For years, branch retinal vein occlusion is still a controversial disease in many aspects. An increasing amount of data is available regarding classification, pathogenesis, risk factors, natural history, and therapy of branch retinal vein occlusion. Some of the conclusions may even change our impression of branch retinal vein occlusion. It will be beneficial for our doctors to get a deeper understanding of this disease and improve the treatment skills. The aims of this review is to collect the information above and report new ideas especially from the past a few years.
Lesion detection is a critical component of disease diagnosis, but the manual segmentation of lesions in medical images is time-consuming and experience-demanding. These issues have recently been addressed through deep learning models. However, most of the existing algorithms were developed using supervised training, which requires time-intensive manual labeling and prevents the model from detecting unaware lesions. As such, this study proposes a weakly supervised learning network based on CycleGAN for lesions segmentation in full-width optical coherence tomography (OCT) images. The model was trained to reconstruct underlying normal anatomic structures from abnormal input images, then the lesions can be detected by calculating the difference between the input and output images. A customized network architecture and a multi-scale similarity perceptual reconstruction loss were used to extend the CycleGAN model to transfer between objects exhibiting shape deformations. The proposed technique was validated using an open-source retinal OCT image dataset. Image-level anomaly detection and pixel-level lesion detection results were assessed using area-under-curve (AUC) and the Dice similarity coefficient, producing results of 96.94% and 0.8239, respectively, higher than all comparative methods. The average test time required to generate a single full-width image was 0.039 s, which is shorter than that reported in recent studies. These results indicate that our model can accurately detect and segment retinopathy lesions in real-time, without the need for supervised labeling. And we hope this method will be helpful to accelerate the clinical diagnosis process and reduce the misdiagnosis rate.
Purpose
The purpose of this study was to design an automated algorithm that can detect fluorescence leakage accurately and quickly without the use of a large amount of labeled data.
Methods
A weakly supervised learning-based method was proposed to detect fluorescein leakage without the need for manual annotation of leakage areas. To enhance the representation of the network, a residual attention module (RAM) was designed as the core component of the proposed generator. Moreover, class activation maps (CAMs) were used to define a novel anomaly mask loss to facilitate more accurate learning of leakage areas. In addition, sensitivity, specificity, accuracy, area under the curve (AUC), and dice coefficient (DC) were used to evaluate the performance of the methods.
Results
The proposed method reached a sensitivity of 0.73 ± 0.04, a specificity of 0.97 ± 0.03, an accuracy of 0.95 ± 0.05, an AUC of 0.86 ± 0.04, and a DC of 0.87 ± 0.01 on the HRA data set; a sensitivity of 0.91 ± 0.02, a specificity of 0.97 ± 0.02, an accuracy of 0.96 ± 0.03, an AUC of 0.94 ± 0.02, and a DC of 0.85 ± 0.03 on Zhao's publicly available data set; and a sensitivity of 0.71 ± 0.04, a specificity of 0.99 ± 0.06, an accuracy of 0.87 ± 0.06, an AUC of 0.85 ± 0.02, and a DC of 0.78 ± 0.04 on Rabbani's publicly available data set.
Conclusions
The experimental results showed that the proposed method achieves better performance on fluorescence leakage detection and can detect one image within 1 second and thus has great potential value for clinical diagnosis and treatment of retina-related diseases, such as diabetic retinopathy and malarial retinopathy.
Translational Relevance
The proposed weakly supervised learning-based method that automates the detection of fluorescence leakage can facilitate the assessment of retinal-related diseases.
Purpose:
To describe a novel technique for capsular bag reopening and secondary in-the-bag intraocular lens (IOL) implantation in aphakic eyes after vitreoretinal surgery and intraocular tamponade.
Methods:
We enrolled 14 eyes of 14 patients who underwent primary vitreoretinal surgery with silicone oil tamponade for rhegmatogenous retinal detachment between September 2018 and September 2019. The novel technique was used for capsular bag reopening and foldable single-piece IOL implantation. Patients were followed up at least 24 weeks with routine ophthalmic examinations, corneal endothelial cell density, and IOL tilt and decentration measurement.
Results:
The procedure was successfully completed in 13 cases; in one case, because of posterior capsular tear, the IOL was implanted with ciliary sulcus fixation. After a mean follow-up of 48.8 ± 14.8 (range, 24.9–65.9) weeks, the best-corrected visual acuity (before 20/76 Snellen, 0.63 ± 0.23 logarithm of the minimum angle of resolution equivalent and after 20/35 Snellen, 0.32 ± 0.32 logarithm of the minimum angle of resolution equivalent; P = 0.001) and spherical equivalent (before +8.22 ± 4.08, after −2.39 ± 1.77 D; P < 0.001) improved, intraocular pressure (before 15.93 ± 4.40, after 16.25 ± 4.25 mmHg; P = 0.743) remained unchanged. The IOL was well centered with a mean horizontal and vertical tilt of 0.5070 ± 0.3319° and 0.4652 ± 0.3465°, respectively, and decentration of 0.1705 ± 0.1334 mm and 0.1712 ± 0.1576 mm, respectively.
Conclusion:
With this technique, capsular bag reopening and secondary in-the-bag IOL implantation could be achieved in most cases with satisfactory visual outcome and IOL position.
Caveolin-1(Cav-1) is involved in lipid metabolism and energy homeostasis, which is important for the energetically demanding retina. Although retinal function deficits were noted in Cav-1 knockout (Cav-1 -/-) mice, the underlying causes remain largely unknown. Here, we investigate if the disruption in energy homeostasis presents a potential mechanism for retinal function deficits in Cav-1 -/retina and if it can be ameliorated by nicotinamide (NAM). In this study, NAM was administrated orally for 2 weeks in Cav-1 -/mice before experiments. Oxidative lipidomics was conducted to detect the oxylipin changes, the retinal energy flux was measured by seahorse assay, and the retinal function was assessed by electroretinogram (ERG). Cav-1 deficiency induced the dysregulation of oxidative lipidomics and reduction in energy consumption/production in the retina by decreasing Na + /K + -ATPase, oxidative phosphorylation CII, cytochrome c, and oxygen consumption rate (OCR). A decrease in Sirt1 was also detected. Therapeutic administration of NAM significantly increased Sirt1 expression and improved energy deficiency by increasing Na + /K + -ATPase, cytochrome c, and OCR. The dysregulation of oxidative lipidomics was partially recovered, and the retinal function was improved as assessed by ERG compared to Cav-1 -/mice. Our study demonstrated the dysregulation of oxidative lipidomics in Cav-1 -/retina and established a link between energy deficiency and retinal function deficits in Cav-1 -/mice. Administration of NAM ameliorated energy deficiency, increased the expression of Sirt1, and improved retinal function, which presents a potential therapeutic strategy for Cav-1 deficiency-induced retinal function deficits.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.