Assessing retinal vein occlusion based on color fundus photographs using neural understanding network (NUN)

Abstract

Objective To develop and validate a novel deep learning architecture to classify retinal vein occlusion (RVO) on color fundus photographs (CFPs) and reveal the image features contributing to the classification. Methods The neural understanding network (NUN) is formed by two components: (1) convolutional neural network (CNN)‐based feature extraction and (2) graph neural networks (GNN)‐based feature understanding. The CNN‐based image features were transformed into a graph representation to encode and visualize long‐range feature interactions to identify the image regions that significantly contributed to the classification decision. A total of 7062 CFPs were classified into three categories: (1) no vein occlusion (“normal”), (2) central RVO, and (3) branch RVO. The area under the receiver operative characteristic (ROC) curve (AUC) was used as the metric to assess the performance of the trained classification models. Results The AUC, accuracy, sensitivity, and specificity for NUN to classify CFPs as normal, central occlusion, or branch occlusion were 0.975 (± 0.003), 0.911 (± 0.007), 0.983 (± 0.010), and 0.803 (± 0.005), respectively, which outperformed available classical CNN models. Conclusion The NUN architecture can provide a better classification performance and a straightforward visualization of the results compared to CNNs.

Classification of Color Fundus Photographs Using Fusion Extracted Features and Customized CNN Models

“…The presented method was benchmarked against related works in the field, and the results are presented in Table 7 [23][24][25][26][27][28][29][30][31]. The most recent study by [23] utilized a Hybrid CNN-RNN with Artificial Humming Bird Optimization, achieving an accuracy of 97.4% on binary classification.…”