题名 | Unsupervised Domain Adaptation for Cross-Modality Retinal Vessel Segmentation via Disentangling Representation Style Transfer and Collaborative Consistency Learning |
作者 | |
通讯作者 | Tang, Xiaoying |
DOI | |
发表日期 | 2022
|
会议名称 | 19th IEEE International Symposium on Biomedical Imaging (IEEE ISBI)
|
ISSN | 1945-7928
|
EISSN | 1945-8452
|
ISBN | 978-1-6654-2924-5
|
会议录名称 | |
页码 | 1-5
|
会议日期 | 28-31 March 2022
|
会议地点 | Kolkata, India
|
出版地 | 345 E 47TH ST, NEW YORK, NY 10017 USA
|
出版者 | |
摘要 | Various deep learning models have been developed to segment anatomical structures from medical images, but they typically have poor performance when tested on another target domain with different data distribution. Recently, unsupervised domain adaptation methods have been proposed to alleviate this so-called domain shift issue, but most of them are designed for scenarios with relatively small domain shifts and are likely to fail when encountering a large domain gap. In this paper, we propose DCDA, a novel cross-modality unsupervised domain adaptation framework for tasks with large domain shifts, e.g., segmenting retinal vessels from OCTA and OCT images. DCDA mainly consists of a disentangling representation style transfer (DRST) module and a collaborative consistency learning (CCL) module. DRST decomposes images into content components and style codes and performs style transfer and image reconstruction. CCL contains two segmentation models, one for source domain and the other for target domain. The two models use labeled data (together with the corresponding transferred images) for supervised learning and perform collaborative consistency learning on unlabeled data. Each model focuses on the corresponding single domain and aims to yield an expertized domain-specific segmentation model. Through extensive experiments on retinal vessel segmentation, our framework achieves Dice scores close to target-trained oracle both from OCTA to OCT and from OCT to OCTA, significantly outperforming other state-of-the-art methods. |
关键词 | |
学校署名 | 第一
; 通讯
|
语种 | 英语
|
相关链接 | [Scopus记录] |
收录类别 | |
资助项目 | Shenzhen Basic Research Program[JCYJ20200925153847004]
|
WOS研究方向 | Engineering
; Radiology, Nuclear Medicine & Medical Imaging
|
WOS类目 | Engineering, Biomedical
; Radiology, Nuclear Medicine & Medical Imaging
|
WOS记录号 | WOS:000836243800271
|
EI入藏号 | 20221912089277
|
EI主题词 | Computer Vision
; Deep Learning
; Image Segmentation
; Medical Imaging
; Ophthalmology
|
EI分类号 | Biomedical Engineering:461.1
; Ergonomics And Human Factors Engineering:461.4
; Medicine And Pharmacology:461.6
; Computer Applications:723.5
; Vision:741.2
; Imaging Techniques:746
|
Scopus记录号 | 2-s2.0-85129590697
|
来源库 | Scopus
|
全文链接 | https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9761675 |
引用统计 |
被引频次[WOS]:11
|
成果类型 | 会议论文 |
条目标识符 | http://sustech.caswiz.com/handle/2SGJ60CL/334857 |
专题 | 工学院_电子与电气工程系 |
作者单位 | 1.Southern University of Science and Technology,Department of Electronic and Electrical Engineering,Shenzhen,China 2.Department of Electrical and Electronic Engineering,The University of Hong Kong,Hong Kong |
第一作者单位 | 电子与电气工程系 |
通讯作者单位 | 电子与电气工程系 |
第一作者的第一单位 | 电子与电气工程系 |
推荐引用方式 GB/T 7714 |
Peng, Linkai,Lin, Li,Cheng, Pujin,et al. Unsupervised Domain Adaptation for Cross-Modality Retinal Vessel Segmentation via Disentangling Representation Style Transfer and Collaborative Consistency Learning[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2022:1-5.
|
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | 操作 | |
10.1109@ISBI52829.20(2290KB) | -- | -- | 开放获取 | -- | 浏览 |
|
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论