A novel DAG network based on multi-feature fusion of fundus images for multi-classification of diabetic retinopathy

被引:0
作者
Lingling Fang
Huan Qiao
机构
[1] Liaoning Normal University,Department of Computing and Information Technology
来源
Multimedia Tools and Applications | 2023年 / 82卷
关键词
Diabetic retinopathy; Multi-feature fusion; DAG network; Multi-classification;
D O I
暂无
中图分类号
学科分类号
摘要
Diabetic retinopathy is one of the most serious causes of blindness, clinically, doctors' judgment of lesion grade is time-consuming and laborious, which may lead to early misdiagnosis. Here, the features of diabetic retinopathy are of great significance to the effective diagnosis and prognosis of ophthalmologists. Accordingly, this paper proposes a novel directed acyclic graph (DAG) network for the multi-classification of diabetic retinopathy based on multi-feature fusion of fundus images. Firstly, according to the prior knowledge of doctors, different algorithms are used to extract three features of microaneurysms, neovascularization, and cotton wool spots from diabetic retinas of different grades. Then, these features are fed into the proposed novel DAG network. Besides, diabetic retinas of different grades are learned by combining the multi-feature fusion mechanism. Finally, the optimized classification model is applied to the clinical multi-classification of diabetic retina. IDRiD dataset and clinical dataset from Dalian NO.3 People's Hospital are used to evaluate the performance of the proposed method, and the accuracy can reach 98.5% and 98.6%, respectively. This method can reduce the possibility of early misdiagnosis of diabetic retinopathy, help doctors accurately identify the grade, and effectively prevent further impairment of visual function in patients.
引用
收藏
页码:47669 / 47693
页数:24
相关论文
共 50 条
[41]   Moving objects multi-classification based on information fusion [J].
Honnit, Bouchra ;
Soulam, Khaoula Belhaj ;
Said, Mohamed Nabil ;
Tamtaoui, Ahmed .
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2022, 34 (04) :1219-1230
[42]   A lightweight multi-feature fusion structure for automatic modulation classification [J].
Li, Zhigang ;
Zhang, Wentao ;
Wang, Yutong ;
Li, Shujie ;
Sun, Xiaochuan .
PHYSICAL COMMUNICATION, 2023, 61
[43]   Social media network public opinion emotion classification method based on multi-feature fusion and multi-scale hybrid neural network [J].
Yao, Yuan ;
Chen, Xi ;
Zhang, Peng .
PEERJ COMPUTER SCIENCE, 2025, 11
[44]   Modified capsule network for diabetic retinopathy detection and classification using fundus images [J].
Aswini, A. Arockia ;
Sivarani, T. S. .
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2023, 44 (04) :5521-5542
[45]   Multi-feature Fusion Flame Detection Algorithm Based on BP Neural Network [J].
Wu, Jin ;
Yang, Ling ;
Gao, Yaqiong ;
Zhang, Zhaoqi .
ADVANCES IN NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY, ICNC-FSKD 2022, 2023, 153 :395-401
[46]   A Hybrid Attention Network for Malware Detection Based on Multi-Feature Aligned and Fusion [J].
Yang, Xing ;
Yang, Denghui ;
Li, Yizhou .
ELECTRONICS, 2023, 12 (03)
[47]   MFNN: Position and Attitude Measurement Neural Network Based on Multi-Feature Fusion [J].
Man, Jiabao ;
Li, Gen ;
Xi, Meng ;
Lei, Yutian ;
Lu, Wen ;
Gao, Xinbo .
IEEE ACCESS, 2019, 7 :109495-109505
[48]   The Recognition of Cirrhotic Liver Ultrasonic Images of Multi-feature Fusion Based on BP_Adaboost Neural Network [J].
Wang, Shourun ;
Pan, Zhenkuan ;
Wei, Weibo ;
Zhao, Ximei ;
Wang, Guodong .
ADVANCES IN IMAGE AND GRAPHICS TECHNOLOGIES, IGTA 2016, 2016, 634 :106-114
[49]   Multi-feature fusion gesture recognition based on deep convolutional neural network [J].
Yun Wei-guo ;
Shi Qi-qi ;
Wang Min .
CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS, 2019, 34 (04) :417-422
[50]   Breast tumor detection using multi-feature block based neural network by fusion of CT and MRI images [J].
Kumari, Bersha ;
Nandal, Amita ;
Dhaka, Arvind .
COMPUTATIONAL INTELLIGENCE, 2024, 40 (03)