Background: The aim of this study was to develop an intelligent system based on a deep learning algorithm for automatically diagnosing fungal keratitis (FK) in in vivo confocal microscopy (IVCM) images.Methods: A total of 2,088 IVCM images were included in the training dataset. The positive group consisted of 688 images with fungal hyphae, and the negative group included 1,400 images without fungal hyphae. A total of 535 images in the testing dataset were not included in the training dataset. Deep Residual Learning for Image Recognition (ResNet) was used to build the intelligent system for diagnosing FK automatically. The system was verified by external validation in the testing dataset using the area under the receiver operating characteristic curve (AUC), accuracy, specificity and sensitivity.Results: In the testing dataset, 515 images were diagnosed correctly and 20 were misdiagnosed (including 6 with fungal hyphae and 14 without). The system achieved an AUC of 0.9875 with an accuracy of 0.9626 in detecting fungal hyphae. The sensitivity of the system was 0.9186, with a specificity of 0.9834. When 349 diabetic patients were included in the training dataset, 501 images were diagnosed correctly and thirtyfour were misdiagnosed (including 4 with fungal hyphae and 30 without). The AUC of the system was 0.9769.The accuracy, specificity and sensitivity were 0.9364, 0.9889 and 0.8256, respectively. Conclusions:The intelligent system based on a deep learning algorithm exhibited satisfactory diagnostic performance and effectively classified FK in various IVCM images. The context of this deep learning automated diagnostic system can be extended to other types of keratitis.

Background To evaluate the subfoveal choroidal thickness (SFCT) in eyes with macular edema (ME) secondary to retinal vein occlusion(RVO), and to investigate the short term response after a single intravitreal ranibizumab (IVR) injection. What is more, to compare SFCT and SFCT change between central RVO (CRVO) and branch RVO (BRVO). Methods In the retrospective study, we had collected 36-six treatment-naïve patients with unilateral ME secondary to RVO (including 19 CRVO and 17 BRVO). All patients had received IVR injection after newly diagnosed. The SFCT was measured at the onset and after 2 weeks of IVR injection. Paired t test was performed to compare the SFCT of RVO eyes and fellow eyes, as well as the SFCT of pre-injection and post-injection. In further, independent t test was used to compare SFCT and SFCT change between CRVO eyes and BRVO eyes. Results The mean SFCT at the onset was 326.03 ± 30.86 μm in CRVO eyes, which was significantly thicker than that in contralateral fellow eyes ( p < 0.01, paired t test), and reduced to 294.15 ± 30.83 μm rapidly after 2 weeks of IVR injection ( p < 0.01, paired t test). Similarly, the SFCT in BRVO eyes was significantly thicker than that in contralateral eyes at the onset, and decreased significantly after IVR injection. However, our findings showed that there was no statistically significant difference in SFCT and SFCT reduction after IVR injection between CRVO eyes and BRVO eyes. Conclusions The SFCT in eyes with ME secondary to CRVO and BRVO was significantly thicker than that in fellow eyes, and decreased significantly within a short time in response to a single IVR injection. In further, the study showed that SFCT and SFCT change had no correlation with RVO subtypes.

Backgroud: To evaluate the subfoveal choroidal thickness (SFCT) in eyes with macular edema (ME) secondary to retinal vein occlusion（RVO），and to investigate the short term response after a single intravitreal ranibizumab (IVR) injection. What is more, to compare SFCT and SFCT change between central RVO (CRVO) and branch RVO (BRVO). Methods: In the retrospective study, we had collected thirty-six treatment-naïve patients with unilateral ME secondary to RVO (including nineteen CRVO and seventeen BRVO). All patients had received IVR injection after newly diagnosed. The SFCT was measured at the onset and after two weeks of IVR injection. Paired t test was performed to compare the SFCT of RVO eyes and fellow eyes, as well as the SFCT of pre-injection and post-injection. In further, independent t test was used to compare SFCT and SFCT change between CRVO eyes and BRVO eyes. Results: The mean SFCT at the onset was 326.03±30.86 μm in CRVO eyes, which was significantly thicker than that in contralateral fellow eyes (p<0.01, paired t test), and reduced to 294.15±30.83 μm rapidly after two weeks of IVR injection (p<0.01, paired t test). Similarly, the SFCT in BRVO eyes was significantly thicker than that in contralateral eyes at the onset, and decreased significantly after IVR injection. However, our findings showed that there was no statistically significant difference in SFCT and SFCT reduction after IVR injection between CRVO eyes and BRVO eyes. Conclusions: The SFCT in eyes with ME secondary to CRVO and BRVO was significantly thicker than that in fellow eyes, and decreased significantly within a short time in response to a single IVR injection. In further, the study showed that SFCT and SFCT change had no correlation with RVO subtypes.

BackgroundAge-related macular degeneration (AMD) causes the dysfunction of the retinal pigment epithelial (RPE) cells. In this study, we examined the effects of riluzole, a sustained activator of the TRAAK potassium channel, on human RPE (ARPE-19) cells in an oxidant-induced cell-injury model and elucidate the mechanism of riluzole on RPE cell apoptosis.MethodsThe follow four groups of ARPE-19 cells were treated with riluzole and/or tert-butyl hydroperoxide (t-BHP) for 24.0 h: control, t-BHP, riluzole, and t-BHP + riluzole. Cell apoptosis was measured by flow cytometry, and Western blotting was performed to analyze the expression of the weakly inward rectifying potassium (TRAAK) channel. Finally, the mitochondrial membrane potential (Δψm) was detected by flow cytometry, and cytochrome C (Cyt-c) release was assessed by Western blotting.ResultsThe viability of the cells in the cotreated group was significantly higher (85.6 ± 3.1%) than that in the t-BHP group (66.2 ± 2.5%). In addition, the cells in the cotreated group had a higher effect on increasing the expression of TRAAK than the t-BHP group. The results also showed that Cyt-c translocation significantly decreased and Δψm increased in the cotreated group.ConclusionsThese results demonstrate that riluzole protects RPE cells from apoptosis. The protection mechanism of riluzole could be from stabilizing mitochondrial Δψm and preventing the release of Cyt-c. Changes in TRAAK expression might also contribute to the protection of RPE cells.