[Artificial intelligence and glaucoma: A literature review]. / Intelligence artificielle et glaucome : une revue de la littérature.

In recent years, research in artificial intelligence (AI) has experienced an unprecedented surge in the field of ophthalmology, in particular glaucoma. The diagnosis and follow-up of glaucoma is complex and relies on a body of clinical evidence and ancillary tests. This large amount of information from structural and functional testing of the optic nerve and macula makes glaucoma a particularly appropriate field for the application of AI. In this paper, we will review work using AI in the field of glaucoma, whether for screening, diagnosis or detection of progression. Many AI strategies have shown promising results for glaucoma detection using fundus photography, optical coherence tomography, or automated perimetry. The combination of these imaging modalities increases the performance of AI algorithms, with results comparable to those of humans. We will discuss potential applications as well as obstacles and limitations to the deployment and validation of such models. While there is no doubt that AI has the potential to revolutionize glaucoma management and screening, research in the coming years will need to address unavoidable questions regarding the clinical significance of such results and the explicability of the predictions.

Evaluation of pterygium severity with en face anterior segment optical coherence tomography and correlations with in vivo confocal microscopy.

PURPOSE: To describe en face anterior segment optical coherence tomography (EF-OCT) characteristics of pterygia and their correlation with in vivo confocal microscopy (IVCM). PATIENTS AND METHODS: In this observational case series, we prospectively included 21 eyes of 17 subjects with pterygium. All subjects underwent detailed ophthalmic examination, anterior segment photography, an ocular surface disease index (OSDI) questionnaire, IVCM, and EF-OCT. Eyes were divided into two groups according to pterygium severity (Modified Pterygium Classification System) and OSDI score. EF-OCT images for both groups were analyzed for surface area of Fuchs Patches (FP). The IVCM activity score was based on the number of inflammatory cells, blood vessels, activated keratocytes and the appearance of the cornea/pterygium at the head of the pterygium. The correlations between EF-OCT and IVCM images were then analyzed and compared in both groups. RESULTS: EF-OCT permits clear visualization and evaluation of FPs and the border between the pterygium and the adjacent cornea. The severe pterygium group was characterized by irregular borders and larger FPs (0.13±0.06 mm2 versus 0.06±0.02 mm2 respectively) (P=0.003). The mean IVCM activity score was 2.36±0.81 in the severe pterygium group and 1.2±0.42 in the mild pterygium group (P=0.0013). There was a positive correlation between FP surface area and IVCM activity score. A larger FP surface area was associated with a higher activity score on IVCM. CONCLUSION: EF-OCT allows good evaluation of pterygium extension, borders and FP surface area. EF-OCT analysis of pterygium could represent a simple, non-invasive and reproducible method to evaluate pterygium severity and activity.