Background To identify and analyse the character and relationship between flat irregular pigment epithelial detachment feature (FIPED), choroidal thickness and choroidal neovascularisation (CNV) network seen on optical coherence tomography angiography (OCTA) in eyes with central serous chorioretinopathy (CSCR) in Chinese patients. Method In the present study, 152 eyes of 144 Chinese patients, who were previously diagnosed with CSCR, were retrospectively studied. Patients’ baseline characteristics, the course of CSCR, best-corrected visual acuity, the pattern of CNV on OCTA, FIPED and choroidal thickness detected by enhanced depth imaging-OCT (EDI-OCT) were analysed. Results It was disclosed that 7.23% of CSCR patients had CNV. Age and the course of CSCR were found to be correlated with the occurrence of CNV. Among the eyes with CNV network (11 eyes), 100% of them had FIPED, whereas, among the eyes without CNV (141 eyes), 18.04% had FIPED. The maximum width and en-face area of PED were greater in the CNV group compared with that in the non-CNV group (p<0.001). It also was revealed that female gender and a poor vision were risk factors for CNV in eyes with CSCR. The choroidal thickness detected by EDI-OCT was also statistically significant between eyes with CNV and eyes without CNV. The patients who have CNV complicated with FIPED are susceptible to have low vision. Conclusion The present research demonstrated that the majority of CNV cases were linked to FIPED, and the thinner thickness of choroid. The greater width and en-face area of PED may point towards the presence of an underlying CNV network.

Automated lesion segmentation is one of the important tasks for the quantitative assessment of retinal diseases in SD-OCT images. Recently, deep convolutional neural networks (CNN) have shown promising advancements in the field of automated image segmentation, whereas they always benefit from large-scale datasets with high-quality pixel-wise annotations. Unfortunately, obtaining accurate annotations is expensive in both human effort and finance. In this paper, we propose a weakly supervised two-stage learning architecture to detect and further segment central serous chorioretinopathy (CSC) retinal detachment with only image-level annotations. Specifically, in the first stage, a Located-CNN is designed to detect the location of lesion regions in the whole SD-OCT retinal images, and highlight the distinguishing regions. To generate available a pseudo pixel-level label, the conventional level set method is employed to refine the distinguishing regions. In the second stage, we customize the active-contour loss function in deep networks to achieve the effective segmentation of the lesion area. A challenging dataset is used to evaluate our proposed method, and the results demonstrate that the proposed method consistently outperforms some current models trained with a different level of supervision, and is even as competitive as those relying on stronger supervision. To our best knowledge, we are the first to achieve CSC segmentation in SD-OCT images using weakly supervised learning, which can greatly reduce the labeling efforts.

Purpose: To observe and analyze the clinical and multi-mode imaging features of eyes with PHOMS, and to introduce two cases of PHOMS which underwent multi-mode imaging. Methods: Retrospective clinical observational study. A total of 26 patients (37 eyes) with hyperreflective structures surrounded by hyporeflective edges around the optic discs who were examined and diagnosed at Shandong Eye Hospital between January 2019 and June 2021 were included in the study. Among these patients, 12 were male and 14 were female. Fifteen were monocular. The average age was 39 years. All patients underwent the following examinations: Best-corrected visual acuity (BCVA), intraocular pressure examinations, slit-lamp anterior segment examinations, indirect ophthalmoscopy, visual field examinations, fundus color photography, fundus autofluorescence (FAF), optical coherence tomography (OCT), and optical coherence tomography angiography (OCTA). Some of the patients were examined with fundus fluorescein angiography (FFA). Clinical data and imaging characteristics from the OCT, OCTA, and FFA were analyzed retrospectively. Results: We found the hyperreflective structures surrounded by hyporeflective edges around the optic discs in 37 eyes. EDI-OCT results revealed hyperreflective structures surrounded by hyporeflective edges around the optic discs in all eyes. Typical hyperreflexia lesions occurred around the optic disc, located subretinally and above Bruch's membrane. OCTA revealed that the highly reflective perioptic material also had vascular structures. Conclusion: EDI-OCT of PHOMS showed hyperreflective structures surrounded by hyporeflective edges around all of the optic discs. Infra-red photography showed temporal hyperreflexia. These characteristics can be seen in a variety of diseases and may be a relatively common feature revealed by EDI-OCT scanning. These characteristics may also be seen in elderly patients as well as children. PHOMS may be found in optic disc drusen (ODD), tilted disc syndrome (TDS), optic neuritis, ischemic optic neuropathy, and in white dot syndromes. Few patients may be developed into macular neovascularization (MNV). In order to improve the accuracy and robustness of the conclusions and provide better clinical guidance, we need to conduct more comprehensive research in the subsequent clinical work.

Purpose: To observe the changes in retinal and choroidal microstructures in patients with different stages of diabetic retinopathy (DR) and to evaluate the vascular perfusion of retina and choroid retinal thickness, retinal and choroidal vessel density by the swept-source optical coherence tomography angiography (SS-OCTA). Methods: Subjects were divided into three groups: healthy control group (30 cases, 51 eyes), non-proliferative diabetic retinopathy (NPDR, 42 cases, 71 eyes) and proliferative diabetic retinopathy (PDR, 31 cases, 53 eyes). The area of the foveal avascular zone (FAZ), retinal and choroidal vascular perfusion, and the deep vascular complexes, including the intermediate capillary plexus (ICP) and deep capillary plexus (DCP) within the radius of 3, 6, 9, and 12 mm around the fovea were measured by SS-OCTA. Results: Compared with the healthy control group, DR patients presented significantly increased fovea avascular area, while vessel density (VD) in the ICP and DCP, vascular perfusion rate, and the retinal thickness were considerably decreased. There were significant differences in the retinal thickness, ICP, and DCP vessel densities between the control and NPDR groups, or control and PDR groups, or PDR and NPDR groups. The deep vascular perfusion rate also significantly differed between the control and PDR groups, but there was no significant difference between the PDR and NPDR groups. The choroidal perfusion exhibited significant differences across different areas and amongst the three groups. Furthermore, the choroidal thickness showed a significant difference between the PDR and NPDR groups. Conclusion: Our results showed significant differences in the area of the avascular fovea and the VD of deep vascular complexes between DR patients and healthy control subjects. Moreover, there were significant differences in retinal VD, especially in the deep-retinalregions, choroidal perfusion, and the volume of large vessel choroid in DR patients with different degrees of disease severity. Notably, SS-OCTA provided in-depth information for detecting the potential VD damage in DR patients caused by a multitudeof factors.

Autoimmune uveitis is characterized by immune disorders of the eyes and the whole body and is often recurrent in young adults, but its pathogenesis is still unclear. IL-35 is an essential regulatory factor in many autoimmune diseases, which is produced by Breg cells and can induce Breg cells to regulate the immune response. The relationship between the expression and gene polymorphism of IL-35 and the immune status of patients with autoimmune uveitis has not been reported. The peripheral blood of the subjects was collected from patients with Behçet’s Disease (BD) and those with Vogt–Koyanagi–Harada (VKH) syndrome. The percentage of immune cell subsets including B cells, DC, and T cells, and the expression of IL-35 in serum of these two kinds of disease were analyzed. And then, the associations between seven IL-35 single nucleotide polymorphism (SNP) sites and disease susceptibility, the immune status, the clinical characteristics, and the serum IL-35 levels were analyzed. Our results showed that the percentage of Breg cells was significantly decreased in the blood of patients with VKH syndrome compared to that of healthy controls. The levels of IL-35 in the serum of patients with VKH syndrome or BD patients were not changed significantly, compared to that of healthy controls. Furthermore, the associations between two subunits of IL-35 (IL-12p35 and EBI3) and BD or VKH patients were analyzed. We found that there was an association between the EBI3 rs428253 and the occurrence of BD. There was an association between the IL-12p35 rs2243131 and the low level of Breg cell of VKH patients. In addition, there were associations between the polymorphisms of EBI3 rs4740 and the occurrence of headache and tinnitus of VKH patients, respectively. And the genotype frequency of IL-12p35 rs2243115 was related to the concentration of serum IL-35 in patients with VKH syndrome. Thus, the specific SNP sites change of IL-35 were correlated to the immune disorders in uveitis. And they may also play a guiding role in the occurrence of clinical symptoms in patients with uveitis, especially for VKH syndrome.

Purpose: To identify a reliable biomarker for screening diabetic nephropathy (DN) using artificial intelligence (AI)–assisted ultra-widefield swept-source optical coherence tomography angiography (UWF SS-OCTA). Methods: This study analyzed data from 169 patients (287 eyes) with type 2 diabetes mellitus (T2DM), resulting in 15,211 individual data points. These data points included basic demographic information, clinical data, and retinal and choroidal data obtained through UWF SS-OCTA for each eye. Statistical analysis, 10-fold cross-validation, and the random forest approach were employed for data processing. Results: The degree of retinal microvascular damage in the diabetic retinopathy (DR) with the DN group was significantly greater than in the DR without DN group, as measured by SS-OCTA parameters. There were strong associations between perfusion density (PD) and DN diagnosis in both the T2DM population (r = −0.562 to −0.481, P < 0.001) and the DR population (r = −0.397 to −0.357, P < 0.001). The random forest model showed an average classification accuracy of 85.8442% for identifying DN patients based on perfusion density in the T2DM population and 82.5739% in the DR population. Conclusions: Quantitative analysis of microvasculature reveals a correlation between DR and DN. UWF PD may serve as a significant and noninvasive biomarker for evaluating DN in patients through deep learning. AI-assisted SS-OCTA could be a rapid and reliable tool for screening DN. Translational Relevance: We aim to study the pathological processes of DR and DN and determine the correspondence between their clinical and pathological manifestations to further clarify the potential of screening DN using AI-assisted UWF PD.