Evaluation of artificial intelligence-based quantitative analysis to identify clinically significant severe retinopathy of prematurity.

PURPOSE:To evaluate the screening potential of a deep learning algorithm-derived severity score by determining its ability to detect clinically significant severe retinopathy of prematurity (ROP). METHODS:Fundus photographs were collected, and standard panel diagnosis was generated for each examination by combining three independent image-based gradings. All images were analyzed using a deep learning algorithm, and a quantitative assessment of retinal vascular abnormality (DeepROP score) was assigned on a 1 to 100 scale. The area under the receiver operating curve and distribution pattern of all diagnostic parameters and categories of ROP were analyzed. The correlation between the DeepROP score and expert rank ordering according to overall ROP severity of 50 examinations was calculated. RESULTS:A total of 9,882 individual examinations with 54,626 images from 2,801 infants were analyzed. Fifty-six examinations (0.6%) demonstrated Type 1 ROP and 54 examinations (0.5%) demonstrated Type 2 ROP. The DeepROP score had an area under the receiver operating curve of 0.981 for detecting Type 1 ROP and 0.986 for Type 2 ROP. There was a statistically significant correlation between the expert rank ordering of overall disease severity and the DeepROP score (correlation coefficient 0.758, P < 0.001). When hypothetical referral cutoff score of 35 was selected, all cases of severe ROP (Type 1 and Type 2 ROP) was captured and 8,562 eyes (87.6%) with no or mild ROP were excluded. CONCLUSION:The DeepROP score determined by deep learning algorithm was an objective and quantitative indicator for the severity of ROP, and it had potential in automated detecting clinically significant severe ROP.