Background/aims The aim of this study was to generate and evaluate individualised post-therapeutic optical coherence tomography (OCT) images that could predict the short-term response of antivascular endothelial growth factor therapy for typical neovascular age-related macular degeneration (nAMD) based on pretherapeutic images using generative adversarial network (GAN). Methods A total of 476 pairs of pretherapeutic and post-therapeutic OCT images of patients with nAMD were included in training set, while 50 pretherapeutic OCT images were included in the tests set retrospectively, and their corresponding post-therapeutic OCT images were used to evaluate the synthetic images. The pix2pixHD method was adopted for image synthesis. Three experiments were performed to evaluate the quality, authenticity and predictive power of the synthetic images by retinal specialists. Results We found that 92% of the synthetic OCT images had sufficient quality for further clinical interpretation. Only about 26%–30% synthetic post-therapeutic images could be accurately identified as synthetic images. The accuracy to predict macular status of wet or dry was 0.85 (95% CI 0.74 to 0.95). Conclusion Our results revealed a great potential of GAN to generate post-therapeutic OCT images with both good quality and high accuracy.
1 June 2022 in Translational Vision Science & Technology
Purpose: To develop deep learning models based on color fundus photographs that can automatically grade myopic maculopathy, diagnose pathologic myopia, and identify and segment myopia-related lesions. Methods: Photographs were graded and annotated by four ophthalmologists and were then divided into a high-consistency subgroup or a low-consistency subgroup according to the consistency between the results of the graders. ResNet-50 network was used to develop the classification model, and DeepLabv3+ network was used to develop the segmentation model for lesion identification. The two models were then combined to develop the classification-and-segmentation–based co-decision model. Results: This study included 1395 color fundus photographs from 895 patients. The grading accuracy of the co-decision model was 0.9370, and the quadratic-weighted κ coefficient was 0.9651; the co-decision model achieved an area under the receiver operating characteristic curve of 0.9980 in diagnosing pathologic myopia. The photograph-level F1 values of the segmentation model identifying optic disc, peripapillary atrophy, diffuse atrophy, patchy atrophy, and macular atrophy were all >0.95; the pixel-level F1 values for segmenting optic disc and peripapillary atrophy were both >0.9; the pixel-level F1 values for segmenting diffuse atrophy, patchy atrophy, and macular atrophy were all >0.8; and the photograph-level recall/sensitivity for detecting lacquer cracks was 0.9230. Conclusions: The models could accurately and automatically grade myopic maculopathy, diagnose pathologic myopia, and identify and monitor progression of the lesions. Translational Relevance: The models can potentially help with the diagnosis, screening, and follow-up for pathologic myopic in clinical practice.
4 February 2021 in Graefe's Archive for Clinical and Experimental Ophthalmology
Intraocular surgery is challenged by restricted environmental perception and difficulties in instrument depth estimation. The advent of autonomous intraocular surgery represents a milestone in medical technology, given that it can enhance surgical consistency that improves patient safety, shorten surgeon training periods so that more patients can undergo surgery, reduce dependency on human resources, and enable surgeries in remote or extreme environments. In this study, an autonomous robotic system for intraocular surgery (ARISE) was developed, achieving targeted retinal injections throughout the intraocular space. The robotic system achieves intelligent perception and macro/microprecision positioning of the instrument throughout the intraocular space through two key innovations. The first is a multiview spatial fusion that reconciles imaging feature disparities and corrects dynamic spatial misalignments. The second is a criterion-weighted fusion of multisensor data that mitigates inconsistencies in detection range, error magnitude, and sampling frequency. Subretinal and vascular injections were performed on eyeball phantoms, ex vivo porcine eyeballs, and in vivo animal eyeballs. In ex vivo porcine eyeballs, 100% success was achieved for subretinal ( n = 20), central retinal vein (CRV) ( n = 20), and branch retinal vein (BRV) ( n = 20) injections; in in vivo animal eyeballs, 100% success was achieved for subretinal ( n = 16), CRV ( n = 16), and BRV ( n = 16) injections. Compared with manual and teleoperated robotic surgeries, positioning errors were reduced by 79.87 and 54.61%, respectively. These results demonstrate the clinical feasibility of an autonomous intraocular microsurgical robot and its ability to enhance injection precision, safety, and consistency.
The relationship between vitamin A supplementation and myopia has been a topic of debate, with conflicting and inconclusive findings. We aimed to determine whether there is a causal relationship between vitamin A supplementation and the risk of myopia using Mendelian randomization (MR) and meta-analytical methods. Genetic variants from the UK Biobank and FinnGen studies associated with the response to vitamin A supplementation were employed as instrumental variables to evaluate the causal relationship between vitamin A supplementation and myopia. Fixed-effects meta-analysis was then used to combine MR estimates from multiple sources for each outcome. The meta-analysis of MR results found no convincing evidence to support a direct causal relationship between vitamin A supplementation and myopia risk (odds ratio (OR) = 0.99, 95% confidence interval (CI) = 0.82–1.20, I2 = 0%, p = 0.40). The analysis of three out of the four sets of MR analyses indicated no direction of causal effect, whereas the other set of results suggested that higher vitamin A supplementation was associated with a lower risk of myopia (OR = 0.002, 95% CI 1.17 × 10−6–3.099, p = 0.096). This comprehensive MR study and meta-analysis did not find valid evidence of a direct association between vitamin A supplementation and myopia. Vitamin A supplementation may not have an independent effect on myopia, but intraocular processes associated with vitamin A may indirectly contribute to its development.