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.
The purpose of this article is to evaluate the accuracy of the optical coherence tomography (OCT) measurement of choroidal thickness in healthy eyes using a deep-learning method with the Mask R-CNN model. Thirty EDI-OCT of thirty patients were enrolled. A mask region-based convolutional neural network (Mask R-CNN) model composed of deep residual network (ResNet) and feature pyramid networks (FPNs) with standard convolution and fully connected heads for mask and box prediction, respectively, was used to automatically depict the choroid layer. The average choroidal thickness and subfoveal choroidal thickness were measured. The results of this study showed that ResNet 50 layers deep (R50) model and ResNet 101 layers deep (R101). R101 U R50 (OR model) demonstrated the best accuracy with an average error of 4.85 pixels and 4.86 pixels, respectively. The R101 ∩ R50 (AND model) took the least time with an average execution time of 4.6 s. Mask-RCNN models showed a good prediction rate of choroidal layer with accuracy rates of 90% and 89.9% for average choroidal thickness and average subfoveal choroidal thickness, respectively. In conclusion, the deep-learning method using the Mask-RCNN model provides a faster and accurate measurement of choroidal thickness. Comparing with manual delineation, it provides better effectiveness, which is feasible for clinical application and larger scale of research on choroid.
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 r...
A 51-year-old male who had suffered from right eye rhegmatogenous retinal detachment with proliferative vitreoretinopathy received surgical treatments which included the following procedures: lens extraction, scleral buckle, vitrectomy, membrane peeling, photocoagulation, and silicone oil injection. The presenting visual acuity of the right eye was light perception. Slit-lamp examination revealed corneal opacity without a visible fundus. B-scan ultrasonography revealed retinal detachment. Endoscope-assisted vitrectomy was then performed in December 2014. The procedure also included photocoagulation and silicone oil tamponade. Postoperative follow-up confirmed retinal attachment through B-scan ultrasonography. To assess the feasibility of a penetrating keratoplasty, an endoscopic evaluation was performed in May 2015. A temporal retinal break was noted, and photocoagulation was applied around the break as well as the peripheral retina. Endoscopy later confirmed the retinal attachment. From the present case, we concluded that endoscope-assisted vitrectomy could be an option for patients with corneal opacity indicated for vitreoretinal surgery. We report the first case of endoscope-assisted vitrectomy in the management of retinal detachment in Taiwan.