CASIA OpenIR
graph convolution based residual connected network for morphological reconstruction in fluorescence molecular tomography
Wang Y(王宇); Bian C(边畅); Du Y(杜洋); Tian J(田捷)
2022-03
Conference NameSPIE Medical image 2022
Volume12036
Pages527-533
Conference Date2022-2
Conference Place美国
Abstract

Fluorescence molecular tomography (FMT) is a promising multimodality-fused medical imaging technique, aiming at noninvasively and dynamically visualizing the interaction processes at the cellular and molecular level. However, the quality of FMT reconstruction is limited by the simplified linear model of photon propagation. In this work, we propose a novel GCN based Residual connected (GCN-RC) network to improve the quality of FMT morphological reconstruction. Instead of using a simplified linear model of photon propagation for FMT recon-struction, the method can directly construct a nonlinear mapping relationship between the photon density of an object surface and its internal fluorescent source. GCNRC network consists of a fully connected(FC) sub-network and a GCN sub-network connected by means of residual connection. The FC sub-network provides a coarse reconstruction result and GCN sub-network fine-tunes the morphological quality of reconstructed result. In order to validate the reconstruction performance of GCN-RC, we performed numerical simulation experiments and in vivo experiments based on tumor-bearing mice. Comparisons were performed with the L2-based Tikhonov method (Tikhonov-L2), inverse problem simulation (IPS) method and GCN-RC method. Both numerical simulated and in vivo experimental results demonstrated that GCN-RC achieved improved reconstruction in terms of both source localization and morphology recovery.

KeywordFluorescence molecular tomography Graph convolution network
DOIhttps://doi.org/10.1117/12.2605349
Indexed ByEI
Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48534
Collection中国科学院自动化研究所
中国科学院分子影像重点实验室
Corresponding AuthorDu Y(杜洋); Tian J(田捷)
AffiliationInstitute of Automation CAS
Recommended Citation
GB/T 7714
Wang Y,Bian C,Du Y,et al. graph convolution based residual connected network for morphological reconstruction in fluorescence molecular tomography[C],2022:527-533.
Files in This Item:
File Name/Size DocType Version Access License
120361X.pdf(625KB)会议论文 开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang Y(王宇)]'s Articles
[Bian C(边畅)]'s Articles
[Du Y(杜洋)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang Y(王宇)]'s Articles
[Bian C(边畅)]'s Articles
[Du Y(杜洋)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang Y(王宇)]'s Articles
[Bian C(边畅)]'s Articles
[Du Y(杜洋)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 120361X.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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