Automatic segmentation of intraocular lens, the retrolental space and Berger's space using deep learning

To develop and validate a deep learning model to automatically segment three structures using an anterior segment optical coherence tomography The intraocular lens (IOL), the retrolental space (IOL to the posterior lens capsule) and Berger's space (BS; posterior capsule to the anterior hyaloid membrane). An artificial intelligence (AI) approach based on a deep learning model to automatically segment the IOL, the retrolental space, and BS in ASOCT, was trained using annotations from an experienced clinician. The deep learning model allows for fully automatic segmentation of all investigated structures, achieving human performance in BS segmentation. The study, therefore, expects promising applications of the algorithm with a particular interest in BS in automated extensive data analysis and real-time intraoperative support in ophthalmology, particularly in conjunction with primary posterior capsulotomy in femtosecond laser-assisted cataract surgery.