41 out of 44 eyes. Branches were identified in the PSVs of 24 eyes (57.14%), and 20 eyes did not have PSV branches (47.62%). In eight eyes (18.18%), PSVs were adjacent to mCNV, and in 36 eyes (81.82%), PSVs were not adjacent to mCNV. After anti-VEGF therapy for mCNV, BCVA increased (F = 6.119, p < 0.001) and CMT decreased (F = 7.664, p < 0.001). In the eyes where PSVs were adjacent to mCNV, BCVA improvements (F = 7.649, p = 0.009) were poor, and changes in CMT were small.

Conclusion

The eyes with PSVs adjacent to mCNV showed poor therapeutic responses after intravitreal anti-VEGF therapy.

Efficacy of a Deep Learning System for Screening Myopic Maculopathy Based on Color Fundus Photographs

INTRODUCTION

The maculopathy in highly myopic eyes is complex. Its clinical diagnosis is a huge workload and subjective. To simply and quickly classify pathologic myopia (PM), a deep learning algorithm was developed and assessed to screen myopic maculopathy lesions based on color fundus photographs.

METHODS

This study included 10,347 ocular fundus photographs from 7606 participants. Of these photographs, 8210 were used for training and validation, and 2137 for external testing. A deep learning algorithm was trained, validated, and externally tested to screen myopic maculopathy which was classified into four categories: normal or mild tessellated fundus, severe tessellated fundus, early-stage PM, and advanced-stage PM. The area under the precision-recall curve, the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, and Cohen's kappa were calculated and compared with those of retina specialists.

RESULTS

In the validation data set, the model detected normal or mild tessellated fundus, severe tessellated fundus, early-stage PM, and advanced-stage PM with AUCs of 0.98, 0.95, 0.99, and 1.00, respectively; while in the external-testing data set of 2137 photographs, the model had AUCs of 0.99, 0.96, 0.98, and 1.00, respectively.

CONCLUSIONS

We developed a deep learning model for detection and classification of myopic maculopathy based on fundus photographs. Our model achieved high sensitivities, specificities, and reliable Cohen's kappa, compared with those of attending ophthalmologists.

Global trends and frontiers of research on pathologic myopia since the millennium: A bibliometric analysis

Background and purpose

Pathologic myopia (PM) is an international public health issue. This study aimed to analyze PM research trends by reporting on publication trends since 2000 and identifying influential journals, countries, authors, and keywords involved in PM.

Methods

A bibliometric analysis was performed to evaluate global production and development trends in PM since 2000 and the keywords associated with PM.

Results

A total of 1,435 publications were retrieved. PM has become a fascinating topic (with relative research interest ranging from 0.0018% in 2000 to 0.0044% in 2021) and a global public health issue. The top three countries with the highest number of publications were China, the USA, and Japan. The journals, authors, and institutions that published the most relevant literature came from these three countries. China exhibited the most rapid increase in the number of publications (from 0 in 2000 to 69 in 2021). Retina published the most papers on PM. Kyoko Ohno-Matsui and Tokyo Medical and Dental University contributed the most publications among authors and institutions, respectively. Based on keyword analysis, previous research emphasized myopic choroidal neovascularization and treatment, while recent hotspots include PM changes based on multimodal imaging, treatment, and pathogenesis. Keyword analysis also revealed that deep learning was the latest hotspot and has been used for the detection of PM.

Conclusion

Our results can help researchers understand the current status and future trends of PM. China, the USA, and Japan have the greatest influence, based on the number of publications, top journals, authors, and institutions. Current research on PM highlights the pathogenesis and application of novel technologies, including multimodal imaging and artificial intelligence.

Morphological characteristics of the optic nerve head and impacts on longitudinal change in macular choroidal thickness during myopia progression

PURPOSE

The aim of this study was to investigate the association between morphological characteristics of Bruch's membrane opening distance (BMOD), border length (BL), border tissue angle (BTA), peripapillary atrophy (PPA) as well as axial length (AL) and incident decreased macular choroidal thickness (mChT) in young healthy myopic eyes.

METHODS

A total of 323 participants aged 17-30 years were included in the current 2-year longitudinal study. Each participant underwent detailed ocular examinations at baseline and follow-up. Data of AL, refraction error, PPA area, BMOD, BL, BTA and mChT were measured individually. Incident decreased mChT was defined as follow-up mChT of participants decreased into the lowest quartile of baseline mChT.

RESULTS

Subjects with longer AL, longer BMOD were more likely to have incident decreased mChT (odds ratio [OR], 1.56; 2.09, respectively, per 1 Z-score increment), whereas larger BTA was less likely to develop decreased mChT (odds ratio [OR], 0.51, per 1 Z-score increment). The area under the receiver operating curve (AUROC) of basic risk model for incident decreased mChT was 0.6284. After adding BMOD, BTA and AL separately to the basic risk model, the AUROC of the combination could reach 0.6967, 0.6944 and 0.7383, respectively. After combining BMOD, BTA and AL to the basic model, the AUROC of the combination showed the highest AUROC of 0.7608.

CONCLUSIONS

Bruch's membrane opening distance and AL are significant risk factors for incident decreased mChT, whereas BTA played protective role in the deterioration of mChT. In addition, a combination of BMOD, BTA and AL could serve as earlier predictors of the attenuation of mChT in myopia progression.

Effect of Ocular Magnification on Macular Choroidal Thickness Measurements Made Using Optical Coherence Tomography in Children

PURPOSE

To evaluate the relationship between ocular magnification correction and macular choroidal thickness (ChT) measurements in children, and to demonstrate when ocular magnification correction is necessary.

METHODS

Chinese children aged 6-9 years with various refractive statuses were included. Swept-source optical coherence tomography was used to measure macular ChT. A self-designed program was adopted to simulate ChT changes in each sector of the ETDRS grid in the macula under various simulated axial lengths (ALs).

RESULTS

ChT measurements were not affected for all simulated ALs in over 95% of the individuals in the central fovea. In the inferior, superior, and temporal parafoveal sectors, the extent of AL that may include 95% of the individuals narrowed from approximately 22.0 mm to 27.2 mm. In the nasal parafoveal sector and inferior, superior, and temporal perifoveal sectors, the extent of AL that may include 95% of the individuals became even narrower, from approximately 22.8 mm to 26.0 mm. The narrowest extent was observed in the perifoveal nasal sector, ranging from 23.3 mm to 25.5 mm. The effect of ocular magnification was more significant in hyperopes than in myopes in the inferior parafoveal sector and temporal, superior, and nasal perifoveal sectors.

CONCLUSION

During macular ChT measurements, ocular magnification correction is not necessary in the central fovea. However, ocular magnification should be corrected normally in the nasal perifoveal region and in individuals with ALs shorter than 22.8 mm or longer than 26.0 mm in the remaining macular regions.

Association of Retinal Sensitivity With Optical Coherence Tomography Microstructure in Highly Myopic Patients

Purpose

To investigate the association of retinal sensitivity with microstructural features in optical coherence tomography (OCT) of high myopic eyes.

Methods

This cross-sectional study included 78 eyes (78 patients). Microstructural features on spectral-domain OCT, such as the integrity of the retinal pigment epithelium (RPE), ellipsoid zone (EZ), and external limiting membrane (ELM) and outer retinoschisis, were evaluated at each retinal location corresponding to microperimetric testing points.

Results

For all testing points, retinal sensitivity was significantly associated with the integrity of the RPE, EZ, and ELM (all P < 0.001) based on OCT but not with outer retinoschisis (P = 0.183). A higher category of myopic maculopathy according to the Meta-Analysis of Pathologic Myopia classification was associated with lower mean retinal sensitivity (P < 0.001). In eyes with patchy atrophy (PA), mean retinal sensitivity of testing points adjacent to the PA lesion (15.7 ± 6.8 dB) was greater than points within or at the PA border (2.6 ± 5.2 dB; P < 0.001) but lower than distant points (19.6 ± 4.3 dB; P < 0.001). Microstructural features in OCT were well correlated with the differences in retinal sensitivity according to myopic maculopathy severity and proximity to the PA lesion.

Conclusions

In highly myopic eyes, retinal sensitivity on microperimetry was strongly associated with microstructural features in OCT. Both retinal sensitivity and microstructure were affected by the severity of myopic degeneration and proximity to the PA lesion.

Risk factors for myopic choroidal neovascularization-related macular atrophy after anti-VEGF treatment

Purpose

The study aimed to evaluate risk factors for macular atrophy (MA) associated with myopic choroidal neovascularization (mCNV) during long-term follow-up after intravitreal anti-vascular endothelial growth factor (VEGF) treatment in highly myopic eyes.

Methods

The medical records of patients who received intravitreal injection of anti-VEGF agents as mCNV treatment and were followed-up for more than 36 months were retrospectively reviewed. The risk factors for the development of mCNV-MA, which is the fovea-involving patchy atrophy lesion adjacent to mCNV, were investigated using the Cox proportional hazard model.

Results

A total of 82 eyes (74 patients) were included in the study. The mean age at anti-VEGF treatment was 56.3 ± 12.5 years (range, 26–77), and the mean follow-up period was 76.3 ± 33.5 months (range, 36–154). During follow-up, mCNV-MA developed in 27 eyes (32.9%), and its occurrence was estimated to be 24.5% at 3 years and 37.3% at 5 years after the first anti-VEGF treatment. Old age (hazard ratio [HR] = 1.054, 95% confidence interval [CI]: 1.018–1.091; P = 0.003) and greater CNV size at baseline (HR = 2.396, CI: 1.043–5.504; P = 0.040) were significant factors for mCNV-MA development. Eyes with a thinner subfoveal choroid were more likely to show faster enlargement of the mCNV-MA during follow-up.

Conclusions

In mCNV eyes treated with intravitreal anti-VEGF agents, older age and greater mCNV size at baseline were risk factors for the development of MA during long-term follow-up, which was associated with a poor visual prognosis.

Advances in OCT Imaging in Myopia and Pathologic Myopia

Advances in imaging with optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) technology, including the development of swept source OCT/OCTA, widefield or ultra-widefield systems, have greatly improved the understanding, diagnosis, and treatment of myopia and myopia-related complications. Anterior segment OCT is useful for imaging the anterior segment of myopes, providing the basis for implantable collamer lens optimization, or detecting intraocular lens decentration in high myopic patients. OCT has enhanced imaging of vitreous properties, and measurement of choroidal thickness in myopic eyes. Widefield OCT systems have greatly improved the visualization of peripheral retinal lesions and have enabled the evaluation of wide staphyloma and ocular curvature. Based on OCT imaging, a new classification system and guidelines for the management of myopic traction maculopathy have been proposed; different dome-shaped macula morphologies have been described; and myopia-related abnormalities in the optic nerve and peripapillary region have been demonstrated. OCTA can quantitatively evaluate the retinal microvasculature and choriocapillaris, which is useful for the early detection of myopic choroidal neovascularization and the evaluation of anti-vascular endothelial growth factor therapy in these patients. In addition, the application of artificial intelligence in OCT/OCTA imaging in myopia has achieved promising results.

Distribution and association of visual impairment with myopic maculopathy across age groups among highly myopic eyes - based on the new classification system (ATN)

Purpose

To investigate the percentages and risk factors for visual impairment (VI) across age groups in a highly myopic cohort with a wide range of age (18–93 years).

Methods

A total of 2099 eyes (1220 participants) were enrolled. All participants underwent detailed ocular examinations. Myopic maculopathy (MM) was assessed as myopic atrophy maculopathy (MAM), myopic traction maculopathy (MTM) or myopic neovascular maculopathy (MNM) based on the ATN system.

Results

Most participants younger than 50 years had normal vision, while the cumulative risk of VI and blindness gradually increased after 50–59 years. The percentage of each type of MM increased nonlinearly with ageing (all p < 0.001), with an accelerated period of increase after 45 years for MAM, and after 50 years for MTM and MNM. Axial length (AL) ≥30 mm was the only associated factor for mild VI or worse in participants aged 18–39 years (p < 0.001). Older age, AL ≥30 mm and the presence of MAM were predictors for mild VI or worse in the group aged 40–49 years (all p < 0.05). In participants aged ≥50 years, older age, female sex, longer AL and increased severity of MM were risk factors for VI and blindness (all p < 0.05).

Conclusion

The percentages of MM and related VI increased nonlinearly with older age, with a turning point at 45 years for MAM, preceding that of MTM, MNM and VI by 5 years, warranting future longitudinal studies to confirm. Different age groups presented different risk factors for VI. Timely screening should be in place for middle‐aged high myopes.

Novel Uses and Challenges of Artificial Intelligence in Diagnosing and Managing Eyes with High Myopia and Pathologic Myopia

Myopia is a global health issue, and the prevalence of high myopia has increased significantly in the past five to six decades. The high incidence of myopia and its vision-threatening course emphasize the need for automated methods to screen for high myopia and its serious form, named pathologic myopia (PM). Artificial intelligence (AI)-based applications have been extensively applied in medicine, and these applications have focused on analyzing ophthalmic images to diagnose the disease and to determine prognosis from these images. However, unlike diseases that mainly show pathologic changes in the fundus, high myopia and PM generate even more data because both the ophthalmic information and morphological changes in the retina and choroid need to be analyzed. In this review, we present how AI techniques have been used to diagnose and manage high myopia, PM, and other ocular diseases and discuss the current capacity of AI in assisting in preventing high myopia.

Deep Learning Model Based on 3D Optical Coherence Tomography Images for the Automated Detection of Pathologic Myopia

Pathologic myopia causes vision impairment and blindness, and therefore, necessitates a prompt diagnosis. However, there is no standardized definition of pathologic myopia, and its interpretation by 3D optical coherence tomography images is subjective, requiring considerable time and money. Therefore, there is a need for a diagnostic tool that can automatically and quickly diagnose pathologic myopia in patients. This study aimed to develop an algorithm that uses 3D optical coherence tomography volumetric images (C-scan) to automatically diagnose patients with pathologic myopia. The study was conducted using 367 eyes of patients who underwent optical coherence tomography tests at the Ophthalmology Department of Incheon St. Mary’s Hospital and Seoul St. Mary’s Hospital from January 2012 to May 2020. To automatically diagnose pathologic myopia, a deep learning model was developed using 3D optical coherence tomography images. The model was developed using transfer learning based on four pre-trained convolutional neural networks (ResNet18, ResNext50, EfficientNetB0, EfficientNetB4). Grad-CAM was used to visualize features affecting the detection of pathologic myopia. The performance of each model was evaluated and compared based on accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). The model based on EfficientNetB4 showed the best performance (95% accuracy, 93% sensitivity, 96% specificity, and 98% AUROC) in identifying pathologic myopia.

Pathologic myopia: advances in imaging and the potential role of artificial intelligence

Pathologic myopia is a severe form of myopia that can lead to permanent visual impairment. The recent global increase in the prevalence of myopia has been projected to lead to a higher incidence of pathologic myopia in the future. Thus, imaging myopic eyes to detect early pathological changes, or predict myopia progression to allow for early intervention, has become a key priority. Recent advances in optical coherence tomography (OCT) have contributed to the new grading system for myopic maculopathy and myopic traction maculopathy, which may improve phenotyping and thus, clinical management. Widefield fundus and OCT imaging has improved the detection of posterior staphyloma. Non-invasive OCT angiography has enabled depth-resolved imaging for myopic choroidal neovascularisation. Artificial intelligence (AI) has shown great performance in detecting pathologic myopia and the identification of myopia-associated complications. These advances in imaging with adjunctive AI analysis may lead to improvements in monitoring disease progression or guiding treatments. In this review, we provide an update on the classification of pathologic myopia, how imaging has improved clinical evaluation and management of myopia-associated complications, and the recent development of AI algorithms to aid the detection and classification of pathologic myopia.

MACULAR SENSITIVITY AND CAPILLARY PERFUSION IN HIGHLY MYOPIC EYES WITH MYOPIC MACULAR DEGENERATION

PURPOSE

To evaluate the interrelationship between macular sensitivity and retinal perfusion density (PD) in eyes with myopic macular degeneration (MMD).

METHODS

One hundred and thirty-eight highly myopic eyes from 82 adult participants were recruited. Macular sensitivity was evaluated using the Microperimeter MP-3. Retinal PD was measured using the PLEX Elite 9000 swept source optical coherence tomography angiography. Macular sensitivity values between different categories of MMD and its relationship with optical coherence tomography angiography measurements were evaluated using multivariable linear mixed models, adjusting for age and axial length.

RESULTS

Macular sensitivity reduced with increasing severity of MMD (β ≤ -0.95, P < 0.001), whereas the best-corrected visual acuity was not associated with MMD severity (P > 0.04). Persons who were older (β = -0.08, P < 0.001), with longer axial length (β = -0.32, P = 0.005), presence of macular diffuse choroidal atrophy (β = -2.16, P < 0.001) or worse MMD (β = -5.70, P < 0.001), and presence of macular posterior staphyloma (β ≤ -2.98, P < 0.001) or Fuchs spot (β = -1.58, P = 0.04) were associated with reduced macular sensitivity. Macular sensitivity was significantly associated with deep retinal PD in MMD (β = 0.15, P = 0.004) but not with superficial retinal PD (P = 0.62).

CONCLUSION

There was a strong correlation between reduced macular sensitivity and increasing MMD severity, even in mild MMD independent of the best-corrected visual acuity. Furthermore, macular sensitivity was correlated with deep retinal PD, suggesting a vasculature-function relationship in MMD.

Choriocapillaris Flow Deficits in Normal Chinese Imaged by Swept-Source Optical Coherence Tomographic Angiography

PURPOSE

To evaluate the ocular and systemic determinants of the choriocapillaris flow deficits percentage (CC FD%) in normal eyes.

DESIGN

Observational cross-sectional study.

METHODS

Healthy Chinese participants without ocular or systemic diseases underwent detailed ophthalmic evaluations, including swept-source optical coherence tomography angiography (SS-OCTA) with 6- × 6-mm macular choriocapillaris images. The CC FD% was assessed in circular regions with diameters of 1.0 and 5.0 mm, rings with 1.0- to 2.5-mm diameters, and rings with 2.5- to 5.0-mm diameters.

RESULTS

The study included 830 individuals (mean ± SD age 58.66 ± 8.75 years). CC FD% (mean ± SD 22.05% ± 1.13%) was the lowest in the 2.5- to 5.0-mm ring, followed by the 1.0- to 2.5-mm ring, and highest in the 1.0-mm circle. In multivariable analysis, a higher CC FD% was associated with older age (β = 0.16 [95% confidence interval {CI}] 0.08-0.24, P < .001), higher intraocular pressure (β = 0.34 [95% CI 0.25-0.42], P < .001), higher serum concentrations of high-density lipoprotein cholesterol (β = 0.24 [95% CI 0.17-0.32], P < .001), and lower image quality score (β = -0.22 [95% CI -0.30 to -0.14], P < .001). CC FD% was also independent of axial length.

CONCLUSIONS

In healthy adult Chinese individuals, a higher CC FD% was associated with older age, higher intraocular pressure, and higher high-density lipoprotein cholesterol serum concentration. These factors may influence clinical assessments of the choriocapillaris. The lack of an association between CC FD% and axial length is consistent with similar findings for Bruch membrane thickness, macular retinal thickness, and macular retinal pigment epithelium cell density.

Progression pattern of myopic maculopathy according to the severity of diffuse chorioretinal atrophy and choroidal thickness

This observational cohort study aimed to evaluate the progression pattern of diffuse chorioretinal atrophy (DCA) according to its severity. Highly myopic eyes with DCA were graded according to its extent in the 532-nm (green) and 633-nm (red) wavelengths images of the Optos ultra-widefield scanning laser ophthalmoscope at baseline: grade 1 and 2 were defined when increased reflectance at peripapillary region, not beyond the fovea, were observed in red laser image only and in both laser images, respectively; grade 3 and 4 were defined when increased reflectance beyond the fovea were observed in red laser image only and in both laser images, respectively. A total of 307 eyes (221 patients) were included, and progression of myopic maculopathy during follow-up of ≥ 3 years was evaluated. The mean visual acuity and subfoveal choroidal thickness (CT) differed among DCA grades (P = 0.015 and P < 0.001); a higher DCA grade had worse visual acuity and thinner choroid. During follow-up, development of patchy atrophy (PA) was observed in 3.2%, 5.5%, 12.8%, and 23.2% (P < 0.001), while changes in lacquer crack (LC) and/or development of myopic macular neovascularization were observed in 20.6%, 29.1%, 33.3%, and 15.8% (P = 0.061) of 63, 110, 39, and 95 eyes with DCA grade of 1, 2, 3, and 4 at baseline, respectively. New LC formation tended to occur in eyes with thicker CT at baseline compared to PA development and progression of pre-existing LC. In highly myopic eyes with DCA, progression pattern of myopic maculopathy is different according to its severity and CT at baseline. Grading based on separated wavelength images of ultra-widefield scanning laser ophthalmoscope is useful to evaluate the severity and prognosis of DCA in Asian patients with high myopia.

Choriocapillaris Changes in Myopic Macular Degeneration

Purpose

Myopic macular degeneration (MMD) can cause irreversible vision loss. Thinner choroid is associated with increased MMD severity. This cross-sectional study analyzed choriocapillaris (CC) alterations in MMD.

Methods

Axial length (AL), best-corrected visual acuity (BCVA), fundus photography, and swept-source optical coherence tomography angiography (SS-OCTA) were assessed in controls and high myopes (spherical equivalent ≤ −6 diopters). Myopic patients with grade 2 MMD (macular diffuse chorioretinal atrophy [MDCA]), high axial myopia (AL ≥ 26.5 mm), and BCVA ≥ 20/40 were compared with controls without MMD. CC mean thickness was measured from 3 × 3-mm SS-OCTA scans by identifying CC peaks in A-scan intensity profiles. CC flow deficit percent (CC FD%) was quantified using a fuzzy C-mean local thresholding method on en face OCTA images. Multivariate regressions compared CC thickness and CC FD% between myopic patients and controls, correcting for age and other confounders.

Results

Sixteen eyes with MDCA (AL, 26.96–33.93 mm; ages, 40–78 years) were compared with 51 control eyes (AL, 21.65–25.84 mm; ages, 19–88 years). CC thickness in patients with MDCA was 66% lower than that in controls (5.23 ± 0.68 µm [mean ± SD] vs. 15.46 ± 1.82 µm; P < 0.001). CC FD% in patients with MDCA was 237% greater than in controls (26.5 ± 4.3 vs. 11.2 ± 4.6; P < 0.001).

Conclusions

Patients with MDCA with good visual acuity had thinner CC and increased CC FD%, or reduced CC flow, compared with controls. Patients with grade 2 MMD and good visual acuity demonstrated significant choriocapillaris alterations, suggesting that choriocapillaris perfusion defects contribute to the pathogenesis of MMD.

Translational Relevance

Given the potential vascular etiology for MMD, current research about revascularization of ischemic retina likely has implications for the treatment of MMD.

Choroidal Thickness and Its Association With Age, Axial Length, and Refractive Error in Chinese Adults

Purpose

To identify the association between the choroidal thickness (ChT) with age and axial length (AL) under different refractive errors (REs) in Chinese adults.

Methods

Swept-source optical coherence tomography was used to measure ChT in 2126 right eyes of 2126 participants. The participants were classified as having pathologic myopia (PM), high myopia without PM (HM), low myopia (LM), and nonmyopia (non-M) according to their REs and META-PM (the Meta-Analysis of Pathologic Myopia) classification criteria.

Results

The mean age was 52.49 ± 20.39 years (range, 18−93 years), and the mean RE was −5.27 ± 5.37 diopters (D; range, −25.5 to +7.75 D). The mean average ChT was 159.25 ± 80.75 µm and decreased in a linear relationship from non-M to PM (190.04 ± 72.64 µm to 60.99 ± 37.58 µm, P < 0.001). A significant decline in ChT was noted between 50 and 70 years (r = −0.302, P < 0.001) and less rapidly after the age of 70 years (r = −0.105, P = 0.024). No correlation was noted between age and ChT under 50 years (P = 0.260). A significantly higher association with AL was noted in the central fovea (β^HM = −23.92, β^LM = −23.88, β^Non-M = −18.80, all P < 0.001) and parafoveal ChT (β^HM = −22.87, β^LM = −22.31, β^Non-M = −18.61, all P < 0.001) when compared with the perifoveal region (β^HM = −19.80, β^LM = −18.29, β^Non-M = −13.95, all P < 0.001). Within each group of PM, HM, LM, and non-M, regression analysis showed that the coefficients of age and AL with different macular regions of ChT varied significantly.

Conclusions

ChT was negatively correlated with age after 50 years. The thinning of the choroid was more prominent in the center and parafoveal regions as AL increased. Varied distributions of ChT decrease associated with AL and age were noted among different refractive groups.

Vascular endothelial growth factor inhibitors for predominantly Caucasian myopic choroidal neovascularization: 2-year treatment outcomes in clinical practice: data from the Fight Retinal Blindness! Registry

Purpose

To report the 24‐month outcomes of vascular endothelial growth factor (VEGF) inhibitors for myopic choroidal neovascularization (mCNV) in predominantly Caucasian eyes in routine clinical practice.

Methods

Retrospective analysis of treatment‐naïve eyes starting intravitreal injection of VEGF inhibitors of either bevacizumab (1.25 mg) or ranibizumab (0.5 mg) for mCNV from 1 January 2006 to 31 May 2018 that were tracked in the Fight Retinal Blindness! registry.

Results

We identified 203 eyes (bevacizumab–85 and ranibizumab–118) of 189 patients. The estimated mean (95% CI) change in VA over 24 months for all eyes using longitudinal models was +8 (5, 11) letters with a median (Q1, Q3) of 3 (2, 5) injections given mostly during the first year. The estimated mean change in VA at 24 months was similar between bevacizumab and ranibizumab [+9 (5, 13) letters for bevacizumab versus +9 (6, 13) letters for ranibizumab; p = 0.37]. Both agents were also similar in the mCNV activity outcomes, treatment frequency and visit frequency.

Conclusions

The 24‐month treatment outcomes of VEGF inhibitors for mCNV were favourable in this largest series yet reported of predominantly Caucasian eyes in routine clinical practice, with approximately two lines of visual gain and a median of three injections given mostly during the first year. These outcomes are similar to those reported for predominantly Asian eyes. Bevacizumab appeared to be as safe and effective as ranibizumab.

Prevalence of Myopic Macular Features in Dutch Individuals of European Ancestry With High Myopia

Question

What is the prevalence of myopic macular degeneration in Dutch individuals of European ancestry with high myopia?

Findings

In this cross-sectional study of 626 individuals with European ancestry with high myopia, the prevalence of myopic macular degeneration was 25.9% and increased with older age, lower spherical equivalent of refractive error, and higher axial length.

Meaning

Myopic retinal features were frequent in this highly myopic study population, but not different than patients of Asian ancestry with similar risk profiles.

Importance

High myopia incidence and prevalence is increasing worldwide, and the visual burden caused by myopia is expected to rise accordingly. Studies investigating the occurrence of myopic complications in individuals of European ancestry with high myopia are scarce, hampering insights into the frequency of myopic retinal complications in European individuals and their visual burden.

Objective

To assess the frequency of myopic macular features in individuals of European ancestry with high myopia.

Design, Setting, and Participants

This cross-sectional analysis of the Dutch Myopia Study (MYST) and individuals with high myopia from the Rotterdam Study (RS) included 626 patients with high myopia (spherical equivalent of refractive error [SER] ≤−6 diopters [D] or axial length [AL] ≥26 mm) who underwent an extensive ophthalmic examination including multimodal retinal imaging. In addition to this combination of a population-based cohort study and mix-based high myopia study, a systematic literature review was also performed to compare findings with studies of individuals of Asian ancestry.

Exposures

High myopia, age, and AL.

Main Outcomes and Measures

Frequency of myopic macular and optic disc features: tessellated fundus, myopic macular degeneration (MMD), staphyloma, peripapillary intrachoroidal cavitation, peripapillary atrophy (PPA), and “plus” lesions (choroidal neovascularization, Fuchs spot, and lacquer cracks).

Results

The mean (SD) SER of the combined study population (MYST and RS) was −9.9 (3.2) D; the mean (SD) age was 51.4 (15.1) years, and 387 (61.8%) were women. The prevalence of MMD was 25.9% and increased with older age (P for trend <.001), lower SER (odds ratio [OR], 0.70; 95% CI, 0.65-0.76; P < .001), and higher AL (OR, 2.53; 95% CI, 2.13-3.06; P < .001). Choroidal neovascularization or Fuchs spot was present in 2.7% (n = 17), both lesions in 0.3% (n = 2), and lacquer cracks in 1.4% (n = 9). Staphyloma, PPA, and MMD were highly prevalent in visual impaired and blind eyes (frequency was 73.9% [20 of 27], 90.5% [19 of 21], and 63.0% [17 of 27] of unilateral blind eyes for MMD, staphyloma, and PPA, respectively). Seven previous studies in Asian populations reported a variable MMD frequency ranging from 8.3% to 64%, but frequencies were similar for comparable risk profiles based on age and SER.

Conclusions and Relevance

In this cross-sectional study of a highly myopic Dutch population of European ancestry, myopic retinal features were frequent; were associated with age, SER, and AL; and occurred in all visually severely impaired eyes. The absence of treatment options for most of these retinal complications emphasizes the need for effective strategies to prevent high myopia.

Evaluation of Choroidal Thickness Using Optical Coherent Tomography: A Review

The choroid is the main source of blood and nourishment supply to the eye. The dysfunction of the choroid has been implicated in various retinal and choroidal diseases. The identification and in-depth understanding of pachychoroid spectrum disorders are based on the tremendous progress of optical coherence tomography (OCT) technology in recent years, although visibility of choroid is challenging in the era of the time or spectral domain OCT. The recent rapid revolution of OCTs, such as the enhanced depth imaging OCT and the swept-source OCT, has greatly contributed to the significant improvement in the analysis of the morphology and physiology of the choroid precisely, especially to the choroid-scleral boundary and vasculature. The present review highlights the recently available evidence on the measurement methodology and the clinical significance of choroidal thickness in retinal or choroidal disorders.

Assessment of Scleral Contour Changes in High Myopia by Optical Coherence Tomography

Purpose

This study aimed to establish and validate optical coherence tomography (OCT) based diagnostic criteria of high myopia.

Methods

This was a cross-sectional study including 100 eyes of high myopia with axial length larger than 26.5 mm and 100 control eyes, which were examined by spectral-domain OCT. Vertical and horizontal OCT of 9 mm scanning across fovea were analyzed. OCT characteristics including mirror artifact, scleral sink due to steep inclination of posterior sclera, scleral visibility, abnormality of outer retinal layer, foveoschisis, and dome-shaped macula were assessed in each group.

Results

The mean axial length was 28.65 ± 2.07 mm (range, 26.51–34.59 mm) in high myopia group and 23.79 ± 0.99 mm (range, 21.26–25.94 mm) in control group. Among the OCT characteristics noted at high frequency in the eyes with high myopia, three criteria achieving high sensitivity and specificity were determined: scleral sink over 500 μm, scleral visibility over 100 μm, and dome-shaped macula. Under conditions of presence of any of three criteria in either horizontal or vertical OCT scanning, the diagnostic sensitivity, specificity, positive predictive value, and negative predictive value for high myopia were found to be 95.0%, 98.0%, 98.0%, and 95.1%, respectively. In a new set of OCT images from 50 eyes with high myopia and 50 eyes of nonhigh myopia cases, the OCT-based criteria also proved similar level of diagnostic validity.

Conclusions

The OCT-based criteria, which directly addressed posterior scleral contour changes, may lead to an intuitive and accurate diagnosis of high myopia. Also, the criteria may contribute to early detection and monitoring of eyes that cannot be defined as high myopia but can progress. OCT may be useful for monitoring high myopia patients as OCT can detect myopia-associated retinal pathologies as well as scleral contour changes.

Automatic Screening and Identifying Myopic Maculopathy on Optical Coherence Tomography Images Using Deep Learning

Purpose

The purpose of this study was to engineer deep learning (DL) models that can identify myopic maculopathy in patients with high myopia based on optical coherence tomography (OCT) images.

Methods

An artificial intelligence (AI) system was developed using 2342 qualified OCT macular images from 1041 patients with pathologic myopia admitted to the Affiliated Eye Hospital of Wenzhou Medical University (WMU). We adopted an ResNeSt101 architecture to train five independent models to identify the following five myopic maculopathies: macular choroidal thinning, macular Bruch membrane (BM) defects, subretinal hyper-reflective material (SHRM), myopic traction maculopathy (MTM), and dome-shaped macula (DSM). We tested the models with an independent test dataset that included 450 images obtained from 297 patients with high myopia. Focal loss was used to address class imbalance, and optimal operating thresholds were determined according to the Youden Index. The performance was quantified using the area under the receiver operating characteristic (AUC), sensitivity, specificity, and confusion matrix.

Results

For the identification of myopic maculopathy, the AUCs of receiver operating characteristic (ROC) curves were 0.927 to 0.974 for 5 myopic maculopathies. Our AI system achieved sensitivities equal to or even better than those of junior retinal specialists (56.16–99.73%). The diagnosis of it is also interpretable that we provide visual explanations clearly via heatmaps.

Conclusions

We developed a convolutional neural network (CNN)-based DL AI system for detection and classification of myopic maculopathy in patients with high myopia using OCT macular images. Our AI system achieved sensitivities equal to or even better than those of junior retinal specialists.

Translational Relevance

This AI system can be widely applied in sophisticated situations in large-scale high myopia screening.

Choroidal remodeling distribution pattern in the macular region in Chinese young patients with myopia

Background

The pathogenesis of myopia has been found to be associated with the blood supply of the choroid. This study aimed to determine the relationship between the distribution pattern of choroidal remodeling and the degree of myopia in young patients.

Methods

Young patients (age < 18 years) with the spherical equivalent of less than − 12 diopters (D) were included. Spectral-domain optical coherence tomography (SD-OCT) with enhanced depth imaging (EDI) modality was used to measure the choroidal thickness (CT) and choroidal vascularity index (CVI) in the macular regions. CVI was calculated as the proportion of luminal area to choroidal area and was measured within 1 mm and 3 mm nasal (N1 and N3), temporal (T1 and T3), superior (S1 and S3), and inferior (I1 and I3) to the foveal center. CVI was compared across different ages (i.e., 5 ~ 9 years, 10 ~ 13 years, and 14 ~ 18 years), axial lengths (ALs) (i.e., 21.00 ~ 25.00 mm and 25.01 ~ 29.00 mm), and spherical equivalents (SEs) (i.e., SE > -0.5D, − 0.5 ~ − 3.0D, − 3.01 ~ − 6.0D, and < − 6.0D). Linear regression analysis was applied to assess the association between independent (i.e., age, AL, SE, and intraocular pressure) and dependent variables (i.e., CVI of different regions).

Results

One hundred sixty-four eyes from 85 volunteers were included. The mean CT in the central foveal was 269.87 ± 63.32 μm (93.00 μm to 443.00 μm). The mean subfoveal-CVI was 67.66 ± 2.40% (57.84 to 79.60%). Multiple linear regression results revealed significant correlations between SE and T1-CVI (p < 0.05, r² = 0.082, β = 0.194), N1-CVI (p < 0.05, r² = 0.039, β = 0.212). Simple linear regression results revealed that T1-CVI (p < 0.05, r² = 0.09) and T3-CVI (p < 0.05, r² = 0.05) were negatively correlated with SE; N1-CVI (p < 0.05, r² = 0.05) and N3-CVI (p < 0.05, r² = 0.04) were negatively correlated with SE.

Conclusions

CVI in the horizontal meridian underwent the largest change as myopia worsened. Temporal and nasal CVIs within the r = 1 mm, and r = 3 mm subfoveal range were positively associated with the degree of myopia in young patients. The CVI value may be used to assess the vascular status of the choroid and be a potential marker of myopic progression.