Hui Wang1, Guohui Yuan2, Xuegong Zhao3, Lingbing Peng4, Zhuoran Wang5, Yanmin He6, Chao Qu7, Zhenming Peng8. 1. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China; Laboratory of Imaging Detection and Intelligent Perception, University of Electronic Science and Technology of China, Chengdu, 611731, China. Electronic address: uestc.huiwang@outlook.com. 2. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China; Laboratory of Imaging Detection and Intelligent Perception, University of Electronic Science and Technology of China, Chengdu, 611731, China. Electronic address: yuanguohui@uestc.edu.cn. 3. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China; Laboratory of Imaging Detection and Intelligent Perception, University of Electronic Science and Technology of China, Chengdu, 611731, China. Electronic address: xgzhao@uestc.edu.cn. 4. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China. Electronic address: penglingbing@std.uestc.edu.cn. 5. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China; Laboratory of Imaging Detection and Intelligent Perception, University of Electronic Science and Technology of China, Chengdu, 611731, China. Electronic address: wangzhuoran@uestc.edu.cn. 6. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China; Laboratory of Imaging Detection and Intelligent Perception, University of Electronic Science and Technology of China, Chengdu, 611731, China. Electronic address: heyanmin@uestc.edu.cn. 7. Department of Ophthalmology, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu 610072, China. Electronic address: lucyjeffersonqu@hotmail.com. 8. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China; Laboratory of Imaging Detection and Intelligent Perception, University of Electronic Science and Technology of China, Chengdu, 611731, China. Electronic address: zmpeng@uestc.edu.cn.
Abstract
BACKGROUND AND OBJECTIVE: Diabetic retinopathy (DR), which is generally diagnosed by the presence of hemorrhages and hard exudates, is one of the most prevalent causes of visual impairment and blindness. Early detection of hard exudates (HEs) in color fundus photographs can help in preventing such destructive damage. However, this is a challenging task due to high intra-class diversity and high similarity with other structures in the fundus images. Most of the existing methods for detecting HEs are based on characterizing HEs using hand crafted features (HCFs) only, which can not characterize HEs accurately. Deep learning methods are scarce in this domain because they require large-scale sample sets for training which are not generally available for most routine medical imaging research. METHODS: To address these challenges, we propose a novel methodology for HE detection using deep convolutional neural network (DCNN) and multi-feature joint representation. Specifically, we present a new optimized mathematical morphological approach that first segments HE candidates accurately. Then, each candidate is characterized using combined features based on deep features with HCFs incorporated, which is implemented by a ridge regression-based feature fusion. This method employs multi-space-based intensity features, geometric features, a gray-level co-occurrence matrix (GLCM)-based texture descriptor, a gray-level size zone matrix (GLSZM)-based texture descriptor to construct HCFs, and a DCNN to automatically learn the deep information of HE. Finally, a random forest is employed to identify the true HEs among candidates. RESULTS: The proposed method is evaluated on two benchmark databases. It obtains an F-score of 0.8929 with an area under curve (AUC) of 0.9644 on the e-optha database and an F-score of 0.9326 with an AUC of 0.9323 on the HEI-MED database. These results demonstrate that our approach outperforms state-of-the-art methods. Our model also proves to be suitable for clinical applications based on private clinical images from a local hospital. CONCLUSIONS: This newly proposed method integrates the traditional HCFs and deep features learned from DCNN for detecting HEs. It achieves a new state-of-the-art in both detecting HEs and DR screening. Furthermore, the proposed feature selection and fusion strategy reduces feature dimension and improves HE detection performance.
BACKGROUND AND OBJECTIVE:Diabetic retinopathy (DR), which is generally diagnosed by the presence of hemorrhages and hard exudates, is one of the most prevalent causes of visual impairment and blindness. Early detection of hard exudates (HEs) in color fundus photographs can help in preventing such destructive damage. However, this is a challenging task due to high intra-class diversity and high similarity with other structures in the fundus images. Most of the existing methods for detecting HEs are based on characterizing HEs using hand crafted features (HCFs) only, which can not characterize HEs accurately. Deep learning methods are scarce in this domain because they require large-scale sample sets for training which are not generally available for most routine medical imaging research. METHODS: To address these challenges, we propose a novel methodology for HE detection using deep convolutional neural network (DCNN) and multi-feature joint representation. Specifically, we present a new optimized mathematical morphological approach that first segments HE candidates accurately. Then, each candidate is characterized using combined features based on deep features with HCFs incorporated, which is implemented by a ridge regression-based feature fusion. This method employs multi-space-based intensity features, geometric features, a gray-level co-occurrence matrix (GLCM)-based texture descriptor, a gray-level size zone matrix (GLSZM)-based texture descriptor to construct HCFs, and a DCNN to automatically learn the deep information of HE. Finally, a random forest is employed to identify the true HEs among candidates. RESULTS: The proposed method is evaluated on two benchmark databases. It obtains an F-score of 0.8929 with an area under curve (AUC) of 0.9644 on the e-optha database and an F-score of 0.9326 with an AUC of 0.9323 on the HEI-MED database. These results demonstrate that our approach outperforms state-of-the-art methods. Our model also proves to be suitable for clinical applications based on private clinical images from a local hospital. CONCLUSIONS: This newly proposed method integrates the traditional HCFs and deep features learned from DCNN for detecting HEs. It achieves a new state-of-the-art in both detecting HEs and DR screening. Furthermore, the proposed feature selection and fusion strategy reduces feature dimension and improves HE detection performance.
Authors: Ali H Al-Timemy; Zahraa M Mosa; Zaid Alyasseri; Alexandru Lavric; Marcelo M Lui; Rossen M Hazarbassanov; Siamak Yousefi Journal: Transl Vis Sci Technol Date: 2021-12-01 Impact factor: 3.283