Purpose: To evaluate the performance of deep learning (DL) in diagnosing glaucoma and predicting its progression using fundus photography and retinal optical coherence tomography (OCT) images. Materials and Methods: Relevant studies published up to 30 October 2024 were retrieved from PubMed, Medline, EMBASE, Cochrane Library, Web of Science, and ClinicalKey. A bivariate random-effects model was employed to calculate pooled sensitivity, specificity, positive and negative likelihood ratios, and area under the receiver operating characteristic curve (AUROC). Results: A total of 48 studies were included in the meta-analysis. DL algorithms demonstrated high diagnostic performance in glaucoma detection using fundus photography and OCT images. For fundus photography, the pooled sensitivity and specificity were 0.92 (95% CI: 0.89–0.94) and 0.93 (95% CI: 0.90–0.95), respectively, with an AUROC of 0.90 (95% CI: 0.88–0.92). For the OCT imaging, the pooled sensitivity and specificity were 0.90 (95% CI: 0.84–0.94) and 0.87 (95% CI: 0.81–0.91), respectively, with an AUROC of 0.86 (95% CI: 0.83–0.90). In predicting glaucoma progression, DL models generally showed less robust performance, with pooled sensitivities and specificities ranging lower than in diagnostic tasks. Internal validation datasets showed higher accuracy than external validation datasets. Conclusions: DL algorithms achieve excellent performance in diagnosing glaucoma using fundus photography and OCT imaging. To enhance the prediction of glaucoma progression, future DL models should integrate multimodal data, including functional assessments, such as visual field measurements, and undergo extensive validation in real-world clinical settings.

Purpose: To report the application of LUXIE and validate its reliability by comparing the test results with those of Humphrey Field Analyzer 3 (HFA3). Methods: In this pilot study, we prospectively recruited participants who had received HFA3 SITA standard 30-2 perimetry and tested them with LUXIE on the same day. LUXIE is a software designed for visual field testing cooperating with HTC Vive Pro Eye, a head-mounted virtual reality device with an eye-tracking system. The test stimuli were synchronized with eye movements captured by the eye-tracking system to eliminate fixation loss. The global, hemifields, quadrants, glaucoma hemifield test (GHT) sectors, and point-by-point retinal sensitivities were compared between LUXIE and HFA3. All participants were asked to fill out a post-test user survey. Results: Thirty-eight participants with 65 eyes were enrolled. LUXIE demonstrated good correlations with HFA3 in global (r = 0.81), superior hemifield (r = 0.77), superonasal, superotemporal, and inferonasal quadrants (r = 0.80, 0.78, 0.80). The user survey showed that participants were more satisfied with LUXIE in operating difficulty, comfortability, time perception, concentration, and overall satisfaction. Conclusions: LUXIE demonstrated good correlations with HFA3. Fixation loss could be eliminated in LUXIE with the eye-tracking system. The application of virtual reality devices such as the HTC Vive Pro Eye makes telemedicine and even home-based self-screening visual field tests possible. Key Messages: 1. Virtual reality perimetry is a developing technology that has the potential in telemedicine, and home self-screening visual field tests. 2. LUXIE demonstrated good correlations with Humphrey Field Analyzer 3 in visual field retinal sensitivities.

Moraxella species are Gram-negative coccobacilli that typically colonize the flora of the human upper respiratory tract and have low pathogenic potential. There are limited case reports implicating the organisms as the cause of endocarditis, bacteremia, septic arthritis, ocular infection, and meningitis. In cases of keratitis and conjunctivitis, Moraxella nonliquefaciens is not commonly isolated from the ocular surface. We present a case of a diabetic patient who developed late-onset bleb-related endophthalmitis caused by M. nonliquefaciens 4 years after glaucoma filtering surgery. Within one day, the patient presented with an acutely fulminant course with sudden visual loss, redness, and ocular pain. Appropriate antibiotic treatment and early vitrectomy resulted in a favorable final visual acuity of 20/100, which was his vision prior to infection. The use of Matrix-Assisted Laser Desorption Ionization–Time of Flight Mass spectrometry (MALDI-TOF MS) enabled the rapid identification of the organism. Endophthalmitis caused by M. nonliquefaciens should be considered in patients who underwent glaucoma filtering surgery with antifibrotic agents.