PA-Net: A hybrid architecture for retinal vessel segmentation☆

被引:0
作者
Luo, Xuebing [1 ]
Peng, Lingxi [1 ]
Ke, Ziyan [1 ]
Lin, Jinhui [1 ]
Yu, Zhiwen [2 ]
机构
[1] Guangzhou Univ, Sch Mech & Elect Engn, Guangzhou 510006, Guangdong, Peoples R China
[2] South China Univ Technol, Sch Comp Sci & Engn, Guangzhou 510650, Guangdong, Peoples R China
基金
中国国家自然科学基金;
关键词
Retinal vessel segmentation; Retinal images; Transformer; Feature fusion; Deep learning; IMAGES; ATTENTION;
D O I
10.1016/j.patcog.2024.111254
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes a hybrid architecture, PA-Net, which amalgamates the strengths of convolutional neural networks and the transformer model to enhance the precision of retinal vessel segmentation. We propose a novel component, the Lightweight Parallel Transformer (LPT), to augment the transformer's adaptability for the task of retinal vessel segmentation. This LPT addresses the shortcomings of standard transformer that are highly dependent on large datasets and computing resources, and can capture long-range dependencies to prevent slender vessels from breaking. Furthermore, we introduce an Adaptive Vascular Feature Fusion module to offset the vascular information loss induced by downsampling layers, thereby enhancing microvessel recognition. The effectiveness of PA-Net was assessed across four distinct datasets: DRIVE, CHASE_DB1, STARE, and HRF, with sensitivities of 0.8284, 0.8570, 0.8813, and 0.8497, respectively. The results suggest that the proposed method outperforms other state-of-the-art alternatives.
引用
收藏
页数:12
相关论文
共 36 条
[11]  
Huang H., 2023, P IEEE C COMP VIS PA, P22690, DOI DOI 10.48550/ARXIV.2211.11167
[12]  
Huiyu Wang, 2020, Computer Vision - ECCV 2020. 16th European Conference. Proceedings. Lecture Notes in Computer Science (LNCS 12349), P108, DOI 10.1007/978-3-030-58548-8_7
[13]   Robust retinal blood vessel segmentation using hybrid active contour model [J].
Karn, Prakash Kumar ;
Biswal, Birendra ;
Samantaray, Subhransu Ranjan .
IET IMAGE PROCESSING, 2019, 13 (03) :440-450
[14]   Retinal vessel segmentation by using AFNet [J].
Li, Dongyuan ;
Peng, Lingxi ;
Peng, Shaohu ;
Xiao, Hongxin ;
Zhang, Yifan .
VISUAL COMPUTER, 2023, 39 (05) :1929-1941
[15]   Accurate Retinal Vessel Segmentation in Color Fundus Images via Fully Attention-Based Networks [J].
Li, Kaiqi ;
Qi, Xingqun ;
Luo, Yiwen ;
Yao, Zeyi ;
Zhou, Xiaoguang ;
Sun, Muyi .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2021, 25 (06) :2071-2081
[16]  
Li LZ, 2020, IEEE WINT CONF APPL, P3645, DOI 10.1109/WACV45572.2020.9093621
[17]   Wave-Net: A lightweight deep network for retinal vessel segmentation from fundus images [J].
Liu, Yanhong ;
Shen, Ji ;
Yang, Lei ;
Yu, Hongnian ;
Bian, Guibin .
COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 152
[18]   ResDO-UNet: A deep residual network for accurate retinal vessel segmentation from fundus images [J].
Liu, Yanhong ;
Shen, Ji ;
Yang, Lei ;
Bian, Guibin ;
Yu, Hongnian .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 79
[19]   Swin Transformer: Hierarchical Vision Transformer using Shifted Windows [J].
Liu, Ze ;
Lin, Yutong ;
Cao, Yue ;
Hu, Han ;
Wei, Yixuan ;
Zhang, Zheng ;
Lin, Stephen ;
Guo, Baining .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :9992-10002
[20]   Measuring Retinal Vessel Tortuosity in 10-Year-Old Children: Validation of the Computer-Assisted Image Analysis of the Retina (CAIAR) Program [J].
Owen, Christopher G. ;
Rudnicka, Alicja R. ;
Mullen, Robert ;
Barman, Sarah A. ;
Monekosso, Dorothy ;
Whincup, Peter H. ;
Ng, Jeffrey ;
Paterson, Carl .
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2009, 50 (05) :2004-2010