Application of Artificial Intelligence and Deep Learning for Choroid Segmentation in Myopia

Choroidalyzer: An Open-Source, End-to-End Pipeline for Choroidal Analysis in Optical Coherence Tomography

Purpose

To develop Choroidalyzer, an open-source, end-to-end pipeline for segmenting the choroid region, vessels, and fovea, and deriving choroidal thickness, area, and vascular index.

Methods

We used 5600 OCT B-scans (233 subjects, six systemic disease cohorts, three device types, two manufacturers). To generate region and vessel ground-truths, we used state-of-the-art automatic methods following manual correction of inaccurate segmentations, with foveal positions manually annotated. We trained a U-Net deep learning model to detect the region, vessels, and fovea to calculate choroid thickness, area, and vascular index in a fovea-centered region of interest. We analyzed segmentation agreement (AUC, Dice) and choroid metrics agreement (Pearson, Spearman, mean absolute error [MAE]) in internal and external test sets. We compared Choroidalyzer to two manual graders on a small subset of external test images and examined cases of high error.

Results

Choroidalyzer took 0.299 seconds per image on a standard laptop and achieved excellent region (Dice: internal 0.9789, external 0.9749), very good vessel segmentation performance (Dice: internal 0.8817, external 0.8703), and excellent fovea location prediction (MAE: internal 3.9 pixels, external 3.4 pixels). For thickness, area, and vascular index, Pearson correlations were 0.9754, 0.9815, and 0.8285 (internal)/0.9831, 0.9779, 0.7948 (external), respectively (all P < 0.0001). Choroidalyzer's agreement with graders was comparable to the intergrader agreement across all metrics.

Conclusions

Choroidalyzer is an open-source, end-to-end pipeline that accurately segments the choroid and reliably extracts thickness, area, and vascular index. Especially choroidal vessel segmentation is a difficult and subjective task, and fully automatic methods like Choroidalyzer could provide objectivity and standardization.

Peripheral Choroidal Response to Localized Defocus Blur: Influence of Native Peripheral Aberrations

Purpose

This study aims to examine the short-term peripheral choroidal thickness (PChT) response to signed defocus blur, both with and without native peripheral aberrations. This examination will provide insights into the role of peripheral aberration in detecting signs of defocus.

Methods

The peripheral retina (temporal 15°) of the right eye was exposed to a localized video stimulus in 11 young adults. An adaptive optics system induced 2D myopic or hyperopic defocus onto the stimulus, with or without correcting native peripheral ocular aberrations (adaptive optics [AO] or NoAO defocus conditions). Choroidal scans were captured using Heidelberg Spectralis OCT at baseline, exposure (10, 20, and 30 minutes), and recovery phases (4, 8, and 15 minutes). Neural network-based automated MATLAB segmentation program measured PChT changes from OCT scans, and statistical analysis evaluated the effects of different optical conditions over time.

Results

During the exposure phase, NoAO myopic and hyperopic defocus conditions exhibited distinct bidirectional PChT alterations, showing average thickening (10.0 ± 5.3 µm) and thinning (-9.1 ± 5.5 µm), respectively. In contrast, induced AO defocus conditions did not demonstrate a significant change from baseline. PChT recovery to baseline occurred for all conditions. The unexposed fovea did not show any significant ChT change, indicating a localized ChT response to retinal blur.

Conclusions

We discovered that the PChT response serves as a marker for detecting peripheral retinal myopic and hyperopic defocus blur, especially in the presence of peripheral aberrations. These findings highlight the significant role of peripheral oriented blur in cueing peripheral defocus sign detection.

Insights into artificial intelligence in myopia management: from a data perspective

Given the high incidence and prevalence of myopia, the current healthcare system is struggling to handle the task of myopia management, which is worsened by home quarantine during the ongoing COVID-19 pandemic. The utilization of artificial intelligence (AI) in ophthalmology is thriving, yet not enough in myopia. AI can serve as a solution for the myopia pandemic, with application potential in early identification, risk stratification, progression prediction, and timely intervention. The datasets used for developing AI models are the foundation and determine the upper limit of performance. Data generated from clinical practice in managing myopia can be categorized into clinical data and imaging data, and different AI methods can be used for analysis. In this review, we comprehensively review the current application status of AI in myopia with an emphasis on data modalities used for developing AI models. We propose that establishing large public datasets with high quality, enhancing the model's capability of handling multimodal input, and exploring novel data modalities could be of great significance for the further application of AI for myopia.

Evaluation of an Automated Choroid Segmentation Algorithm in a Longitudinal Kidney Donor and Recipient Cohort

Purpose

To evaluate the performance of an automated choroid segmentation algorithm in optical coherence tomography (OCT) data using a longitudinal kidney donor and recipient cohort.

Methods

We assessed 22 donors and 23 patients requiring renal transplantation over up to 1 year posttransplant. We measured choroidal thickness (CT) and area and compared our automated CT measurements to manual ones at the same locations. We estimated associations between choroidal measurements and markers of renal function (estimated glomerular filtration rate [eGFR], serum creatinine, and urea) using correlation and linear mixed-effects (LME) modeling.

Results

There was good agreement between manual and automated CT. Automated measures were more precise because of smaller measurement error over time. External adjudication of major discrepancies was in favor of automated measures. Significant differences were observed in the choroid pre- and posttransplant in both cohorts, and LME modeling revealed significant linear associations observed between choroidal measures and renal function in recipients. Significant associations were mostly stronger with automated CT (eGFR, P < 0.001; creatinine, P = 0.004; urea, P = 0.04) compared to manual CT (eGFR, P = 0.002; creatinine, P = 0.01; urea, P = 0.03).

Conclusions

Our automated approach has greater precision than human-performed manual measurements, which may explain stronger associations with renal function compared to manual measurements. To improve detection of meaningful associations with clinical endpoints in longitudinal studies of OCT, reducing measurement error should be a priority, and automated measurements help achieve this.

Translational Relevance

We introduce a novel choroid segmentation algorithm that can replace manual grading for studying the choroid in renal disease and other clinical conditions.

An Open-Source Deep Learning Algorithm for Efficient and Fully Automatic Analysis of the Choroid in Optical Coherence Tomography

Purpose

To develop an open-source, fully automatic deep learning algorithm, DeepGPET, for choroid region segmentation in optical coherence tomography (OCT) data.

Methods

We used a dataset of 715 OCT B-scans (82 subjects, 115 eyes) from three clinical studies related to systemic disease. Ground-truth segmentations were generated using a clinically validated, semiautomatic choroid segmentation method, Gaussian Process Edge Tracing (GPET). We finetuned a U-Net with the MobileNetV3 backbone pretrained on ImageNet. Standard segmentation agreement metrics, as well as derived measures of choroidal thickness and area, were used to evaluate DeepGPET, alongside qualitative evaluation from a clinical ophthalmologist.

Results

DeepGPET achieved excellent agreement with GPET on data from three clinical studies (AUC = 0.9994, Dice = 0.9664; Pearson correlation = 0.8908 for choroidal thickness and 0.9082 for choroidal area), while reducing the mean processing time per image on a standard laptop CPU from 34.49 ± 15.09 seconds using GPET to 1.25 ± 0.10 seconds using DeepGPET. Both methods performed similarly according to a clinical ophthalmologist who qualitatively judged a subset of segmentations by GPET and DeepGPET, based on smoothness and accuracy of segmentations.

Conclusions

DeepGPET, a fully automatic, open-source algorithm for choroidal segmentation, will enable researchers to efficiently extract choroidal measurements, even for large datasets. As no manual interventions are required, DeepGPET is less subjective than semiautomatic methods and could be deployed in clinical practice without requiring a trained operator.

Translational Relevance

DeepGPET addresses the lack of open-source, fully automatic, and clinically relevant choroid segmentation algorithms, and its subsequent public release will facilitate future choroidal research in both ophthalmology and wider systemic health.

Effects of dopamine D2 receptor antagonists on retinal pigment epithelial/choroid complex metabolism in form-deprived myopic guinea pigs

The retinal pigment epithelial (RPE)/choroid complex regulates myopia development, but the precise pathogenesis of myopia remains unclear. We aimed to investigate the changes in RPE/choroid complex metabolism in a form deprivation myopia model after dopamine D2 receptor (D2R) modulation. Guinea pigs were randomly divided into normal (NC), form deprivation myopia (FDM), and FDM treated with dopamine D2R antagonist groups. Differential metabolites were screened using SIMCA-P software and MetaboAnalyst metabolomics analysis tool. Functions of differential metabolites were analyzed using KEGG enrichment pathways. Relative to the NC group, 38 differential metabolites were identified, comprising 29 increased metabolites (including nicotinic acid, cytosine, and glutamate) and 9 decreased metabolites, of which proline exhibited the largest decrease. Pathway analysis revealed regulation of arginine/proline and aspartate/glutamate metabolism. Intravitreal D2R antagonist injection increased proline concentrations and activated arginine/proline and purine metabolism pathways. In sum, D2R antagonists alleviated the myopia trend of refractive biological parameters in form deprivation myopic guinea pigs, suggesting the involvement of dopamine D2R signaling in myopia pathogenesis. The RPE/choroid may provide glutamate to the retina by activating proline metabolism via metabolic coupling with the retina. Dopamine D2R antagonism may modulate proline/arginine metabolic pathways in the RPE/choroid and regulate metabolism, information presentation, and myopia.

Artificial intelligence in retinal image analysis: Development, advances, and challenges

Modern advances in diagnostic technologies offer the potential for unprecedented insight into ophthalmic conditions relating to the retina. We discuss the current landscape of artificial intelligence in retina with respect to screening, diagnosis, and monitoring of retinal pathologies such as diabetic retinopathy, diabetic macular edema, central serous chorioretinopathy, and age-related macular degeneration. We review the methods used in these models and evaluate their performance in both research and clinical contexts and discuss potential future directions for investigation, use of multiple imaging modalities in artificial intelligence algorithms, and challenges in the application of artificial intelligence in retinal pathologies.

IMI 2023 Digest

Myopia is a dynamic and rapidly moving field, with ongoing research providing a better understanding of the etiology leading to novel myopia control strategies. In 2019, the International Myopia Institute (IMI) assembled and published a series of white papers across relevant topics and updated the evidence with a digest in 2021. Here, we summarize findings across key topics from the previous 2 years. Studies in animal models have continued to explore how wavelength and intensity of light influence eye growth and have examined new pharmacologic agents and scleral cross-linking as potential strategies for slowing myopia. In children, the term premyopia is gaining interest with increased attention to early implementation of myopia control. Most studies use the IMI definitions of ≤-0.5 diopters (D) for myopia and ≤-6.0 D for high myopia, although categorization and definitions for structural consequences of high myopia remain an issue. Clinical trials have demonstrated that newer spectacle lens designs incorporating multiple segments, lenslets, or diffusion optics exhibit good efficacy. Clinical considerations and factors influencing efficacy for soft multifocal contact lenses and orthokeratology are discussed. Topical atropine remains the only widely accessible pharmacologic treatment. Rebound observed with higher concentration of atropine is not evident with lower concentrations or optical interventions. Overall, myopia control treatments show little adverse effect on visual function and appear generally safe, with longer wear times and combination therapies maximizing outcomes. An emerging category of light-based therapies for children requires comprehensive safety data to enable risk versus benefit analysis. Given the success of myopia control strategies, the ethics of including a control arm in clinical trials is heavily debated. IMI recommendations for clinical trial protocols are discussed.

Artificial intelligence technology for myopia challenges: A review

Myopia is a significant global health concern and affects human visual function, resulting in blurred vision at a distance. There are still many unsolved challenges in this field that require the help of new technologies. Currently, artificial intelligence (AI) technology is dominating medical image and data analysis and has been introduced to address challenges in the clinical practice of many ocular diseases. AI research in myopia is still in its early stages. Understanding the strengths and limitations of each AI method in specific tasks of myopia could be of great value and might help us to choose appropriate approaches for different tasks. This article reviews and elaborates on the technical details of AI methods applied for myopia risk prediction, screening and diagnosis, pathogenesis, and treatment.

Choroidal layer segmentation in OCT images by a boundary enhancement network

Morphological changes of the choroid have been proved to be associated with the occurrence and pathological mechanism of many ophthalmic diseases. Optical Coherence Tomography (OCT) is a non-invasive technique for imaging of ocular biological tissues, that can reveal the structure of the retinal and choroidal layers in micron-scale resolution. However, unlike the retinal layer, the interface between the choroidal layer and the sclera is ambiguous in OCT, which makes it difficult for ophthalmologists to identify with certainty. In this paper, we propose a novel boundary-enhanced encoder-decoder architecture for choroid segmentation in retinal OCT images, in which a Boundary Enhancement Module (BEM) forms the backbone of each encoder-decoder layer. The BEM consists of three parallel branches: 1) a Feature Extraction Branch (FEB) to obtain feature maps with different receptive fields; 2) a Channel Enhancement Branch (CEB) to extract the boundary information of different channels; and 3) a Boundary Activation Branch (BAB) to enhance the boundary information via a novel activation function. In addition, in order to incorporate expert knowledge into the segmentation network, soft key point maps are generated on the choroidal boundary, and are combined with the predicted images to facilitate precise choroidal boundary segmentation. In order to validate the effectiveness and superiority of the proposed method, both qualitative and quantitative evaluations are employed on three retinal OCT datasets for choroid segmentation. The experimental results demonstrate that the proposed method yields better choroid segmentation performance than other deep learning approaches. Moreover, both 2D and 3D features are extracted for statistical analysis from normal and highly myopic subjects based on the choroid segmentation results, which is helpful in revealing the pathology of high myopia. Code is available at https://github.com/iMED-Lab/Choroid-segmentation.

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.

Ocular and Hemodynamic Factors Contributing to the Central Visual Function in Glaucoma Patients With Myopia

Purpose

The purpose of this study was to investigate the ocular and hemodynamic factors contributing to the central visual function in glaucoma patients with myopia.

Methods

This study was a prospective observational study, which included 236 eyes of 140 patients with normal-tension glaucoma (NTG), which includes 114 eyes with mild myopia (axial length ≥24 and <26 mm) and 122 eyes with moderate-to-severe myopia (axial length ≥26 mm). Ocular characteristics were axial length and posterior pole profiles, including peripapillary atrophy (PPA) to disc area ratio, disc tilt ratio, disc torsion, and disc-foveal angle. Hemodynamic factors included standard deviation of the mean of qualified normal-to-normal intervals (SDNN) of a heart rate variability (HRV) test and vessel density (VD) parameters from optical coherence tomography angiography (OCTA). The root mean square error was estimated as a measure of the VD fluctuation. Association between ocular characteristics and VD parameters of the OCTA with the central sensitivity of the 10-degree visual field or the presence of central scotoma were analyzed.

Results

Deep layer VD of the peripapillary and macular areas showed significant differences between mild and moderate-to-severe myopia (P = 0.034 and P = 0.045, respectively). Structural parameters, especially PPA to disc area ratio, had significant correlation with peripapillary VD parameters in myopic eyes. Lower SDNN value (ß = 0.924, P = 0.011), lower deep VD of the macular area (ß = 0.845, P = 0.001), and greater fluctuation of deep VD in the peripapillary area (ß = 1.517, P = 0.005) were associated with the presence of central scotoma in patients with glaucoma with myopia in multivariate logistic regression analysis.

Conclusions

The structural changes by myopia, especially in the peripapillary region, affected VD parameters in myopic eyes. Lower deep VD and greater VD fluctuation in the peripapillary region showed association with central scotoma in patients with glaucoma with myopia, suggesting both structural and vascular changes by myopia may be related to central visual function in glaucoma patients with myopia.