Correlation between choroidal thickness and intraocular pressure control in primary angle-closure glaucoma

ChoroidSeg-ViT: A Transformer Model for Choroid Layer Segmentation Based on a Mixed Attention Feature Enhancement Mechanism

Purpose

To develop a Vision Transformer (ViT) model based on the mixed attention feature enhancement mechanism, ChoroidSeg-ViT, for choroid layer segmentation in optical coherence tomography (OCT) images.

Methods

This study included a dataset of 100 OCT B-scans images. Ground truths were carefully labeled by experienced ophthalmologists. An end-to-end local-enhanced Transformer model, ChoroidSeg-ViT, was designed to segment the choroid layer by integrating the local enhanced feature extraction and semantic feature fusion paths. Standard segmentation metrics were selected to evaluate ChoroidSeg-ViT.

Results

Experimental results demonstrate that ChoroidSeg-ViT exhibited superior segmentation performance (mDice: 98.31, mIoU: 96.62, mAcc: 98.29) compared to other deep learning approaches, thus indicating the effectiveness and superiority of this proposed model for the choroid layer segmentation task. Furthermore, ablation and generalization experiments validated the reasonableness of the module design.

Conclusions

We developed a novel Transformer model to precisely and automatically segment the choroid layer and achieved the state-of-the-art performance.

Translational Relevance

ChoroidSeg-ViT could segment precise and smooth choroid layers and form the basis of an automatic choroid analysis system that would facilitate future choroidal research in ophthalmology.

Three-dimensional choroidal vascularity index and choroidal thickness in fellow eyes of acute and chronic primary angle-closure using swept-source optical coherence tomography

AIM

To compare the three-dimensional choroidal vascularity index (CVI) and choroidal thickness between fellow eyes of acute primary angle-closure (F-APAC) and chronic primary angle-closure glaucoma (F-CPACG) and the eyes of normal controls.

METHODS

This study included 37 patients with unilateral APAC, 37 with asymmetric CPACG without prior treatment, and 36 healthy participants. Using swept-source optical coherence tomography (SS-OCT), the macular and peripapillary choroidal thickness and three-dimensional CVI were measured and compared globally and sectorally. Pearson's correlation analysis and multivariate regression models were used to evaluate choroidal thickness or CVI with related factors.

RESULTS

The mean subfoveal CVIs were 0.35±0.10, 0.33±0.09, and 0.29±0.04, and the mean subfoveal choroidal thickness were 315.62±52.92, 306.22±59.29, and 262.69±45.55 µm in the F-APAC, F-CPACG, and normal groups, respectively. All macular sectors showed significantly higher CVIs and choroidal thickness in the F-APAC and F-CPACG eyes than in the normal eyes (P<0.05), while there were no significant differences between the F-APAC and F-CPACG eyes. In the peripapillary region, the mean overall CVIs were 0.21±0.08, 0.20±0.08, and 0.19±0.05, and the mean overall choroidal thickness were 180.45±54.18, 174.82±50.67, and 176.18±37.94 µm in the F-APAC, F-CPACG, and normal groups, respectively. There were no significant differences between any of the two groups in all peripapillary sectors. Younger age, shorter axial length, and the F-APAC or F-CPACG diagnosis were significantly associated with higher subfoveal CVI and thicker subfoveal choroidal thickness (P<0.05).

CONCLUSION

The fellow eyes of unilateral APAC or asymmetric CPACG have higher macular CVI and choroidal thickness than those of the normal controls. Neither CVI nor choroidal thickness can distinguish between eyes predisposed to APAC or CPACG. A thicker choroid with a higher vascular volume may play a role in the pathogenesis of primary angle-closure glaucoma.

Comparison of the Choroid in Primary Open Angle and Angle Closure Glaucoma Using Optical Coherence Tomography

PRCIS

The current study highlights distinct choroidal alterations in primary open angle (POAG) and primary angle closure (PACG) glaucomas, underscoring the potential of the Choroidal Vascularity Index (CVI) as a valuable indicator for understanding glaucoma pathogenesis.

PURPOSE

To evaluate choroidal structural changes in patients with POAG and PACG and healthy controls utilizing the CVI and subfoveal choroidal thickness by enhanced depth imaging optical coherence tomography.

METHODS

This study was cross-sectional. A total of 171 eyes of 171 subjects, comprising 69 eyes with untreated POAG, 58 eyes with untreated PACG, and 44 healthy eyes, were enrolled in this study. Subfoveal choroidal thickness, luminal area (LA), stromal area (SA), and total choroidal area were measured on enhanced depth imaging-optical coherence tomography scans. The CVI parameter is calculated as the proportion of LA to the total choroidal area.

RESULTS

This study included 69 patients with POAG with a mean age of 51.4 ± 13.3 years, 58 patients with PACG with a mean age of 57.0 ± 7.3 years, and 44 healthy subjects with a mean age of 51.11 ± 10.7 years. The CVI in the POAG and PACG groups was significantly lower than that in the control group ( P = 0.001 and P = 0.005, respectively); however, not significantly different between the two glaucoma groups ( P = 1.000). POAG eyes had significantly lower LA than PACG and controls ( P = 0.014 and P = 0.049, respectively), whereas PACG eyes had significantly greater SA than controls ( P = 0.041).

CONCLUSIONS

The CVI of POAG and PACG eyes was significantly lower than that of normal eyes. A reduced LA was observed mainly in eyes with POAG, and an increased SA was observed mainly in eyes with PACG. The role of the choroid may differ between POAG and PACG eyes.

Comparison of Lens Extraction Versus Laser Iridotomy on Anterior Segment, Choroid, and Intraocular Pressure in Primary Angle Closure Using Machine Learning

PRCIS

Treatment strategy of primary angle closure (PAC) is not clear due to the large number of clinical and anatomic-topographic parameters in PAC, influencing the treatment algorithm. Using the machine learning method DD-SIMCA, we justify the expediency of early lens extraction (LE) in PAC.

PURPOSE

To compare the anatomic and functional efficacy of LE and laser peripheral iridotomy (LPI) in patients with PAC using Machine Learning.

MATERIALS AND METHODS

This prospective study included 120 patients aged 41-80 years: 60 eyes with PAC, 30 with PAC suspects, and 30 with healthy eyes (control). Thirty PAC eyes with intraocular pressure (IOP) up to 30 mm Hg were treated using LE with intraocular lens implantation and 30 eyes with LPI. All subjects underwent Swept Source optical coherence tomography. We analyzed 35 parameters of each eye including the lens vault, the choroidal thickness, the anterior chamber angle, and iris specifications such as iris curvature. Considering the correlations between them, the machine learning method DD-SIMCA 1-class classification was applied: the proximity of each sample to the target class (control) was characterized by the total distance to it.

RESULTS

After LE, IOP was significantly lower than after LPI ( P =0). Every third eye with PAC after LE reached the target class: specificity according to DD-SIMCA equals 0.67. This was not observed for the eyes after LPI: specificity equals 1.0. After LE, all parameters of the anterior chamber angle did not differ from the control (all P >0.05). After LPI, there was an increase in anterior chamber depth ( P =0) and a decrease in lens vault ( P =0), but results comparable to the control were achieved only for iris curvature ( P =1.000).

CONCLUSION

The efficacy of LE in PAC is higher than LPI due to the better postoperative anterior chamber topography and lower IOP. This study lends further clinical and anatomic support to the emerging notion of LE as an effective treatment for PAC.

Changes in Anterior Chamber Angle and Choroidal Thickness in Patients with Primary Angle-Closure Glaucoma after Phaco-Goniosynechialysis

We aimed to observe changes in angle width and choroidal thickness (CT) before and after phacoemulsification intraocular lens implantation (PEI) combined with goniosynechialysis (GSL) in patients with primary angle-closure glaucoma (PACG) complicated by cataracts. This prospective cohort study included 60 patients with PACG complicated by cataracts from the Department of Ophthalmology of Shaoxing People’s Hospital, China. Patients underwent PEI combined with GSL (PEI-GSL group) or laser peripheral iridotomy (LPI) followed by PEI (PEI group). Intraocular pressure (IOP) and endothelial counts were significantly decreased in both groups after surgery, while best-corrected visual acuity and central anterior chamber depth were significantly increased. However, there were no significant differences between the two groups. The opening degrees of room corners at 12, 3, 6, and 9 o’clock were recorded as AA12, AA3, AA6, and AA9, respectively. Anterior chamber depth was significantly increased postoperatively compared to preoperatively in both groups, with no significant between-group differences (all ps > 0.05). At 1, 3, and 6 months postoperatively, the width at AA12, AA3, and AA9 points was higher in the PEI-GSL group than in the PEI group (all ps < 0.05). Significant between-group differences at AA6 were observed preoperatively (p = 0.023) and at 1 (p = 0.027) and 3 (p = 0.033) months postoperatively but not at 6 months postoperatively (p = 0.055). CT was smaller postoperatively than preoperatively (all ps < 0.001). The present study suggests that patients with PACG who underwent PEI with or without GSL had reduced IOP and CT after surgery.

[Primary anterior chamber angle closure: progression from suspect to glaucoma. Part 2. Predictors of primary angle closure]

To review the literature devoted to the search of predictors of primary angle closure (PAC) progression as an important link in the pathogenesis of primary angle-closure glaucoma. This part presents a cluster analysis, describes the mechanisms of PAC development, and considers the studies aimed at discovering the risk factors for the progression of primary angle closure suspect into true angle closure. The results of the analyzed literature are ambiguous, indicating the need for further research that would involve strict inclusion criteria, and a standard approach to defining the primary angle closure disease and expanding the diagnostic parameters, in which a key role belongs to anterior segment optical coherence tomography (AS-OCT).