Diabetic retinopathy classification based on dense connectivity and asymmetric convolutional neural network

• Published in: Neural computing & applications Vol. 37; no. 11; pp. 7527 - 7540
• Main Authors: Cao, Juan, Chen, Jiaran, Zhang, Xinying, Peng, Yang
• Format: Journal Article
• Language: English
• Published: London Springer London 01.04.2025; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Artificial neural networks; Asymmetry; Classification; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Connectivity; Data Mining and Knowledge Discovery; Datasets; Deep learning; Design; Diabetes; Diabetic retinopathy; Image Processing and Computer Vision; Machine learning; Medical screening; Neural networks; Patients; Principal components analysis; Probability and Statistics in Computer Science; S.I.: Efficient Artificial Intelligent Algorithms for Medical Image Analysis Based on High-Performance Computing; Special Issue on Efficient Artificial Intelligent Algorithms for Medical Image Analysis Based on High-Performance Computing; Deep learning; Diabetic retinopathy; Image recognition; Dense connection
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-022-07952-5

Diabetic retinopathy (DR) is the leading cause of blindness in diabetics. The low contrast and microscopic nature of the lesions lead to a high false positive rate for automated DR screening. To address this issue, we propose a neural network named AC-DenseNet for the five-stage DR classification. In order to exploit the shallow features and enhance the feature extraction performance, dense connectivity is added to the convolution layer of AC-DenseNet. For the convolution layer to be more robust for DR detection in rotated or flipped pictures, asymmetric convolution branches are also introduced. In addition, attention mechanisms and auxiliary classifiers are incorporated into the network for the improvement of the performance of DR classification. We validate AC-DenseNet on the enhanced Kaggle dataset. The results show that AC-DenseNet can achieve 88.8% accuracy, 97.1% specificity, and 88.7% sensitivity, demonstrating that our model outperforms several state-of-the-art algorithms.