Title | Student Becomes Decathlon Master in Retinal Vessel Segmentation via Dual-Teacher Multi-target Domain Adaptation |
Author | |
Corresponding Author | Tang, 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]:1
|
Document Type | Conference paper |
Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/479621 |
Department | Department 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 Affilication | Department of Electrical and Electronic Engineering |
Corresponding Author Affilication | Department of Electrical and Electronic Engineering; Southern University of Science and Technology |
First Author's First Affilication | Department 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. |
|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment