Plus Disease in Retinopathy of Prematurity: Convolutional Neural Network Performance Using a Combined Neural Network and Feature Extraction Approach

• Published in: Translational vision science & technology 2020-02, Vol.9 (2), p.10-10
• Main Authors: Yildiz, Veysi M, Tian, Peng, Yildiz, Ilkay, Brown, James M, Kalpathy-Cramer, Jayashree, Dy, Jennifer, Ioannidis, Stratis, Erdogmus, Deniz, Ostmo, Susan, Kim, Sang Jin, Chan, R V Paul, Campbell, J Peter, Chiang, Michael F
• Format: Article
• Language: English
• Subjects: Area Under Curve; Child; Humans; Infant, Newborn; Neural Networks, Computer; Ophthalmoscopy; Retinal Vessels - diagnostic imaging; Retinopathy of Prematurity - diagnosis; Special Issue
• ISSN: 2164-2591; 2164-2591
• DOI: 10.1167/tvst.9.2.10

Retinopathy of prematurity (ROP), a leading cause of childhood blindness, is diagnosed by clinical ophthalmoscopic examinations or reading retinal images. Plus disease, defined as abnormal tortuosity and dilation of the posterior retinal blood vessels, is the most important feature to determine treatment-requiring ROP. We aimed to create a complete, publicly available and feature-extraction-based pipeline, I-ROP ASSIST, that achieves convolutional neural network (CNN)-like performance when diagnosing plus disease from retinal images. We developed two datasets containing 100 and 5512 posterior retinal images, respectively. After segmenting retinal vessels, we detected the vessel centerlines. Then, we extracted features relevant to ROP, including tortuosity and dilation measures, and used these features in the classifiers including logistic regression, support vector machine and neural networks to assess a severity score for the input. We tested our system with fivefold cross-validation and calculated the area under the curve (AUC) metric for each classifier and dataset. For predicting plus versus not-plus categories, we achieved 99% and 94% AUC on the first and second datasets, respectively. For predicting pre-plus or worse versus normal categories, we achieved 99% and 88% AUC on the first and second datasets, respectively. The CNN method achieved 98% and 94% for predicting two categories on the second dataset. Our system combining automatic retinal vessel segmentation, tracing, feature extraction and classification is able to diagnose plus disease in ROP with CNN-like performance. The high performance of I-ROP ASSIST suggests potential applications in automated and objective diagnosis of plus disease.