Search

Automatic detection of the referable Diabetic Retinopathy (RDR) has become essential in diabetic patients, especially who live in the remote regions, to avoid a serious visual impairment. For this reason, different approaches have been developed with the aim of detect and segment the principal DR lesions for automatic diagnosis of the RDR. Exudate is one of the DR lesions and if these lesions appear in the macular region, a diabetic macular edema (DME) can be suspected and a detailed analysis by ophthalmologist is required. Then it is important to detect these lesions with their position related to the macular region to determine the danger level. This paper presents an automatic method to localize the exudates and optic disc (OD) using Single Shot Detector (SSD) scheme based on MobileNet-V1 as base network to determine if the risk of DME exits to indicate patients the necessity of consultation by ophthalmologist. The proposed system is evaluated using MESSIDOR Database, providing 89.15% accuracy, 88.17% sensitivity and 91.67% specificity.

Uveal melanoma (UM) and conjunctival melanoma (CM) are distinct entities with different etiologies and genetic background. We present a case of an atypical subconjunctival melanoma arising from a blue nevus.A 61-year-old female presented with a partially melanocytic epibulbar mass with surrounding episcleral pigmented spots. The lesion was detached from the overlying conjunctiva without an intraocular component. Excisional biopsy revealed a predominantly epithelioid melanoma, that was suggested to be metastasic, although there was no evidence of a primary melanoma elsewhere.Molecular analysis identified GNAQ and BAP1 pathogenic variants, which strongly suggested the diagnosis as a primary epibulbar melanoma arising from episcleral blue nevus.This case demonstrates the value of tumor molecular analysis using Next Generation Sequencing (NGS) for differentiating the origin of an unusually located ocular melanoma.

To provide a diagnostic algorithm of recurrence and treatment failure after intravitreal bevacizumab (IVB) injection for retinopathy of prematurity type 1 (ROP1) and the stepwise therapeutic approach for both conditions. Retrospective chart review of all patients diagnosed with ROP1 initially treated with IVB in 6 tertiary referral centers of Toluca and Mexico City from 2005 to 2017. Treatment failure was defined as persistence or progression of neovascularization, elevation of the ridge, worsening of plus disease, or retinal crunch within the first week after treatment. Recurrence was defined as the new appearance of plus disease, an elevated ridge, or pathological new vessels after an initial regression of ROP following treatment. Therapy was observation, switch of anti-VEGF agent, retinal photocoagulation, vitrectomy, or a combination of two or more, depending on the severity of findings. A total of 672 patients who received intravitreal bevacizumab injection for ROP1 treatment were included. Of these, 2.5% (17 patients) failed to treatment, 6.8% (46 patients) developed a recurrence for ROP, and 5.5% (37 patients) carried a misdiagnosis of recurrence and were diagnosed with other than ROP1 after examination. Based on the severity of findings, patients with recurrence or treatment failure were further treated by observation, repeat anti-VEGF intravitreal injection (bevacizumab or other), laser photocoagulation, vitrectomy, or a combination of these. Based on the treatment results, a therapeutic algorithm was created. Intravitreal injection of anti-VEGFs for the treatment of ROP warrants close follow-up as some of these patients may have treatment failure or recurrence of the disease. It is crucial to differentiate between them to avoid a misdiagnosis and offer the correct treatment. We propose a novel algorithm for the follow-up and treatment approach of ROP1 following initial treatment with IVB. This algorithm offers a summary of our recommendations based on a large case series of ROP1 patients. It is meant to grow and expand as more clinical evidence becomes available.

To describe fundus autofluorescence (FAF) patterns in premature infants and to determine whether FAF increases gradually with increasing post-gestational age. This was a cross-sectional, observational and descriptive case series. FAF images were obtained from patients screened for Retinopathy of Prematurity. The presence of the following hypo-autofluorescence areas/structures was graded and ranked: macular pigment (foveal centre), optic nerve head, peripapillary vessels/vascular arcade (PP/VA), and equatorial vessels (EqV). Ranks were attributed to the number of structures visualized from the posterior pole towards the periphery. The rank of FAF could then be analysed by Spearman’s correlation against age. Additionally, patients were divided by age into group 1 ( 40 WCGA). Differences between groups were tested with the Mann–Whitney U test. Thirteen patients were analysed. The mean WCGA at examination was 47.85 weeks. Spearman’s correlation showed a strong positive correlation (r = 0.714) (P = 0.006) of FAF and WCGA. The Mann–Whitney U test revealed that the PP/VA and EqV were significantly more visible at > 40 WCGA than at

Diabetic Retinopathy (DR) is one of the biggest eye diseases affecting the worldwide population. The DR presents several damages in the retina depending on its grade of advance, although the damages are asymptomatic in almost all cases. The presence of neovascularization (NV) is considered as the worse stage in the DR, and the patients of this stage require urgent treatment to avoid partial or total blindness. Timely detection of the new vessels in the retina can lead to an adequate treatment to avoid vision loss. In this work, we present automatic detection of neovascularization in the optic disc region (NVD) using a deep learning algorithm. We evaluate several deep neural networks (DNNs) to classify between health optic disc region and NVD. The better DNNs are DenseNet-161 and Efficientnet-B7, which show 93.3% and 92.0% accuracy and 89.5% and 84.2% in sensitivity, respectively. In the computational complexity, DenseNet-161 has a lower number of trainable parameters than that of Efficientnet-B7. To train the DNNs appropriately, we construct a labeled dataset from one of the largest public datasets, bounding NV regions in the retinal images.

This paper proposes a teleophthalmology support system in which we use algorithms of object detection and semantic segmentation, such as faster region-based CNN (FR-CNN) and SegNet, based on several CNN architectures such as: Vgg16, MobileNet, AlexNet, etc. These are used to segment and analyze the principal anatomical elements, such as optic disc (OD), region of interest (ROI) composed by the macular region, real retinal region, and vessels. Unlike the conventional retinal image quality assessment system, the proposed system provides some possible reasons about the low-quality image to support the operator of an ophthalmoscope and patient to acquire and transmit a better-quality image to central eye hospital for its diagnosis. The proposed system consists of four steps: OD detection, OD quality analysis, obstruction detection of the region of interest (ROI), and vessel segmentation. For the OD detection, artefacts and vessel segmentation, the FR-CNN and SegNet are used, while for the OD quality analysis, we use transfer learning. The proposed system provides accuracies of 0.93 for the OD detection, 0.86 for OD image quality, 1.0 for artefact detection, and 0.98 for vessel segmentation. As the global performance metric, the kappa-based agreement score between ophthalmologist and the proposed system is calculated, which is higher than the score between ophthalmologist and general practitioner.

Purpose We describe the functioning of a novel device, aimed to assess patient head position after a pneumatic retinopexy. Methods We enrolled patients with the clinical diagnosis of rhegmatogenous retinal detachment. All patients were asked to wear a specially designed headband with a monitoring device composed of an accelerometer, gyroscope, and magnetometer, powered by a 3.7V lithium battery. Every 200 ms, the device measured neck flexion and extension, left and right rotation, and left and right flexion. Patients were asked to come back the next morning for follow-up and headband retrieving. Results The device was worn an average of 19.17 ± 2.1 hours and performed a mean number of 57,670 ± 8663 measurements without power failures or program errors. An acceptable head position was kept for a mean of 3.33 ± 1.8 hours. The hardest axis to maintain was the right and left flexion of the neck (5.5 ± 2.54 hours of acceptable positioning). Conclusion Real-time monitoring of patient head position after a vitreoretinal procedure is feasible. Maintaining a fixed head position for more than 5 consecutive hours is difficult to achieve and physicians should consider this difficulty when planning treatment. Translational relevance In addition to a significant improvement to the basic design of similar devices, our device allows for assessment of patient adherence to postoperative instructions objectively for the first time to our knowledge. This information could be used in the future to elaborate more detailed position nomograms to improve outcomes.