■ A team of scientists from IBM Research and New York University are looking at new ways to use artificial intelligence (AI) to help ophthalmologists further utilize eye images, and potentially help to speed the process for detecting glaucoma in diagnostic images. The research team has developed a new deep-learning framework that detects glaucoma directly from raw OCT imaging.

Ultimately, when normalized by a false-positive rate, in a cohort of 624 subjects (217 healthy and 432 glaucoma patients) the new approach, founded in deep learning, correctly detects glaucoma eyes in 94% of cases, while previously used techniques only found this in 86% of cases. The team believes this improved accuracy is a result of eliminating errors in the automated segmentation of structures in images, as well as the inclusion of regions of the image not currently utilized clinically for this purpose.