Retinal Vessel Segmentation Using Multi-scale Generative Adversarial Network with Class Activation Mapping

Minqiang Yang, Yinru Ye, Kai Ye, Xiping Hu*, Bin Hu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationWireless Mobile Communication and Healthcare - 10th EAI International Conference, MobiHealth 2021, Proceedings
EditorsXinbo Gao, Abbas Jamalipour, Lei Guo
PublisherSpringer Science and Business Media Deutschland GmbH
Pages95-105
Number of pages11
ISBN (Print)9783031063671
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event10th EAI International Conference on Wireless Mobile Communication and Healthcare, MobiHealth 2021 - Virtual, Online
Duration: 13 Nov 202114 Nov 2021

Publication series

NameLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume440 LNICST
ISSN (Print)1867-8211
ISSN (Electronic)1867-822X

Conference

Conference10th EAI International Conference on Wireless Mobile Communication and Healthcare, MobiHealth 2021
CityVirtual, Online
Period13/11/2114/11/21

Keywords

  • Class activation mapping
  • Data augmentation
  • Multi-scale generative adversarial network
  • Retinal vessel segmentation

Fingerprint

Dive into the research topics of 'Retinal Vessel Segmentation Using Multi-scale Generative Adversarial Network with Class Activation Mapping'. Together they form a unique fingerprint.

Cite this