Minimizing-Entropy and Fourier Consistency Network for Domain Adaptation on Optic Disc and Cup Segmentation

Automated segmentation of the optic disc (OD) and optic cup (OC) from different datasets plays an important role in the diagnosis of glaucoma and greatly saves human resources in both data annotation and image segmentation. However, the domain shift between different datasets suppresses the generali...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shao-Peng Xu, Tian-Bao Li, Zhe-Qi Zhang, Dan Song
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	OD and OC segmentation unsupervised domain adaptation entropy minimization Fourier consistency fundus image Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/da6af6d370fa467e9657ee7e7f84c9bf
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:da6af6d370fa467e9657ee7e7f84c9bf
record_format	dspace
spelling	oai:doaj.org-article:da6af6d370fa467e9657ee7e7f84c9bf2021-11-24T00:03:21ZMinimizing-Entropy and Fourier Consistency Network for Domain Adaptation on Optic Disc and Cup Segmentation2169-353610.1109/ACCESS.2021.3128174https://doaj.org/article/da6af6d370fa467e9657ee7e7f84c9bf2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9615072/https://doaj.org/toc/2169-3536Automated segmentation of the optic disc (OD) and optic cup (OC) from different datasets plays an important role in the diagnosis of glaucoma and greatly saves human resources in both data annotation and image segmentation. However, the domain shift between different datasets suppresses the generalization ability of the segmentation network, especially damaging the performance of segmentation in the target domain, which is unlabeled. Therefore, using a transfer learning algorithm or domain adaptation method to enhance the migration ability of segmentation models has become an essential step and has attracted the attention of many researchers. In this paper, we propose an unsupervised domain adaptation network, called the Minimizing-entropy and Fourier Domain Adaptation network (MeFDA), to narrow the discrepancy between the source and target domains and prevent the degradation of segmentation performance. First, we perform adversarial optimization on the entropy maps of the predicted segmentation results to alleviate the domain shift. Then, direct entropy-minimization optimization is applied to the unlabeled target domain data to improve the credibility of the prediction segmentation maps. To enhance the prediction consistency of the target domain data, we augment the target domain dataset through the Fourier transform by replacing the low-frequency part in the target images with that of the source images. Then, a semantic consistency constraint is imposed on the raw images and augmented images of the target domain to improve the prediction consistency of the segmentation model, thereby further narrowing the discrepancy between the source and target domains. Experiments on several public retinal fundus image datasets prove the superiority of MeFDA compared with state-of-the-art methods, and the ablation study analyzes the importance of the different proposed components.Shao-Peng XuTian-Bao LiZhe-Qi ZhangDan SongIEEEarticleOD and OC segmentationunsupervised domain adaptationentropy minimizationFourier consistencyfundus imageElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 153985-153994 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	OD and OC segmentation unsupervised domain adaptation entropy minimization Fourier consistency fundus image Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	OD and OC segmentation unsupervised domain adaptation entropy minimization Fourier consistency fundus image Electrical engineering. Electronics. Nuclear engineering TK1-9971 Shao-Peng Xu Tian-Bao Li Zhe-Qi Zhang Dan Song Minimizing-Entropy and Fourier Consistency Network for Domain Adaptation on Optic Disc and Cup Segmentation
description	Automated segmentation of the optic disc (OD) and optic cup (OC) from different datasets plays an important role in the diagnosis of glaucoma and greatly saves human resources in both data annotation and image segmentation. However, the domain shift between different datasets suppresses the generalization ability of the segmentation network, especially damaging the performance of segmentation in the target domain, which is unlabeled. Therefore, using a transfer learning algorithm or domain adaptation method to enhance the migration ability of segmentation models has become an essential step and has attracted the attention of many researchers. In this paper, we propose an unsupervised domain adaptation network, called the Minimizing-entropy and Fourier Domain Adaptation network (MeFDA), to narrow the discrepancy between the source and target domains and prevent the degradation of segmentation performance. First, we perform adversarial optimization on the entropy maps of the predicted segmentation results to alleviate the domain shift. Then, direct entropy-minimization optimization is applied to the unlabeled target domain data to improve the credibility of the prediction segmentation maps. To enhance the prediction consistency of the target domain data, we augment the target domain dataset through the Fourier transform by replacing the low-frequency part in the target images with that of the source images. Then, a semantic consistency constraint is imposed on the raw images and augmented images of the target domain to improve the prediction consistency of the segmentation model, thereby further narrowing the discrepancy between the source and target domains. Experiments on several public retinal fundus image datasets prove the superiority of MeFDA compared with state-of-the-art methods, and the ablation study analyzes the importance of the different proposed components.
format	article
author	Shao-Peng Xu Tian-Bao Li Zhe-Qi Zhang Dan Song
author_facet	Shao-Peng Xu Tian-Bao Li Zhe-Qi Zhang Dan Song
author_sort	Shao-Peng Xu
title	Minimizing-Entropy and Fourier Consistency Network for Domain Adaptation on Optic Disc and Cup Segmentation
title_short	Minimizing-Entropy and Fourier Consistency Network for Domain Adaptation on Optic Disc and Cup Segmentation
title_full	Minimizing-Entropy and Fourier Consistency Network for Domain Adaptation on Optic Disc and Cup Segmentation
title_fullStr	Minimizing-Entropy and Fourier Consistency Network for Domain Adaptation on Optic Disc and Cup Segmentation
title_full_unstemmed	Minimizing-Entropy and Fourier Consistency Network for Domain Adaptation on Optic Disc and Cup Segmentation
title_sort	minimizing-entropy and fourier consistency network for domain adaptation on optic disc and cup segmentation
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/da6af6d370fa467e9657ee7e7f84c9bf
work_keys_str_mv	AT shaopengxu minimizingentropyandfourierconsistencynetworkfordomainadaptationonopticdiscandcupsegmentation AT tianbaoli minimizingentropyandfourierconsistencynetworkfordomainadaptationonopticdiscandcupsegmentation AT zheqizhang minimizingentropyandfourierconsistencynetworkfordomainadaptationonopticdiscandcupsegmentation AT dansong minimizingentropyandfourierconsistencynetworkfordomainadaptationonopticdiscandcupsegmentation
_version_	1718416124356329472

Minimizing-Entropy and Fourier Consistency Network for Domain Adaptation on Optic Disc and Cup Segmentation

Ejemplares similares