TY - GEN
T1 - Retinal Vessel Segmentation Using Multi-scale Generative Adversarial Network with Class Activation Mapping
AU - Yang, Minqiang
AU - Ye, Yinru
AU - Ye, Kai
AU - Hu, Xiping
AU - Hu, Bin
N1 - Publisher Copyright:
© 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.
PY - 2022
Y1 - 2022
N2 - Retinal vessel segmentation plays a significant role in the accurate diagnosis of retinal diseases. However, existing methods commonly omit micro-vessels in retinal images and generate some false-positive vessels. To alleviate this issue, we propose a multi-scale generative adversarial network with class activation mapping to achieve efficient segmentation. For the problem of small amount of data, we introduce a novel data augmentation method, which can generate multiple samples by cutting pixels from other samples. This method increases the diversity of samples and improve the robustness of the model. We compare our method with previous models with several metrics, and experiments show the superiority and effectiveness of our model.
AB - Retinal vessel segmentation plays a significant role in the accurate diagnosis of retinal diseases. However, existing methods commonly omit micro-vessels in retinal images and generate some false-positive vessels. To alleviate this issue, we propose a multi-scale generative adversarial network with class activation mapping to achieve efficient segmentation. For the problem of small amount of data, we introduce a novel data augmentation method, which can generate multiple samples by cutting pixels from other samples. This method increases the diversity of samples and improve the robustness of the model. We compare our method with previous models with several metrics, and experiments show the superiority and effectiveness of our model.
KW - Class activation mapping
KW - Data augmentation
KW - Multi-scale generative adversarial network
KW - Retinal vessel segmentation
UR - http://www.scopus.com/inward/record.url?scp=85132981022&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-06368-8_7
DO - 10.1007/978-3-031-06368-8_7
M3 - Conference contribution
AN - SCOPUS:85132981022
SN - 9783031063671
T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
SP - 95
EP - 105
BT - Wireless Mobile Communication and Healthcare - 10th EAI International Conference, MobiHealth 2021, Proceedings
A2 - Gao, Xinbo
A2 - Jamalipour, Abbas
A2 - Guo, Lei
PB - Springer Science and Business Media Deutschland GmbH
T2 - 10th EAI International Conference on Wireless Mobile Communication and Healthcare, MobiHealth 2021
Y2 - 13 November 2021 through 14 November 2021
ER -