中文版 | English
Title

Student Becomes Decathlon Master in Retinal Vessel Segmentation via Dual-Teacher Multi-target Domain Adaptation

Author
Corresponding AuthorTang, Xiaoying
DOI
Publication Years
2022
Conference Name
13th MICCAI Workshop on Machine Learning in Medical Imaging (MICCAI-MLMI)
ISSN
0302-9743
EISSN
1611-3349
ISBN
978-3-031-21013-6
Source Title
Volume
13583
Conference Date
SEP 18, 2022
Conference Place
null,Singapore,SINGAPORE
Publication Place
GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND
Publisher
Abstract

Unsupervised domain adaptation has been proposed recently to tackle the so-called domain shift between training data and test data with different distributions. However, most of them only focus on single-target domain adaptation and cannot be applied to the scenario with multiple target domains. In this paper, we propose RVms, a novel unsupervised multi-target domain adaptation approach to segment retinal vessels (RVs) from multimodal and multicenter retinal images. RVms mainly consists of a style augmentation and transfer (SAT) module and a dual-teacher knowledge distillation (DTKD) module. SAT augments and clusters images into source-similar domains and source-dissimilar domains via Bezier and Fourier transformations. DTKD utilizes the augmented and transformed data to train two teachers, one for source-similar domains and the other for source-dissimilar domains. Afterwards, knowledge distillation is performed to iteratively distill different domain knowledge from teachers to a generic student. The local relative intensity transformation is employed to characterize RVs in a domain invariant manner and promote the generalizability of teachers and student models. Moreover, we construct a new multimodal and multicenter vascular segmentation dataset from existing publicly-available datasets, which can be used to benchmark various domain adaptation and domain generalization methods. Through extensive experiments, RVms is found to be very close to the target-trained Oracle in terms of segmenting the RVs, largely outperforming other state-of-the-art methods.

Keywords
SUSTech Authorship
First ; Corresponding
Language
English
URL[Source Record]
Indexed By
Funding Project
Shenzhen Basic Research Program[JCYJ20200925153847004] ; National Natural Science Foundation of China[62071210] ; Shenzhen Science and Technology Program[RCYX2021060910305 6042] ; Shenzhen Science and Technology Innovation Committee[KCXFZ2020122117340001]
WOS Research Area
Computer Science ; Radiology, Nuclear Medicine & Medical Imaging
WOS Subject
Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Radiology, Nuclear Medicine & Medical Imaging
WOS Accession No
WOS:000922009300004
Data Source
Web of Science
Citation statistics
Cited Times [WOS]:0
Document TypeConference paper
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/479621
DepartmentDepartment of Electrical and Electronic Engineering
Affiliation
1.Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen, Peoples R China
2.Univ Hong Kong, Dept Elect & Elect Engn, Hong Kong, Peoples R China
3.Southern Univ Sci & Technol, Jiaxing Res Inst, Jiaxing, Peoples R China
First Author AffilicationDepartment of Electrical and Electronic Engineering
Corresponding Author AffilicationDepartment of Electrical and Electronic Engineering;  Southern University of Science and Technology
First Author's First AffilicationDepartment of Electrical and Electronic Engineering
Recommended Citation
GB/T 7714
Peng, Linkai,Lin, Li,Cheng, Pujin,et al. Student Becomes Decathlon Master in Retinal Vessel Segmentation via Dual-Teacher Multi-target Domain Adaptation[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2022.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Peng, Linkai]'s Articles
[Lin, Li]'s Articles
[Cheng, Pujin]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Peng, Linkai]'s Articles
[Lin, Li]'s Articles
[Cheng, Pujin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Peng, Linkai]'s Articles
[Lin, Li]'s Articles
[Cheng, Pujin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.