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

页码：1742 / 1746

页数：5

共 50 条

[21] An automatic retinal vessel segmentation approach based on Convolutional Neural Networks [J].

Chala, Mohamed ;

Nsiri, Benayad ;

Alaoui, My Hachem El Yousfi ;

Soulaymani, Abdelmajid ;

Mokhtari, Abdelrhani ;

Benaji, Brahim .

EXPERT SYSTEMS WITH APPLICATIONS, 2021, 184

[22] Dense U-net Based on Patch-Based Learning for Retinal Vessel Segmentation [J].

Wang, Chang ;

Zhao, Zongya ;

Ren, Qiongqiong ;

Xu, Yongtao ;

Yu, Yi .

ENTROPY, 2019, 21 (02)

[23] Retinal Vessel Segmentation Based on Gated Skip-Connection Network [J].

Yao, Huixia ;

Jiang, Yun ;

Cheng, Tongtong ;

Gao, Jing .

NEURAL INFORMATION PROCESSING, ICONIP 2021, PT V, 2021, 1516 :731-738

[24] Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance Imaging [J].

Bernal, Jose ;

Kushibar, Kaisar ;

Cabezas, Mariano ;

Valverde, Sergi ;

Oliver, Arnau ;

Llado, Xavier .

IEEE ACCESS, 2019, 7 :89986-90002

[25] Retinal Vessel Segmentation Using Convolutional Neural Networks [J].

Guleryuz, Mehmet Sefik ;

Ulusoy, Ilkay .

2018 26TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2018,

[26] CONVOLUTIONAL NEURAL NETWORKS FOR DEEP FEATURE LEARNING IN RETINAL VESSEL SEGMENTATION [J].

Khalaf, Aya F. ;

Yassine, Inas A. ;

Fahmy, Ahmed S. .

2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2016, :385-388

[27] Boosting Sensitivity of A Retinal Vessel Segmentation Algorithm With Convolutional Neural Network [J].

Soomro, Toufique A. ;

Afifi, Ahmed J. ;

Gao, Junbin ;

Hellwich, Olaf ;

Khan, Mohammad A. U. ;

Paul, Manoranjan ;

Zheng, Lihong .

2017 INTERNATIONAL CONFERENCE ON DIGITAL IMAGE COMPUTING - TECHNIQUES AND APPLICATIONS (DICTA), 2017, :126-133

[28] W-net: A Convolutional Neural Network for Retinal Vessel Segmentation [J].

Reyes-Figueroa, Alan ;

Rivera, Mariano .

PATTERN RECOGNITION (MCPR 2021), 2021, 12725 :355-368

[29] Parallel Architecture of Fully Convolved Neural Network for Retinal Vessel Segmentation [J].

Sathananthavathi, V. ;

Indumathi, G. ;

Ranjani, A. Swetha .

JOURNAL OF DIGITAL IMAGING, 2020, 33 (01) :168-180

[30] Retinal Vessel Segmentation Based on Recurrent Convolutional Skip Connection U-Net [J].

Hu, Han ;

Liu, Zhao .

2021 4TH INTERNATIONAL CONFERENCE ON INTELLIGENT AUTONOMOUS SYSTEMS (ICOIAS 2021), 2021, :65-71

← 1 2 3 4 5 →