🤖 AI Summary
This study addresses the scarcity of specialists and diagnostic subjectivity in screening for Plus disease associated with retinopathy of prematurity (ROP) in low-resource settings by systematically evaluating the complementary roles of image classification and retinal vessel segmentation in a Kenyan preterm infant cohort. We developed and compared multiple AI pipelines—including RGB-based classifiers, multiple instance learning, multitask joint models, and a segmentation-followed-by-classification pipeline—using patient-stratified nested cross-validation. The proposed probabilistic ensemble model achieved the best balanced performance at the eye level, with a sensitivity of 0.692, specificity of 0.914, and balanced accuracy of 0.803, significantly outperforming single-task classifiers. Additionally, vessel segmentation yielded a Dice coefficient of 0.533 and a high specificity of 0.979, effectively reducing unnecessary referrals.
📝 Abstract
Background. Retinopathy of prematurity (ROP) is a preventable cause of childhood blindness, with rising burden in low- and middle-income countries where ROP-trained ophthalmologists are scarce. Plus disease, marked by retinal vessel dilation and tortuosity, triggers treatment but is subjective and variable. Automated screening could extend specialist reach, but African evidence remains limited.
Methods. We analysed 121 Kenyan preterm infants, covering 237 eyes and 1,635 fundus images graded as No Plus, Pre-Plus or Plus. Vessel annotations from two graders supported segmentation training. Eleven configurations were evaluated for eye-level Plus detection using patient-grouped nested cross-validation, including image classifiers, multiple-instance learning, multi-task segmentation-classification, and segment-then-classify pipelines.
Results. Vessel segmentation was feasible, achieving pooled Dice 0.533, IoU 0.368, sensitivity 0.623 and specificity 0.979 on held-out images. RGB classifiers were highly sensitive but over-referred, while segmentation-coupled models were more specific. Combining approaches improved performance: an OR-based screen achieved the highest sensitivity, an AND-based confirmation achieved the highest specificity, and a probability ensemble gave the best balanced performance, with sensitivity 0.692, specificity 0.914 and balanced accuracy 0.803, outperforming the vision classifier alone.
Conclusions. Classification and vessel segmentation are complementary for ROP Plus detection in Kenyan data. Classifiers support sensitive case-finding, while segmentation improves specificity and reduces over-referral. African ROP AI systems should use combined workflows and undergo prospective multi-site validation.