MPCCN: A Symmetry-Based Multi-Scale Position-Aware Cyclic Convolutional Network for Retinal Vessel Segmentation

被引:0
作者
Xia, Chunfen [1 ]
Lv, Jianqiang [2 ]
机构
[1] Huazhong Univ Sci & Technol, Sch Elect Informat & Commun, Wuhan 430074, Peoples R China
[2] Huanggang Normal Univ, Sch Comp, Huanggang 438000, Peoples R China
来源
SYMMETRY-BASEL | 2024年 / 16卷 / 09期
关键词
retinal vessel segmentation; biomedical image analysis; multi-scale input; guided attention mechanism; deep learning; NEURAL-NETWORK; BLOOD-VESSELS; MODEL; UNET;
D O I
10.3390/sym16091189
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
In medical image analysis, precise retinal vessel segmentation is crucial for diagnosing and managing ocular diseases as the retinal vascular network reflects numerous health indicators. Despite decades of development, challenges such as intricate textures, vascular ruptures, and undetected areas persist, particularly in accurately segmenting small vessels and addressing low contrast in imaging. This study introduces a novel segmentation approach called MPCCN that combines position-aware cyclic convolution (PCC) with multi-scale resolution input to tackle these challenges. By integrating standard convolution with PCC, MPCCN effectively captures both global and local features. A multi-scale input module enhances feature extraction, while a weighted-shared residual and guided attention module minimizes background noise and emphasizes vascular structures. Our approach achieves sensitivity values of 98.87%, 99.17%, and 98.88%; specificity values of 98.93%, 97.25%, and 99.20%; accuracy scores of 97.38%, 97.85%, and 97.75%; and AUC values of 98.90%, 99.15%, and 99.05% on the DRIVE, STARE, and CHASE_DB1 datasets, respectively. In addition, it records F1 scores of 90.93%, 91.00%, and 90.55%. Experimental results demonstrate that our method outperforms existing techniques, especially in detecting small vessels.
引用
收藏
页数:26
相关论文
共 72 条
[1]   Recurrent residual U-Net for medical image segmentation [J].
Alom, Md Zahangir ;
Yakopcic, Chris ;
Hasan, Mahmudul ;
Taha, Tarek M. ;
Asari, Vijayan K. .
JOURNAL OF MEDICAL IMAGING, 2019, 6 (01)
[2]   GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond [J].
Cao, Yue ;
Xu, Jiarui ;
Lin, Stephen ;
Wei, Fangyun ;
Hu, Han .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, :1971-1980
[3]   Retinal Vessel Segmentation Using Deep Learning: A Review [J].
Chen, Chunhui ;
Chuah, Joon Huang ;
Ali, Raza ;
Wang, Yizhou .
IEEE ACCESS, 2021, 9 :111985-112004
[4]   Adaptive deformable convolutional network [J].
Chen, Feng ;
Wu, Fei ;
Xu, Jing ;
Gao, Guangwei ;
Ge, Qi ;
Jing, Xiao-Yuan .
NEUROCOMPUTING, 2021, 453 :853-864
[5]   Automatic artery/vein classification methods for retinal blood vessel: A review [J].
Chen, Qihan ;
Peng, Jianqing ;
Zhao, Shen ;
Liu, Wanquan .
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2024, 113
[6]  
Dash Jyotiprava, 2017, Future Computing and Informatics Journal, V2, P103, DOI [10.1016/j.fcij.2017.10.001, 10.1016/j.fcij.2017.10.001]
[7]   A retinal blood vessel segmentation based on improved D-MNet and pulse-coupled neural network [J].
Deng, Xiangyu ;
Ye, Jinhong .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2022, 73
[8]   A ROBUST TECHNIQUES OF ENHANCEMENT AND SEGMENTATION BLOOD VESSELS IN RETINAL IMAGE USING DEEP LEARNING [J].
Desiani, Anita ;
Erwin ;
Suprihatin, Bambang ;
Agustina, Sinta Bella .
BIOMEDICAL ENGINEERING-APPLICATIONS BASIS COMMUNICATIONS, 2022, 34 (04)
[9]   Convolutional neural network: a review of models, methodologies and applications to object detection [J].
Dhillon, Anamika ;
Verma, Gyanendra K. .
PROGRESS IN ARTIFICIAL INTELLIGENCE, 2020, 9 (02) :85-112
[10]   MRU-NET: A U-Shaped Network for Retinal Vessel Segmentation [J].
Ding, Hongwei ;
Cui, Xiaohui ;
Chen, Leiyang ;
Zhao, Kun .
APPLIED SCIENCES-BASEL, 2020, 10 (19)