1
|
Cai P, Li B, Sun G, Yang B, Wang X, Lv C, Yan J. DEAF-Net: Detail-Enhanced Attention Feature Fusion Network for Retinal Vessel Segmentation. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01207-6. [PMID: 39103564 DOI: 10.1007/s10278-024-01207-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/29/2024] [Revised: 06/25/2024] [Accepted: 07/08/2024] [Indexed: 08/07/2024]
Abstract
Retinal vessel segmentation is crucial for the diagnosis of ophthalmic and cardiovascular diseases. However, retinal vessels are densely and irregularly distributed, with many capillaries blending into the background, and exhibit low contrast. Moreover, the encoder-decoder-based network for retinal vessel segmentation suffers from irreversible loss of detailed features due to multiple encoding and decoding, leading to incorrect segmentation of the vessels. Meanwhile, the single-dimensional attention mechanisms possess limitations, neglecting the importance of multidimensional features. To solve these issues, in this paper, we propose a detail-enhanced attention feature fusion network (DEAF-Net) for retinal vessel segmentation. First, the detail-enhanced residual block (DERB) module is proposed to strengthen the capacity for detailed representation, ensuring that intricate features are efficiently maintained during the segmentation of delicate vessels. Second, the multidimensional collaborative attention encoder (MCAE) module is proposed to optimize the extraction of multidimensional information. Then, the dynamic decoder (DYD) module is introduced to preserve spatial information during the decoding process and reduce the information loss caused by upsampling operations. Finally, the proposed detail-enhanced feature fusion (DEFF) module composed of DERB, MCAE and DYD modules fuses feature maps from both encoding and decoding and achieves effective aggregation of multi-scale contextual information. The experiments conducted on the datasets of DRIVE, CHASEDB1, and STARE, achieving Sen of 0.8305, 0.8784, and 0.8654, and AUC of 0.9886, 0.9913, and 0.9911 on DRIVE, CHASEDB1, and STARE, respectively, demonstrate the performance of our proposed network, particularly in the segmentation of fine retinal vessels.
Collapse
Affiliation(s)
- Pengfei Cai
- School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, 300222, China
| | - Biyuan Li
- School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, 300222, China.
- Tianjin Development Zone Jingnuohanhai Data Technology Co., Ltd, Tianjin, China.
| | - Gaowei Sun
- School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, 300222, China
| | - Bo Yang
- School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, 300222, China
| | - Xiuwei Wang
- School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, 300222, China
| | - Chunjie Lv
- School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, 300222, China
| | - Jun Yan
- School of Mathematics, Tianjin University, Tianjin, 300072, China
| |
Collapse
|
2
|
Liu J, Zhao D, Shen J, Geng P, Zhang Y, Yang J, Zhang Z. HRD-Net: High resolution segmentation network with adaptive learning ability of retinal vessel features. Comput Biol Med 2024; 173:108295. [PMID: 38520920 DOI: 10.1016/j.compbiomed.2024.108295] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2023] [Revised: 01/31/2024] [Accepted: 03/12/2024] [Indexed: 03/25/2024]
Abstract
Retinal segmentation is a crucial step in the early warning of human health conditions. However, retinal blood vessels possess complex curvature, irregular distribution, and contain multi-scale fine structures, which make the limited receptive field of regular convolution challenging to process their vascular details efficiently. Additionally, the encoder-decoder based network leads to irreversible spatial information loss because of multiple downsampling, resulting in over-segmentation and missed segmentation of the vessels. For this reason, we develop a high-resolution network based on Deformable Convolution v3, called HRD-Net. By constructing a high-resolution representation, the network allows special attention to be paid to the details of tiny blood vessels. The proposed feature enhancement cascade module based on Deformable Convolution v3 can flexibly adapt and capture the ever-changing morphology and intricate connections of retinal blood vessels, ensuring the continuity of vessel segmentation. In the output phase of the network, the proposed global aggregation module integrates full-resolution feature maps while suppressing redundant features, achieving an effective fusion of high-level semantic information and spatial detail information. In addition, we have re-examined the selection criteria for activation and normalization methods, and also refine the network architectures from a spatial domain perspective to release redundant computational loads. Testing on the DRIVE, STARE, and CHASE_DB1 datasets indicates that HRD-Net, with fewer parameters, outperforms existing segmentation methods on several evaluation metrics such as F1, ACC, SE, SP, AUC, and IOU.
Collapse
Affiliation(s)
- Jianhua Liu
- School of Electrical and Electronic Engineering, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China; Hebei Provincial Collaborative Innovation Center of Transportation Power Grid Intelligent Integration Technology and Equipment, School of Electrical and Electronic Engineering, Shijiazhuang Tiedao University, Shijiazhuang, China.
| | - Dongxin Zhao
- School of Electrical and Electronic Engineering, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China.
| | - Juncai Shen
- College of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China.
| | - Peng Geng
- College of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China.
| | - Ying Zhang
- College of Resources and Environment, Xingtai University, Xingtai, 054001, China.
| | - Jiaxin Yang
- School of Electrical and Electronic Engineering, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China.
| | - Ziqian Zhang
- School of Electrical and Electronic Engineering, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China.
| |
Collapse
|
3
|
Guo H, Meng J, Zhao Y, Zhang H, Dai C. High-precision retinal blood vessel segmentation based on a multi-stage and dual-channel deep learning network. Phys Med Biol 2024; 69:045007. [PMID: 38198716 DOI: 10.1088/1361-6560/ad1cf6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2023] [Accepted: 01/10/2024] [Indexed: 01/12/2024]
Abstract
Objective.The high-precision segmentation of retinal vessels in fundus images is important for the early diagnosis of ophthalmic diseases. However, the extraction for microvessels is challenging due to their characteristics of low contrast and high structural complexity. Although some works have been developed to improve the segmentation ability in thin vessels, they have only been successful in recognizing small vessels with relatively high contrast.Approach.Therefore, we develop a deep learning (DL) framework with a multi-stage and dual-channel network model (MSDC_NET) to further improve the thin-vessel segmentation with low contrast. Specifically, an adaptive image enhancement strategy combining multiple preprocessing and the DL method is firstly proposed to elevate the contrast of thin vessels; then, a two-channel model with multi-scale perception is developed to implement whole- and thin-vessel segmentation; and finally, a series of post-processing operations are designed to extract more small vessels in the predicted maps from thin-vessel channels.Main results.Experiments on DRIVE, STARE and CHASE_DB1 demonstrate the superiorities of the proposed MSDC_NET in extracting more thin vessels in fundus images, and quantitative evaluations on several parameters based on the advanced ground truth further verify the advantages of our proposed DL model. Compared with the previous multi-branch method, the specificity and F1score are improved by about 2.18%, 0.68%, 1.73% and 2.91%, 0.24%, 8.38% on the three datasets, respectively.Significance.This work may provide richer information to ophthalmologists for the diagnosis and treatment of vascular-related ophthalmic diseases.
Collapse
Affiliation(s)
- Hui Guo
- School of Computer, Qufu Normal University, 276826 Rizhao, People's Republic of China
| | - Jing Meng
- School of Computer, Qufu Normal University, 276826 Rizhao, People's Republic of China
| | - Yongfu Zhao
- School of Computer, Qufu Normal University, 276826 Rizhao, People's Republic of China
| | - Hongdong Zhang
- School of Computer, Qufu Normal University, 276826 Rizhao, People's Republic of China
| | - Cuixia Dai
- College of Science, Shanghai Institute of Technology, 201418 Shanghai, People's Republic of China
| |
Collapse
|
4
|
Mahapatra S, Agrawal S, Mishro PK, Panda R, Dora L, Pachori RB. A Review on Retinal Blood Vessel Enhancement and Segmentation Techniques for Color Fundus Photography. Crit Rev Biomed Eng 2024; 52:41-69. [PMID: 37938183 DOI: 10.1615/critrevbiomedeng.2023049348] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2023]
Abstract
The retinal image is a trusted modality in biomedical image-based diagnosis of many ophthalmologic and cardiovascular diseases. Periodic examination of the retina can help in spotting these abnormalities in the early stage. However, to deal with today's large population, computerized retinal image analysis is preferred over manual inspection. The precise extraction of the retinal vessel is the first and decisive step for clinical applications. Every year, many more articles are added to the literature that describe new algorithms for the problem at hand. The majority of the review article is restricted to a fairly small number of approaches, assessment indices, and databases. In this context, a comprehensive review of different vessel extraction methods is inevitable. It includes the development of a first-hand classification of these methods. A bibliometric analysis of these articles is also presented. The benefits and drawbacks of the most commonly used techniques are summarized. The primary challenges, as well as the scope of possible changes, are discussed. In order to make a fair comparison, numerous assessment indices are considered. The findings of this survey could provide a new path for researchers for further work in this domain.
Collapse
Affiliation(s)
- Sakambhari Mahapatra
- Department of Electronics and Telecommunication Engineering, Veer Surendra Sai University of Technology, Burla, India
| | - Sanjay Agrawal
- Department of Electronics and Telecommunication Engineering, Veer Surendra Sai University of Technology, Burla, India
| | - Pranaba K Mishro
- Department of Electronics and Telecommunication Engineering, Veer Surendra Sai University of Technology, Burla, India
| | - Rutuparna Panda
- Department of Electronics and Telecommunication Engineering, Veer Surendra Sai University of Technology, Burla, India
| | - Lingraj Dora
- Department of Electrical and Electronics Engineering, Veer Surendra Sai University of Technology, Burla, India
| | - Ram Bilas Pachori
- Department of Electrical Engineering, Indian Institute of Technology Indore, Indore, India
| |
Collapse
|
5
|
Retinal image blood vessel classification using hybrid deep learning in cataract diseased fundus images. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2023.104776] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/12/2023]
|
6
|
Wang G, Huang Y, Ma K, Duan Z, Luo Z, Xiao P, Yuan J. Automatic vessel crossing and bifurcation detection based on multi-attention network vessel segmentation and directed graph search. Comput Biol Med 2023; 155:106647. [PMID: 36848799 DOI: 10.1016/j.compbiomed.2023.106647] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/08/2022] [Revised: 01/04/2023] [Accepted: 02/07/2023] [Indexed: 02/17/2023]
Abstract
Analysis of the vascular tree is the basic premise to automatically diagnose retinal biomarkers associated with ophthalmic and systemic diseases, among which accurate identification of intersection and bifurcation points is quite challenging but important for disentangling complex vascular network and tracking vessel morphology. In this paper, we present a novel directed graph search-based multi-attentive neural network approach to automatically segment the vascular network and separate intersections and bifurcations from color fundus images. Our approach uses multi-dimensional attention to adaptively integrate local features and their global dependencies while learning to focus on target structures at different scales to generate binary vascular maps. A directed graphical representation of the vascular network is constructed to represent the topology and spatial connectivity of the vascular structures. Using local geometric information including color difference, diameter, and angle, the complex vascular tree is decomposed into multiple sub-trees to finally classify and label vascular feature points. The proposed method has been tested on the DRIVE dataset and the IOSTAR dataset containing 40 images and 30 images, respectively, with 0.863 and 0.764 F1-score of detection points and average accuracy of 0.914 and 0.854 for classification points. These results demonstrate the superiority of our proposed method outperforming state-of-the-art methods in feature point detection and classification.
Collapse
Affiliation(s)
- Gengyuan Wang
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, 510060, China; School of Life Sciences, South China University of Technology, Guangzhou, 510006, Guangdong, China
| | - Yuancong Huang
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, 510060, China
| | - Ke Ma
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, 510060, China
| | - Zhengyu Duan
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, 510060, China
| | - Zhongzhou Luo
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, 510060, China
| | - Peng Xiao
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, 510060, China.
| | - Jin Yuan
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, 510060, China.
| |
Collapse
|
7
|
Susheel Kumar K, Pratap Singh N. Identification of retinal diseases based on retinal blood vessel segmentation using Dagum PDF and feature-based machine learning. THE IMAGING SCIENCE JOURNAL 2023. [DOI: 10.1080/13682199.2023.2183319] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
Affiliation(s)
- K. Susheel Kumar
- Department of Computer science and Engineering, National Institute of Technology, Hamirpur, India
- Department of Computer Science and Engineering, Gandhi Institute of Technology and Management, Bengaluru, India
| | - Nagendra Pratap Singh
- Department of Computer science and Engineering, National Institute of Technology, Hamirpur, India
| |
Collapse
|
8
|
Wang J, Zhou L, Yuan Z, Wang H, Shi C. MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2023; 20:6912-6931. [PMID: 37161134 DOI: 10.3934/mbe.2023298] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/11/2023]
Abstract
PURPOSE Accurate retinal vessel segmentation is of great value in the auxiliary screening of various diseases. However, due to the low contrast between the ends of the branches of the fundus blood vessels and the background, and the variable morphology of the optic disc and cup in the retinal image, the task of high-precision retinal blood vessel segmentation still faces difficulties. METHOD This paper proposes a multi-scale integrated context network, MIC-Net, which fully fuses the encoder-decoder features, and extracts multi-scale information. First, a hybrid stride sampling (HSS) block was designed in the encoder to minimize the loss of helpful information caused by the downsampling operation. Second, a dense hybrid dilated convolution (DHDC) was employed in the connection layer. On the premise of preserving feature resolution, it can perceive richer contextual information. Third, a squeeze-and-excitation with residual connections (SERC) was introduced in the decoder to adjust the channel attention adaptively. Finally, we utilized a multi-layer feature fusion mechanism in the skip connection part, which enables the network to consider both low-level details and high-level semantic information. RESULTS We evaluated the proposed method on three public datasets DRIVE, STARE and CHASE. In the experimental results, the Area under the receiver operating characteristic (ROC) and the accuracy rate (Acc) achieved high performances of 98.62%/97.02%, 98.60%/97.76% and 98.73%/97.38%, respectively. CONCLUSIONS Experimental results show that the proposed method can obtain comparable segmentation performance compared with the state-of-the-art (SOTA) methods. Specifically, the proposed method can effectively reduce the small blood vessel segmentation error, thus proving it a promising tool for auxiliary diagnosis of ophthalmic diseases.
Collapse
Affiliation(s)
- Jinke Wang
- Department of Software Engineering, Harbin University of Science and Technology, Rongcheng 264300, China
- School of Automation, Harbin University of Science and Technology, Harbin 150080, China
| | - Lubiao Zhou
- School of Automation, Harbin University of Science and Technology, Harbin 150080, China
| | - Zhongzheng Yuan
- Department of Software Engineering, Harbin University of Science and Technology, Rongcheng 264300, China
| | - Haiying Wang
- School of Automation, Harbin University of Science and Technology, Harbin 150080, China
| | - Changfa Shi
- Mobile E-business Collaborative Innovation Center of Hunan Province, Hunan University of Technology and Business, Changsha 410205, China
| |
Collapse
|
9
|
Yi S, Wei Y, Zhang G, Wang T, She F, Yang X. Segmentation of retinal vessels based on MRANet. Heliyon 2022; 9:e12361. [PMID: 36685439 PMCID: PMC9852666 DOI: 10.1016/j.heliyon.2022.e12361] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2022] [Revised: 07/27/2022] [Accepted: 12/07/2022] [Indexed: 12/23/2022] Open
Abstract
The segmentation of retinal vessel takes a crucial part in computer-aided diagnosis of diseases and eye disorders. However, the insufficient segmentation of the capillary vessels and weak anti-noise interference ability make such task more difficult. To solve this problem, we proposed a multi-scale residual attention network (MRANet) which is based on U-Net network. Firstly, to collect useful information about the blood vessels more effectively, we proposed a multi-level feature fusion block (MLF block). Then, different weights of each fused feature are learned by using attention blocks, which can retain more useful feature information while reducing the interference of redundant features. Thirdly, multi-scale residual connection block (MSR block) is constructed, which can better extract the image features. Finally, we use the DropBlock layer in the network to reduce the network parameters and alleviate network overfitting. Experiments show that based on DRIVE, the accuracy rate and the AUC performance value of our network are 0.9698 and 0.9899 respectively, and based on CHASE_DB1 dataset, they are 0.9755 and 0.9893 respectively. Our network has a better segmentation effect compared with other methods, which can ensure the continuity and completeness of blood vessel segmentation.
Collapse
|
10
|
Cao J, Chen J, Zhang X, Peng Y. Diabetic retinopathy classification based on dense connectivity and asymmetric convolutional neural network. Neural Comput Appl 2022. [DOI: 10.1007/s00521-022-07952-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|