1
|
Selvachandran G, Quek SG, Paramesran R, Ding W, Son LH. Developments in the detection of diabetic retinopathy: a state-of-the-art review of computer-aided diagnosis and machine learning methods. Artif Intell Rev 2023; 56:915-964. [PMID: 35498558 PMCID: PMC9038999 DOI: 10.1007/s10462-022-10185-6] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 04/04/2022] [Indexed: 02/02/2023]
Abstract
The exponential increase in the number of diabetics around the world has led to an equally large increase in the number of diabetic retinopathy (DR) cases which is one of the major complications caused by diabetes. Left unattended, DR worsens the vision and would lead to partial or complete blindness. As the number of diabetics continue to increase exponentially in the coming years, the number of qualified ophthalmologists need to increase in tandem in order to meet the demand for screening of the growing number of diabetic patients. This makes it pertinent to develop ways to automate the detection process of DR. A computer aided diagnosis system has the potential to significantly reduce the burden currently placed on the ophthalmologists. Hence, this review paper is presented with the aim of summarizing, classifying, and analyzing all the recent development on automated DR detection using fundus images from 2015 up to this date. Such work offers an unprecedentedly thorough review of all the recent works on DR, which will potentially increase the understanding of all the recent studies on automated DR detection, particularly on those that deploys machine learning algorithms. Firstly, in this paper, a comprehensive state-of-the-art review of the methods that have been introduced in the detection of DR is presented, with a focus on machine learning models such as convolutional neural networks (CNN) and artificial neural networks (ANN) and various hybrid models. Each AI will then be classified according to its type (e.g. CNN, ANN, SVM), its specific task(s) in performing DR detection. In particular, the models that deploy CNN will be further analyzed and classified according to some important properties of the respective CNN architectures of each model. A total of 150 research articles related to the aforementioned areas that were published in the recent 5 years have been utilized in this review to provide a comprehensive overview of the latest developments in the detection of DR. Supplementary Information The online version contains supplementary material available at 10.1007/s10462-022-10185-6.
Collapse
Affiliation(s)
- Ganeshsree Selvachandran
- Department of Actuarial Science and Applied Statistics, Faculty of Business & Management, UCSI University, Jalan Menara Gading, Cheras, 56000 Kuala Lumpur, Malaysia
| | - Shio Gai Quek
- Department of Actuarial Science and Applied Statistics, Faculty of Business & Management, UCSI University, Jalan Menara Gading, Cheras, 56000 Kuala Lumpur, Malaysia
| | - Raveendran Paramesran
- Institute of Computer Science and Digital Innovation, UCSI University, Jalan Menara Gading, Cheras, 56000 Kuala Lumpur, Malaysia
| | - Weiping Ding
- School of Information Science and Technology, Nantong University, Nantong, 226019 People’s Republic of China
| | - Le Hoang Son
- VNU Information Technology Institute, Vietnam National University, Hanoi, Vietnam
| |
Collapse
|
2
|
Guo S. Fundus image segmentation via hierarchical feature learning. Comput Biol Med 2021; 138:104928. [PMID: 34662814 DOI: 10.1016/j.compbiomed.2021.104928] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2021] [Revised: 10/06/2021] [Accepted: 10/06/2021] [Indexed: 01/28/2023]
Abstract
Fundus Image Segmentation (FIS) is an essential procedure for the automated diagnosis of ophthalmic diseases. Recently, deep fully convolutional networks have been widely used for FIS with state-of-the-art performance. The representative deep model is the U-Net, which follows an encoder-decoder architecture. I believe it is suboptimal for FIS because consecutive pooling operations in the encoder lead to low-resolution representation and loss of detailed spatial information, which is particularly important for the segmentation of tiny vessels and lesions. Motivated by this, a high-resolution hierarchical network (HHNet) is proposed to learn semantic-rich high-resolution representations and preserve spatial details simultaneously. Specifically, a High-resolution Feature Learning (HFL) module with increasing dilation rates was first designed to learn the high-level high-resolution representations. Then, the HHNet was constructed by incorporating three HFL modules and two feature aggregation modules. The HHNet runs in a coarse-to-fine manner, and fine segmentation maps are output at the last level. Extensive experiments were conducted on fundus lesion segmentation, vessel segmentation, and optic cup segmentation. The experimental results reveal that the proposed method shows highly competitive or even superior performance in terms of segmentation performance and computation cost, indicating its potential advantages in clinical application.
Collapse
Affiliation(s)
- Song Guo
- School of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an, 710055, China.
| |
Collapse
|
3
|
Wang H, Yuan G, Zhao X, Peng L, Wang Z, He Y, Qu C, Peng Z. Hard exudate detection based on deep model learned information and multi-feature joint representation for diabetic retinopathy screening. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2020; 191:105398. [PMID: 32092614 DOI: 10.1016/j.cmpb.2020.105398] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/12/2019] [Revised: 01/18/2020] [Accepted: 02/14/2020] [Indexed: 06/10/2023]
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.
Collapse
Affiliation(s)
- Hui Wang
- 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.
| | - Guohui Yuan
- 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.
| | - Xuegong Zhao
- 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.
| | - Lingbing Peng
- School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
| | - Zhuoran Wang
- 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.
| | - Yanmin He
- 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.
| | - Chao Qu
- Department of Ophthalmology, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu 610072, China.
| | - Zhenming Peng
- 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.
| |
Collapse
|
4
|
Guo S, Li T, Kang H, Li N, Zhang Y, Wang K. L-Seg: An end-to-end unified framework for multi-lesion segmentation of fundus images. Neurocomputing 2019. [DOI: 10.1016/j.neucom.2019.04.019] [Citation(s) in RCA: 37] [Impact Index Per Article: 7.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/18/2023]
|
5
|
Exudate detection in fundus images using deeply-learnable features. Comput Biol Med 2018; 104:62-69. [PMID: 30439600 DOI: 10.1016/j.compbiomed.2018.10.031] [Citation(s) in RCA: 79] [Impact Index Per Article: 13.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2018] [Revised: 10/27/2018] [Accepted: 10/27/2018] [Indexed: 01/28/2023]
Abstract
Presence of exudates on a retina is an early sign of diabetic retinopathy, and automatic detection of these can improve the diagnosis of the disease. Convolutional Neural Networks (CNNs) have been used for automatic exudate detection, but with poor performance. This study has investigated different deep learning techniques to maximize the sensitivity and specificity. We have compared multiple deep learning methods, and both supervised and unsupervised classifiers for improving the performance of automatic exudate detection, i.e., CNNs, pre-trained Residual Networks (ResNet-50) and Discriminative Restricted Boltzmann Machines. The experiments were conducted on two publicly available databases: (i) DIARETDB1 and (ii) e-Ophtha. The results show that ResNet-50 with Support Vector Machines outperformed other networks with an accuracy and sensitivity of 98% and 0.99, respectively. This shows that ResNet-50 can be used for the analysis of the fundus images to detect exudates.
Collapse
|
6
|
Karthikeyan R, Alli P. Feature Selection and Parameters Optimization of Support Vector Machines Based on Hybrid Glowworm Swarm Optimization for Classification of Diabetic Retinopathy. J Med Syst 2018; 42:195. [PMID: 30209620 DOI: 10.1007/s10916-018-1055-x] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2018] [Accepted: 09/04/2018] [Indexed: 10/28/2022]
Abstract
Diabetic Retinopathy (DR) has been a leading cause of blindness in case of human beings falling between the ages of 20 and 74 years. This will have a major influence on both the patient and the society as it can normally influence the humans in their gainful years. An early DR detection is quite challenging as it may not be detected by humans. There are several techniques and algorithms that have been established for detecting the DR. These techniques have been facing problems to achieve effective sensitivity, accuracy, and specificity. In order to overcome all these problems, the work has proposed one more such effective algorithm for image processing in order to increase the efficiency and also identify easily the DR diseases. A major challenge in the task is the automatic detection of the microaneurysms. In this work, the Support Vector Machine (SVM) parameters optimized with Glowworm Swarm Optimization (GSO) and Genetic Algorithm (GA) is used to classify the DR. Because the SVM parameter C and γ to control the performance of the classifier. For this work, the SVMs get fused with the hybrid GSO-GA along with the feature chromosomes that are generated that will thereby direct the GA search to a straight line of the error of optimal generalization in their super parameter space. This GSO algorithm will not have memory and the glow worms will not retain any information in memory. The results of the experiment prove that this method had achieved a better performance.
Collapse
Affiliation(s)
- R Karthikeyan
- Department of CSE, PSNA College of Engineering and Technology, Dindigul, Tamilnadu, India.
| | - P Alli
- Velammal College of Engineering and Technology, Madurai, Tamilnadu, India
| |
Collapse
|