Correlation of choroidal thickness with age in healthy subjects: automatic detection and segmentation using a deep learning model

Pachyvitelliform maculopathy: an optical coherence tomography analysis of a novel entity

PURPOSE

To describe the optical coherence tomography features of pachyvitelliform maculopathy (PVM), an acquired vitelliform lesion (AVL) associated with pachychoroid disease.

METHODS

This study was a retrospective, multicentre, observational analysis.Medical records and multimodal imaging were reviewed in all patients with pachychoroid disease and AVL. Visual acuity, central choroidal thickness (CCT), AVL dimensions, total choroidal area, luminal choroidal area, stromal choroidal area and choroidal vascular index were measured in all eyes with PVM and compared with normal age-matched control eyes.

RESULTS

Mean age of the PVM group (17 eyes of 17 patients) was 71.41 years. Average follow-up was 33.15 months. Baseline VA was 20/40 in the PVM group and declined to 20/100 (p=0.006). AVLs were all detected overlying pachyvessels with optical coherence tomography and were all hyperautofluorescent with fundus autofluorescent imaging. Mean CCT in the PVM group was significantly greater (352.35 µm) than the CCT in the control group (226.88 µm, p<0.001). Retinal pigment epithelium (RPE) disruption was present in 64.71% of eyes with PVM at baseline and 41.18% developed macular atrophy at the end of follow-up.

CONCLUSIONS

PVM, defined by the presence of AVL associated with pachychoroid features, is a distinct novel entity of the pachychoroid disease spectrum. This study suggests a possible pathogenesis of RPE dysfunction secondary to a thick choroid, leading to accumulation of undigested photoreceptor outer segments and AVL. Clinicians should be aware of this common cause of vitelliform lesions and the poor visual prognosis due to the high risk of atrophy development.

GENETIC FACTORS AND CHARACTERISTICS ON SPECTRAL-DOMAIN OPTICAL COHERENCE TOMOGRAPHY ARE ASSOCIATED WITH CHOROIDAL THICKNESS IN ABCA4 -RELATED RETINOPATHY

PURPOSE

To investigate the possible correlation factors of choroidal thickness in ABCA4 -related retinopathy.

METHODS

A total of 66 patients were included in the cohort. It is a retrospective, cross-sectional laboratory investigation. The patients were tested using whole-exon sequencing and ophthalmic examinations, including slit-lamp examinations, best-corrected visual acuity, spectral-domain optical coherence tomography, fundus photograph, and fundus autofluorescence.

RESULTS

Besides demographic characteristics (age, onset age, duration), we selected genetic factors and ocular characteristics on spectral-domain optical coherence tomography as the candidates related to choroidal thickness. Mutation type (inframe mutation or premature termination codon), epiretinal membrane, retinal pigment epithelium- Bruch membrane integrity, and macular curvature changes were identified as related factors to choroidal thickness in ABCA4 -related retinopathy after the adjustment of Logistic LASSO regression.

CONCLUSION

Mutation type, epiretinal membrane, retinal pigment epithelium-Bruch membrane integrity, and macular curvature changes are related factors to choroidal thinning. These findings could provide us a further understanding for the pathological process and clinical features of ABCA4 mutation.

A Deep Learning-Based Fully Automated Program for Choroidal Structure Analysis Within the Region of Interest in Myopic Children

Purpose

To develop and validate a fully automated program for choroidal structure analysis within a 1500-µm-wide region of interest centered on the fovea (deep learning-based choroidal structure assessment program [DCAP]).

Methods

A total of 2162 fovea-centered radial swept-source optical coherence tomography (SS-OCT) B-scans from 162 myopic children with cycloplegic spherical equivalent refraction ranging from -1.00 to -5.00 diopters were collected to develop the DCAP. Medical Transformer network and Small Attention U-Net were used to automatically segment the choroid boundaries and the nulla (the deepest point within the fovea). Automatic denoising based on choroidal vessel luminance and binarization were applied to isolate choroidal luminal/stromal areas. To further compare the DCAP with the traditional handcrafted method, the luminal/stromal areas and choroidal vascularity index (CVI) values for 20 OCT images were measured by three graders and the DCAP separately. Intraclass correlation coefficients (ICCs) and limits of agreement were used for agreement analysis.

Results

The mean ± SD pixel-wise distances from the predicted choroidal inner, outer boundary, and nulla to the ground truth were 1.40 ± 1.23, 5.40 ± 2.24, and 1.92 ± 1.13 pixels, respectively. The mean times required for choroidal structure analysis were 1.00, 438.00 ± 75.88, 393.25 ± 78.77, and 410.10 ± 56.03 seconds per image for the DCAP and three graders, respectively. Agreement between the automatic and manual area measurements was excellent (ICCs > 0.900) but poor for the CVI (0.627; 95% confidence interval, 0.279-0.832). Additionally, the DCAP demonstrated better intersession repeatability.

Conclusions

The DCAP is faster than manual methods. Also, it was able to reduce the intra-/intergrader and intersession variations to a small extent.

Translational Relevance

The DCAP could aid in choroidal structure assessment.