Staff View: Multimodal image fusion offers better spatial resolution for mass spectrometry imaging

Multimodal image fusion offers better spatial resolution for mass spectrometry imaging

High-resolution reconstruction has attracted increasing research interest in mass spectrometry imaging (MSI), but it remains a challenging ill-posed problem. In the present study, we proposed a deep learning model to fuse multimodal images to enhance the spatial resolution of MSI data, namely, DeepF...

Full description

Saved in:

Bibliographic Details
Main Authors:	Guo, Lei, Zhu, Jinyu, Wang, Keqi, Cheng, Kian-Kai, Xu, Jingjing, Dong, Liheng, Xu, Xiangnan, Chen, Can, Shah, Mudassir, Peng, Zhangxiao, Wang, Jianing, Cai, Zongwei, Dong, Jiyang
Format:	Article
Published:	American Chemical Society 2023
Subjects:	TP Chemical technology
Online Access:	http://eprints.utm.my/105023/ http://dx.doi.org/10.1021/acs.analchem.3c02002
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.utm.105023
record_format	eprints
spelling	my.utm.1050232024-04-01T07:50:15Z http://eprints.utm.my/105023/ Multimodal image fusion offers better spatial resolution for mass spectrometry imaging Guo, Lei Zhu, Jinyu Wang, Keqi Cheng, Kian-Kai Xu, Jingjing Dong, Liheng Xu, Xiangnan Chen, Can Shah, Mudassir Peng, Zhangxiao Wang, Jianing Cai, Zongwei Dong, Jiyang TP Chemical technology High-resolution reconstruction has attracted increasing research interest in mass spectrometry imaging (MSI), but it remains a challenging ill-posed problem. In the present study, we proposed a deep learning model to fuse multimodal images to enhance the spatial resolution of MSI data, namely, DeepFERE. Hematoxylin and eosin (H&E) stain microscopy imaging was used to pose constraints in the process of high-resolution reconstruction to alleviate the ill-posedness. A novel model architecture was designed to achieve multi-task optimization by incorporating multi-modal image registration and fusion in a mutually reinforced framework. Experimental results demonstrated that the proposed DeepFERE model is able to produce high-resolution reconstruction images with rich chemical information and a detailed structure on both visual inspection and quantitative evaluation. In addition, our method was found to be able to improve the delimitation of the boundary between cancerous and para-cancerous regions in the MSI image. Furthermore, the reconstruction of low-resolution spatial transcriptomics data demonstrated that the developed DeepFERE model may find wider applications in biomedical fields. American Chemical Society 2023 Article PeerReviewed Guo, Lei and Zhu, Jinyu and Wang, Keqi and Cheng, Kian-Kai and Xu, Jingjing and Dong, Liheng and Xu, Xiangnan and Chen, Can and Shah, Mudassir and Peng, Zhangxiao and Wang, Jianing and Cai, Zongwei and Dong, Jiyang (2023) Multimodal image fusion offers better spatial resolution for mass spectrometry imaging. Analytical Chemistry, 95 (25). pp. 9714-9721. ISSN 0003-2700 http://dx.doi.org/10.1021/acs.analchem.3c02002 DOI : 10.1021/acs.analchem.3c02002
institution	Universiti Teknologi Malaysia
building	UTM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Teknologi Malaysia
content_source	UTM Institutional Repository
url_provider	http://eprints.utm.my/
topic	TP Chemical technology
spellingShingle	TP Chemical technology Guo, Lei Zhu, Jinyu Wang, Keqi Cheng, Kian-Kai Xu, Jingjing Dong, Liheng Xu, Xiangnan Chen, Can Shah, Mudassir Peng, Zhangxiao Wang, Jianing Cai, Zongwei Dong, Jiyang Multimodal image fusion offers better spatial resolution for mass spectrometry imaging
description	High-resolution reconstruction has attracted increasing research interest in mass spectrometry imaging (MSI), but it remains a challenging ill-posed problem. In the present study, we proposed a deep learning model to fuse multimodal images to enhance the spatial resolution of MSI data, namely, DeepFERE. Hematoxylin and eosin (H&E) stain microscopy imaging was used to pose constraints in the process of high-resolution reconstruction to alleviate the ill-posedness. A novel model architecture was designed to achieve multi-task optimization by incorporating multi-modal image registration and fusion in a mutually reinforced framework. Experimental results demonstrated that the proposed DeepFERE model is able to produce high-resolution reconstruction images with rich chemical information and a detailed structure on both visual inspection and quantitative evaluation. In addition, our method was found to be able to improve the delimitation of the boundary between cancerous and para-cancerous regions in the MSI image. Furthermore, the reconstruction of low-resolution spatial transcriptomics data demonstrated that the developed DeepFERE model may find wider applications in biomedical fields.
format	Article
author	Guo, Lei Zhu, Jinyu Wang, Keqi Cheng, Kian-Kai Xu, Jingjing Dong, Liheng Xu, Xiangnan Chen, Can Shah, Mudassir Peng, Zhangxiao Wang, Jianing Cai, Zongwei Dong, Jiyang
author_facet	Guo, Lei Zhu, Jinyu Wang, Keqi Cheng, Kian-Kai Xu, Jingjing Dong, Liheng Xu, Xiangnan Chen, Can Shah, Mudassir Peng, Zhangxiao Wang, Jianing Cai, Zongwei Dong, Jiyang
author_sort	Guo, Lei
title	Multimodal image fusion offers better spatial resolution for mass spectrometry imaging
title_short	Multimodal image fusion offers better spatial resolution for mass spectrometry imaging
title_full	Multimodal image fusion offers better spatial resolution for mass spectrometry imaging
title_fullStr	Multimodal image fusion offers better spatial resolution for mass spectrometry imaging
title_full_unstemmed	Multimodal image fusion offers better spatial resolution for mass spectrometry imaging
title_sort	multimodal image fusion offers better spatial resolution for mass spectrometry imaging
publisher	American Chemical Society
publishDate	2023
url	http://eprints.utm.my/105023/ http://dx.doi.org/10.1021/acs.analchem.3c02002
_version_	1797905896296153088
score	13.211869

Multimodal image fusion offers better spatial resolution for mass spectrometry imaging

Similar Items