Affiliations 

  • 1 Department of Electronic Science, National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen 361005, China
  • 2 Institute of Big Data Science and Industry, Shanxi University, Taiyuan 030006, China
  • 3 Faculty of Chemical and Energy Engineering, Universiti Teknologi Malaysia, Johor Bahru, Johor 81310, Malaysia
  • 4 School of Computing and Data Science, Xiamen University Malaysia, Sepang 43600, Malaysia
  • 5 School of Mathematics and Statistics, The University of Sydney, Sydney, NSW 2006, Australia
  • 6 Department of Hepatobiliary Surgery and Fujian Institute of Hepatobiliary Surgery, Fujian Medical University Union Hospital, Fuzhou 350001, China
  • 7 Department of Molecular Oncology, Eastern Hepatobiliary Surgery Hospital & National Centre for Liver Cancer, Navy Military Medical University, Shanghai 200438, China
  • 8 State Key Laboratory of Environmental and Biological Analysis, Department of Chemistry, Hong Kong Baptist University, Hong Kong SAR 999077, China
Anal Chem, 2023 Jun 27;95(25):9714-9721.
PMID: 37296503 DOI: 10.1021/acs.analchem.3c02002

Abstract

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.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.