中文版 | English
Title

DS3 -Net: Difficulty-Perceived Common-to-T1ce Semi-supervised Multimodal MRI Synthesis Network

Author
Corresponding AuthorTang,Xiaoying
DOI
Publication Years
2022
Conference Name
25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)
ISSN
0302-9743
EISSN
1611-3349
ISBN
978-3-031-16445-3
Source Title
Pages
571-581
Conference Date
SEP 18-22, 2022
Conference Place
null,Singapore,SINGAPORE
Publication Place
GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND
Publisher
Abstract

Contrast-enhanced T1 (T1ce) is one of the most essential magnetic resonance imaging (MRI) modalities for diagnosing and analyzing brain tumors, especially gliomas. In clinical practice, common MRI modalities such as T1, T2, and fluid attenuation inversion recovery are relatively easy to access while T1ce is more challenging considering the additional cost and potential risk of allergies to the contrast agent. Therefore, it is of great clinical necessity to develop a method to synthesize T1ce from other common modalities. Current paired image translation methods typically have the issue of requiring a large amount of paired data and do not focus on specific regions of interest, e.g., the tumor region, in the synthesization process. To address these issues, we propose a Difficulty-perceived common-to-T1ce Semi-Supervised multimodal MRI Synthesis network (DS -Net), involving both paired and unpaired data together with dual-level knowledge distillation. DS -Net predicts a difficulty map to progressively promote the synthesis task. Specifically, a pixelwise constraint and a patchwise contrastive constraint are guided by the predicted difficulty map. Through extensive experiments on the publicly-available BraTS2020 dataset, DS -Net outperforms its supervised counterpart in each respect. Furthermore, with only 5% paired data, the proposed DS -Net achieves competitive performance with state-of-the-art image translation methods utilizing 100% paired data, delivering an average SSIM of 0.8947 and an average PSNR of 23.60. The source code is available at https://github.com/Huangziqi777/DS-3_Net.

Keywords
SUSTech Authorship
First ; Corresponding
Language
English
URL[Source Record]
Indexed By
Funding Project
National Natural Science Foundation of China[62071210]
WOS Research Area
Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
WOS Subject
Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
WOS Accession No
WOS:000867434800054
Scopus EID
2-s2.0-85139109005
Data Source
Scopus
Citation statistics
Cited Times [WOS]:0
Document TypeConference paper
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/406262
DepartmentDepartment of Electrical and Electronic Engineering
Affiliation
1.Department of Electrical and Electronic Engineering,Southern University of Science and Technology,Shenzhen,China
2.Department of Electrical and Electronic Engineering,The University of Hong Kong,Hong Kong
First Author AffilicationDepartment of Electrical and Electronic Engineering
Corresponding Author AffilicationDepartment of Electrical and Electronic Engineering
First Author's First AffilicationDepartment of Electrical and Electronic Engineering
Recommended Citation
GB/T 7714
Huang,Ziqi,Lin,Li,Cheng,Pujin,et al. DS3 -Net: Difficulty-Perceived Common-to-T1ce Semi-supervised Multimodal MRI Synthesis Network[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2022:571-581.
Files in This Item:
There are no files associated with this item.
Related Services
Fulltext link
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Huang,Ziqi]'s Articles
[Lin,Li]'s Articles
[Cheng,Pujin]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Huang,Ziqi]'s Articles
[Lin,Li]'s Articles
[Cheng,Pujin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Huang,Ziqi]'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.