Artificial intelligence in uveitis: A comprehensive review.

Uveitis is a disease complex characterized by intraocular inflammation of the uvea that is an important cause of blindness and social morbidity. With the dawn of artificial intelligence (AI) and machine learning integration in health care, their application in uveitis creates an avenue to improve screening and diagnosis. Our review identified the use of artificial intelligence in studies of uveitis and classified them as diagnosis support, finding detection, screening, and standardization of uveitis nomenclature. The overall performance of models is poor, with limited datasets and a lack of validation studies and publicly available data and codes. We conclude that AI holds great promise to assist with the diagnosis and detection of ocular findings of uveitis, but further studies and large representative datasets are needed to guarantee generalizability and fairness.

Repeatability and Reproducibility of Photoreceptor Density Measurement in the Macula Using the Spectralis High Magnification Module.

PURPOSE: To evaluate the repeatability and reproducibility of photoreceptor density assessment with manual cell counting in healthy participants imaged with the Heidelberg Spectralis High Magnification Module (HMM). DESIGN: Precision study, evaluation of diagnostic test or technology. PARTICIPANTS: Eleven eyes of 8 participants. METHODS: Images were acquired using the Spectralis HMM by a single operator during 2 separate imaging sessions. The 3 highest-quality images of each eye from each session were selected for analysis and coregistered. For a subset of participants, a second operator acquired images in 1 session, and images with the best quality were selected for analysis. Photoreceptor densities were obtained by manual counts in squares of 0.0625 mm2 located in the parafovea. Repeatability (intragrader and intrasession) and reproducibility (interoperator, intergrader, and intersession) were assessed by calculating the intraclass correlation coefficient (ICC) from linear mixed effects models. Bland-Altman plots, coefficients of repeatability, and Pearson correlation results were reported. MAIN OUTCOME MEASURES: Intragrader, intrasession, intersession, interoperator, and intergrader ICC estimates and their 95% confidence intervals for photoreceptor density measurements in the parafovea. RESULTS: Twenty-four eyes of 13 healthy participants were imaged initially. Of these, 11 eyes (45.83%) of 8 participants that had at least 3 acceptable images in each session were included in this study. Mean parafoveal photoreceptor density was 14 988 cells/mm2 (standard deviation, 1403.15 cells/mm2). Intragrader ICC was 0.84 (95% confidence interval, 0.57-0.95), intrasession ICC was 0.69 (95% confidence interval, 0.17-0.86), intersession ICC was 0.88 (95% confidence interval, 0.53-0.96), interoperator ICC was 0.70 (95% confidence interval, 0-0.95), and intergrader ICC was 0.22 (95% confidence interval, 0-0.71). CONCLUSIONS: Images obtained with the HMM allow for photoreceptor mosaic visualization in the macular area, mainly in the parafovea. Although densities obtained are in accordance with other reported methods in the literature, variability within and between images of the apparent cell mosaic were observed, and this study did not demonstrate high repeatability or reproducibility for quantitative assessments using the manual counting method.

Choroidal Neovascularization Analyzed on Ultrahigh-Speed Swept-Source Optical Coherence Tomography Angiography Compared to Spectral-Domain Optical Coherence Tomography Angiography.

PURPOSE: To compare visualization of choroidal neovascularization (CNV) secondary to age-related macular degeneration (AMD) using an ultrahigh-speed swept-source (SS) optical coherence tomography angiography (OCTA) prototype vs a spectral-domain (SD) OCTA device. DESIGN: Comparative analysis of diagnostic instruments. METHODS: Patients were prospectively recruited to be imaged on SD OCT and SS OCT devices on the same day. The SD OCT device employed is the RTVue Avanti (Optovue, Inc, Fremont, California, USA), which operates at ∼840 nm wavelength and 70 000 A-scans/second. The SS OCT device used is an ultrahigh-speed long-wavelength prototype that operates at ∼1050 nm wavelength and 400 000 A-scans/second. Two observers independently measured the CNV area on OCTA en face images from the 2 devices. The nonparametric Wilcoxon signed rank test was used to compare area measurements and P values of <.05 were considered statistically significant. RESULTS: Fourteen eyes from 13 patients were enrolled. The CNV in 11 eyes (78.6%) were classified as type 1, 2 eyes (14.3%) as type 2, and 1 eye (7.1%) as mixed type. Total CNV area measured using SS OCT and SD OCT 3 mm × 3 mm OCTA were 0.949 ± 1.168 mm(2) and 0.340 ± 0.301 mm(2), respectively (P = .001). For the 6 mm × 6 mm OCTA the total CNV area using SS OCT and SD OCT were 1.218 ± 1.284 mm(2) and 0.604 ± 0.597 mm(2), respectively (P = .0019). The field of view did not significantly affect the measured CNV area (P = .19 and P = .18 for SS OCT and SD OCT, respectively). CONCLUSION: SS OCTA yielded significantly larger CNV areas than SD OCTA. It is possible that SS OCTA is better able to demarcate the full extent of CNV vasculature.

Immunofluorescence confocal microscopy of porcine corneas following collagen cross-linking treatment with riboflavin and ultraviolet A.

PURPOSE: To assess ultrastructural stromal modifications in porcine corneas after riboflavin and ultraviolet A (UVA) exposure using immunofluorescence confocal imaging. METHODS: Twenty-five freshly enucleated porcine eyes were enrolled in the study. Five eyes served as control (group I). Twenty eyes had their epithelium removed (groups I, II, IV, and V) and five eyes had their epithelium intact (group III). Groups II and III were cross-linked with riboflavin 0.1% solution (10 mg riboflavin-5-phosphate in 10 mL 20% dextran-T-500) and exposed to UVA (365 nm, 3 mW/cm2) for 30 minutes. Group IV included five eyes soaked with riboflavin without posterior irradiation, and group V included five eyes irradiated, without previous exposure to riboflavin. Ultra-thin sections (8 microm) of the corneas were stained with anti-collagen I and DAPI and their fluorescence was revealed under confocal microscopy. RESULTS: Only the cross-linked corneas (group II) showed a pronounced, highly organized anterior fluorescence zone of 182.5 +/- 22.5 microm. Using DAPI staining, an anterior and concentrated displacement of cell nuclei due to collagen compaction was observed after crosslinking (group II). No structural changes were observed in all other groups. CONCLUSIONS: The cross-linking treatment effect can be directly visualized using confocal fluorescence imaging, allowing for a quantitative analysis. Cross-linked corneas showed a pronounced and limited anterior zone of organized collagen fibers, which was not observed in the other groups. Treatment of the cornea with riboflavin and UVA without previous deepithelialization did not induce any cross-linking effect. Consequently, to facilitate diffusion of riboflavin throughout the corneal stroma, the epithelium should be removed as an important initial step in the treatment.