Endoscopic Vitrectomy Combined with 3D Heads-Up Viewing System in Treating Traumatic Ocular Injury.

Purpose: To investigate effects and complications of endoscopic vitrectomy combined with 3D heads-up viewing system in treating traumatic ocular injury. Patients and Methods. This is a retrospective interventional case series in a tertiary referral center in Taiwan, and we included patients of traumatic ocular injury, and they underwent endoscopic vitrectomy combined with a 3D heads-up viewing system. Results: Fourteen eyes of traumatic globe injury from 14 patients were studied over a 30-month period. Preoperative VA ranged from no light perception (NLP) to 6/6. Postoperative visual acuity improved in 11 of the 14 eyes (79%). Until 6 months after surgery, all eyes had attached retina. The median logMAR BCVA was 2.4 at the first visit and 1.19 at the last visit (p = 0.0028). No subject suffered from retinal detachment, endophthalmitis, or other severe complications. Conclusions: Vitrectomy using endoscopy combined with 3D heads-up viewing system allowed early evaluation and intervention in traumatic ocular injuries. Most of our cases showed both anatomical and visual acuity improvements.

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

PROPOSE: The proposed deep learning model with a mask region-based convolutional neural network (Mask R-CNN) can predict choroidal thickness automatically. Changes in choroidal thickness with age can be detected with manual measurements. In this study, we aimed to investigate choroidal thickness in a comprehensive aspect in healthy eyes by utilizing the Mask R-CNN model. METHODS: A total of 68 eyes from 57 participants without significant ocular disease were recruited. The participants were allocated to one of three groups according to their age and underwent spectral domain optical coherence tomography (SD-OCT) or enhanced depth imaging OCT (EDI-OCT) centered on the fovea. Each OCT sequence included 25 slices. Physicians labeled the choroidal contours in all the OCT sequences. We applied the Mask R-CNN model for automatic segmentation. Comparisons of choroidal thicknesses were conducted according to age and prediction accuracy. RESULTS: Older age groups had thinner choroids, according to the automatic segmentation results; the mean choroidal thickness was 253.7 ± 41.9 µm in the youngest group, 206.8 ± 35.4 µm in the middle-aged group, and 152.5 ± 45.7 µm in the oldest group (p < 0.01). Measurements obtained using physician sketches demonstrated similar trends. We observed a significant negative correlation between choroidal thickness and age (p < 0.01). The prediction error was lower and less variable in choroids that were thinner than the cutoff point of 280 µm. CONCLUSION: By observing choroid layer continuously and comprehensively. We found that the mean choroidal thickness decreased with age in healthy subjects. The Mask R-CNN model can accurately predict choroidal thickness, especially choroids thinner than 280 µm. This model can enable exploring larger and more varied choroid datasets comprehensively, automatically, and conveniently.

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

PURPOSE: To investigate the correlation between choroidal thickness and myopia progression using a deep learning method. METHODS: Two data sets, data set A and data set B, comprising of 123 optical coherence tomography (OCT) volumes, were collected to establish the model and verify its clinical utility. The proposed mask region-based convolutional neural network (R-CNN) model, trained with the pretrained weights from the Common Objects in Context database as well as the manually labeled OCT images from data set A, was used to automatically segment the choroid. To verify its clinical utility, the mask R-CNN model was tested with data set B, and the choroidal thickness estimated by the model was also used to explore its relationship with myopia. RESULTS: Compared with the result of manual segmentation in data set B, the error of the automatic choroidal inner and outer boundary segmentation was 6.72 ± 2.12 and 13.75 ± 7.57 µm, respectively. The mean dice coefficient between the region segmented by automatic and manual methods was 93.87% ± 2.89%. The mean difference in choroidal thickness over the Early Treatment Diabetic Retinopathy Study zone between the two methods was 10.52 µm. Additionally, the choroidal thickness estimated using the proposed model was thinner in high-myopic eyes, and axial length was the most significant predictor. CONCLUSIONS: The mask R-CNN model has excellent performance in choroidal segmentation and quantification. In addition, the choroid of high myopia is significantly thinner than that of nonhigh myopia. TRANSLATIONAL RELEVANCE: This work lays the foundations for mask R-CNN models that could aid in the evaluation of more intricate changes occurring in chorioretinal diseases.

Automatic Segment and Quantify Choroid Layer in Myopic eyes: Deep Learning based Model.

PURPOSE: To report a rapid and accurate method based upon deep learning for automatic segmentation and measurement of the choroidal thickness (CT) in myopic eyes, and to determine the relationship between refractive error (RE) and CT. METHODS: Fifty-four healthy subjects 20-39 years of age were retrospectively reviewed. Data reviewed included age, gender, laterality, visual acuity, RE, and Enhanced Depth Imaging Optical Coherence Tomography (EDI-OCT) images. The choroid layer was labeled by manual and automatic method using EDI-OCT. A Mask Region-convolutional Neural Network (Mask R-CNN) model, using deep Residual Network (ResNet) and Feature Pyramid Networks (FPN) as a backbone network, was trained to automatically outline and quantify the choroid layer. RESULTS: ResNet 50 model was adopted for its 90% accuracy rate and 6.97 s average execution time. CT determined by the manual method had a mean thickness of 258.75 ± 66.11 µm, a positive correlation with RE (r = 0.596, p < .01) and significant association with gender (p = .011) and RE (p < .001) in multivariable linear regression analysis. Meanwhile, CT determined by deep learning presented a mean thickness of 226.39 ± 54.65 µm, a positive correlation with RE (r = 0.546, p < .01) and significant association with gender (p = .043) and RE (p < .001) in multivariable linear regression analysis. Both methods revealed that CT decreased with the increase in myopic RE. CONCLUSIONS: This deep learning method using Mask-RCNN was able to successfully determine the relationship between RE and CT in an accurate and rapid way. It could eliminate the need for manual process, while demonstrating a feasible clinical application.

Surgical outcomes and prognostic factors in traumatic retinal detachment following closed-globe injuries.

PURPOSE: To evaluate the anatomical and functional results of retinal detachment (RD) surgery following closed-globe injuries (CGI). METHODS: Patients treated with vitreoretinal surgeries due to RD following CGI from 2014 to 2020 were retrospectively reviewed. Data included demographics, mechanism of injury, preoperative evaluation, and surgical intervention. Outcome measurements included anatomic success, best corrected visual acuity (BCVA), and possible prognostic factors. RESULTS: A total of 67 eyes from 64 patients (49 males; mean age 52.84 years) were included. The most common causes of the CGI were work-related injury (22.4%) and traffic accidents (23.9%). The primary and final anatomic success rates were 80.6% (54/67) and 89.6% (60/67), respectively. In the multivariable analysis of the logistic regression models, the poor prognostic factor was proliferative vitreoretinopathy (PVR) (P = 0.009) for primary anatomic success. The median preoperative and final BCVA were logMAR 0.7 (IQR, 0.3-1.6) and logMAR 0.5 (IQR, 0.1-1.1), respectively (P = 0.077). Poorly presenting BCVA (counting fingers or worse) and giant tear were associated with poor visual outcomes. CONCLUSION: Work-related injuries and traffic accidents are the prevalent causes of RD following CGI. The anatomic outcomes were favorable, but visual outcomes varied. Poor prognostic factors included PVR and poorly presenting BCVA, highlighting the importance of a careful initial evaluation.