PATCH-BASED FULLY CONVOLUTIONAL NEURAL NETWORK WITH SKIP CONNECTIONS FOR RETINAL BLOOD VESSEL SEGMENTATION

被引:0
作者
Feng, Zhongwei [1 ]
Yang, Jie [1 ]
Yao, Lixiu [1 ]
机构
[1] Shanghai Jiao Tong Univ, Inst Image Proc & Pattern Recognit, Shanghai 200240, Peoples R China
来源
2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2017年
关键词
Computer Aided Diagnosis; Convolutional Neural Networks; Retinal Blood Vessel Segmentation; Local Entropy Sampling; Class-balancing Loss; IMAGES;
D O I
暂无
中图分类号
TB8 [摄影技术];
学科分类号
0804 ;
摘要
Automated segmentation of retinal blood vessels plays an important role in the computer aided diagnosis of retinal diseases. The paper presents a new formulation of patch-based fully Convolutional Neural Networks (CNNs) that allows accurate segmentation of the retinal blood vessels. A major modification in this retinal blood vessel segmentation task is to improve and speed-up the patch-based fully CNN training by local entropy sampling and a skip CNN architecture with class-balancing loss. The proposed method is experimented on DRIVE dataset and achieves strong performance and significantly outperforms the-state-of-the-art for retinal blood vessel segmentation with 78.11% sensitivity, 98.39% specificity, 95.60% accuracy, 87.36% precision and 97.92% AUC score respectively.
引用
收藏
页码:1742 / 1746
页数:5
相关论文
共 50 条
[31]   Atrous residual convolutional neural network based on U-Net for retinal vessel segmentation [J].
Wu, Jin ;
Liu, Yong ;
Zhu, Yuanpei ;
Li, Zun .
PLOS ONE, 2022, 17 (08)
[32]   Skip connection information enhancement network for retinal vessel segmentation [J].
Liang, Jing ;
Jiang, Yun ;
Yan, Hao .
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2024, 62 (10) :3163-3178
[33]   Robust retinal blood vessel segmentation using a patch-based statistical adaptive multi-scale line detector [J].
Iqbal, Shahzaib ;
Naveed, Khuram ;
Naqvi, Syed S. ;
Naveed, Asim ;
Khan, Tariq M. .
DIGITAL SIGNAL PROCESSING, 2023, 139
[34]   Multilevel and Multiscale Deep Neural Network for Retinal Blood Vessel Segmentation [J].
Samuel, Pearl Mary ;
Veeramalai, Thanikaiselvan .
SYMMETRY-BASEL, 2019, 11 (07)
[35]   Sine-Net: A fully convolutional deep learning architecture for retinal blood vessel segmentation [J].
Atli, Ibrahim ;
Gedik, Osman Serdar .
ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH, 2021, 24 (02) :271-283
[36]   Patch-Based Training of Fully Convolutional Network for Hyperspectral Image Classification With Sparse Point Labels [J].
Zhang, Xueliang ;
Zheng, Zixian ;
Xiao, Pengfeng ;
Li, Zhenshi ;
He, Guangjun .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 :8884-8897
[37]   Retinal vessel segmentation using neural network [J].
Thangaraj, Sumathi ;
Periyasamy, Vivekanandan ;
Balaji, Ravikanth .
IET IMAGE PROCESSING, 2018, 12 (05) :669-678
[38]   Simultaneous Segmentation of Multiple Retinal Pathologies Using Fully Convolutional Deep Neural Network [J].
Badar, Maryam ;
Shahzad, M. ;
Fraz, M. M. .
MEDICAL IMAGE UNDERSTANDING AND ANALYSIS, MIUA 2018, 2018, 894 :313-324
[39]   RETRACTED: Robust retinal blood vessel segmentation using convolutional neural network and support vector machine (Retracted Article) [J].
Balasubramanian, Kishore ;
Ananthamoorthy, N. P. .
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2021, 12 (03) :3559-3569
[40]   Dual-channel asymmetric convolutional neural network for an efficient retinal blood vessel segmentation in eye fundus images [J].
Xu, Yanan ;
Fan, Yingle .
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, 2022, 42 (02) :695-706