Artificial intelligence-based grading of human cataracts: A feasibility study.

Abstract

This feasibility study developed and validated an AI algorithm for automatic classification of human lens opacification (cataracts) using anterior segment optical coherence tomography (OCT). The dataset comprised 1,802 unprocessed OCT images from 901 eyes, with cataract severity graded by slit-lamp examination using the Lens Opacities Classification System (LOCS) III. Nuclear opalescence (NO) was stratified as mild (≤3.0), moderate (3.5-4.0), or severe (≥4.5), while posterior subcapsular cataract (PSC) was classified as mild (<4) or severe (≥4). Nuclear color (NC) and cortical cataract (C) were not evaluated. After balancing, images were randomly divided into three sets: 70% for training, 20% for testing and 10% for validation. A convolutional neural network was trained five times. Patients had a mean age of 72 ± 8.8 years, with mean LOCS III grades of 3.81 ± 0.79 (NO) and 1.74 ± 1.55 (PSC). The AI achieved 60.3% accuracy for NO classification; among misclassifications, 34.9% were within one category, 4.8% were grossly inaccurate. PSC classification performed with 86.4% accuracy, yielding a true positive rate of 81.8% and a true negative rate of 90.9%. These results demonstrate the potential of deep learning for automated cataract grading.