Multimodal Image Fusion Offers Better Spatial Resolution for Mass Spectrometry Imaging
Open accessPublished version of a preprint
The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
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.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Similarly, the DeepFERE model fuses mass spectrometry imaging (MSI) with hematoxylin and eosin (H&E) stain microscopy to enhance spatial resolution, improving the delimitation of cancerous and para-cancerous regions (Guo et al., 2023).”
From Spatial pharmacology of anti-cancer immunomodulators: a comprehensive review (2026) · cites this paper as Guo et al., 2023
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Textural Features for Image Classification
Haralick, R. M., Shanmugam, K., & Dinstein, I. (1973) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/tsmc.1973.4309314 · Cited by 22,886
Advances in neural information processing systems 7
Cios, K., & Shields, M. (1997) · Neurocomputing · doi:10.1016/s0925-2312(97)90018-7 · Cited by 22,059
UMAP: Uniform Manifold Approximation and Projection
McInnes, L., Healy, J., Saul, N., & Großberger, L. (2018) · Journal of Open Source Software · doi:10.21105/joss.00861 · Cited by 9,826
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
(2018) · doi:10.1109/cvpr40276.2018 · Cited by 4,737
Cubic convolution interpolation for digital image processing
Keys, R. (1981) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1981.1163711 · Cited by 3,255
Deep Learning for Image Super-Resolution: A Survey
Wang, Z., Chen, J., & Hoi, S. C. H. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2982166 · Cited by 1,969
MALDIquant: a versatile R package for the analysis of mass spectrometry data
Gibb, S., & Strimmer, K. (2012) · Bioinformatics · doi:10.1093/bioinformatics/bts447 · Cited by 695
INet: Convolutional Networks for Biomedical Image Segmentation
Weng, W., & Zhu, X. (2021) · IEEE Access · doi:10.1109/access.2021.3053408 · Cited by 509
Transmission-mode MALDI-2 mass spectrometry imaging of cells and tissues at subcellular resolution
Niehaus, M., Soltwisch, J., Belov, M. E., & Dreisewerd, K. (2019) · Nature Methods · doi:10.1038/s41592-019-0536-2 · Cited by 429
Research works printed but not linked: 1
- Helminiak, D.; Hu, H.; Laskin, J.; Ye, D. IS&T International Symposium on Electronic Imaging , 2021; Vol. 33, pp 2901–2907.
Cited by
Zhang, H., Zhang, J., Yuan, C., Zhang, D., Lu, D., Chen, S., Wu, Y., & Wu, C. (2024) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2024.117834 · Cited by 37
High-resolution imaging mass cytometry to map subcellular structures
Bollhagen, A., Whipman, J., Coelho, R., Heinzelmann-Schwarz, V. A., Jacob, F., & Bodenmiller, B. (2025) · Nature Methods · doi:10.1038/s41592-025-02889-8 · Cited by 34
“We compared nuclear blind deconvolution (for example, SpiDe-SR 11 ) and cross-modality deep learning 12 , have shown promise but rely on strong prior assumptions or high-resolution training data.”
Liang, Z., Guo, Y., Sharma, A., McCurdy, C. R., & Prentice, B. M. (2024) · Analytical Chemistry · doi:10.1021/acs.analchem.4c01553 · Cited by 24
Advances in multimodal mass spectrometry for single‐cell analysis and imaging enhancement
Croslow, S. W., Trinklein, T. J., & Sweedler, J. V. (2024) · FEBS Letters · doi:10.1002/1873-3468.14798 · Cited by 21
Guang, X., Gan, S., Guo, B., & Li, Y. (2024) · Rapid Communications in Mass Spectrometry · doi:10.1002/rcm.9717 · Cited by 8
To image or not to image: Use of imaging mass spectrometry in biomedical lipidomics
Maimó‐Barceló, A., Pérez‐Romero, K., Rodríguez, R. M. A., Huergo, C., Calvo, I., Fernández, J. A., & Barceló‐Coblijn, G. (2025) · Progress in Lipid Research · doi:10.1016/j.plipres.2025.101319 · Cited by 10
Guo, A., Chen, Z., Ma, Y., Lv, Y., Yan, H., Li, F., Xing, Y., Luo, Q., & Zheng, H. (2024) · Artificial Intelligence Chemistry · doi:10.1016/j.aichem.2024.100058 · Cited by 9
Liang, Z., Guo, Y., Diao, X., & Prentice, B. M. (2024) · Journal of the American Society for Mass Spectrometry · doi:10.1021/jasms.4c00144 · Cited by 7
Wang, Y., Zhao, C., Xing, Z., Zhu, M., Hao, L., Wang, K., Bai, J., Tian, H., & Dong, D. (2024) · Analytical Chemistry · doi:10.1021/acs.analchem.4c04548 · Cited by 5
Self-citationImage Fusion for Super‐Resolution Mass Spectrometry Imaging of Plant Tissue
Zou, Y., Sun, S., Tang, W., & Li, B. (2025) · Advanced Science · doi:10.1002/advs.202512662 · Cited by 5
Multimodal Mass Spectrometry Imaging in Atlas Building: A Review
Vanderschoot, K. A., Bender, K. J., Caro, C. M. D., Steineman, K. A., & Neumann, E. K. (2024) · Seminars in Nephrology · doi:10.1016/j.semnephrol.2025.151578 · Cited by 6
“151,152 Data fusion can simplify interpretation tremendously and allow for more impactful visualization of key biological data.”
Chen, D., Colwell, N., & Yang, Z. (2026) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2026.118767 · Cited by 5
Multi‐modal mass spectrometry imaging of a single tissue section
Zhan, L., Huang, Y., & Wang, G. (2024) · Journal of Mass Spectrometry · doi:10.1002/jms.5074 · Cited by 6
Zheng, Y., Li, H., Wang, R., Jiang, C., & Zhao, Y. (2025) · World Journal of Gastroenterology · doi:10.3748/wjg.v31.i39.111323 · Cited by 4
Zhang, D., Zhang, H., Yuexin, Y., Jin, Y., Chen, Y., & Wu, C. (2025) · Journal of Proteomics · doi:10.1016/j.jprot.2025.105436 · Cited by 4
Yang, W., Li, H., Wang, Y.-K., & Wang, Y.-Q. (2026) · Expert systems with applications · doi:10.1016/j.eswa.2025.131083 · Cited by 2
Liang, Z., Guo, Y., Sharma, A., McCurdy, C. R., & Prentice, B. M. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.03.12.584673 · Cited by 3
“43,44,51 The CNN models are attractive options for image fusion because these models only require the original RGB features of the H&E image.”
MethodYang, M., Iqfath, M., Meke, F. N., Qu, Z., Hernly, E., Su, P., Zhang, Z., & Laskin, J. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.09.04.611280 · Cited by 3
Promising mass spectrometry imaging: exploring microscale insights in food
Cao, X., Cong, P., Song, Y., Liu, Y., Xue, C., & Xu, J. (2025) · Critical Reviews in Food Science and Nutrition · doi:10.1080/10408398.2025.2451189 · Cited by 2
Self-citationRSR-MSI: Reference-Based Super-Resolution for Mass Spectrometry Imaging of Tissues and Single Cells
Fang, Y., Wu, C., Zhang, C., Xu, Y., Yin, Z., Xu, Z., & Hang, W. (2025) · Analytical Chemistry · doi:10.1021/acs.analchem.5c05933 · Cited by 2
Advanced Computational Approaches for Multimodal Fusion in Mass Spectrometry Imaging
Guo, L. (2025) · Rapid Communications in Mass Spectrometry · doi:10.1002/rcm.70007 · Cited by 2
“Notably, UMAP has demonstrated superior performance in the visualization of large-scale MSI datasets in some studies [13, 36], making it particularly well-suited for generating representatives from MSI data.”
InfluentialSelf-citationResearch progress of deep learning applications in mass spectrometry imaging data analysis
Huang, D., Liu, X., & Xu, G. (2024) · Chinese Journal of Chromatography · doi:10.3724/sp.j.1123.2023.10035 · Cited by 4
Ozturk, E., Venkataraman, A., Moctezuma, F. G. R., & Coskun, A. F. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.10.21.619323 · Cited by 4
Spatial pharmacology of anti-cancer immunomodulators: a comprehensive review
Chen, S., Tu, L., & Chen, Q. (2026) · Frontiers in Pharmacology · doi:10.3389/fphar.2026.1898418 · Cited by 1
“Similarly, the DeepFERE model fuses mass spectrometry imaging (MSI) with hematoxylin and eosin (H&E) stain microscopy to enhance spatial resolution, improving the delimitation of cancerous and para-cancerous regions (Guo et al., 2023).”
Fields, L. G., Miles, H. N., Adrian, A. E., Patrenets, E., Ricke, W. A., & Li, L. (2025) · Journal of Proteome Research · doi:10.1021/acs.jproteome.4c01140 · Cited by 1
DPM: A Deep Learning and Optimal Transport Framework for Cost-Effective Spatial Metabolomics
Yao, B., Yang, L., Zhang, C., Lv, Y., Yang, C., Di, L., Luo, J., & Lin, S. (2026) · Analytical Chemistry · doi:10.1021/acs.analchem.5c06903 · Cited by 1
Yang, M., Iqfath, M., Meke, F. N., Qu, Z., Hernly, E., Tang, X., Su, P., Zhang, Z., & Laskin, J. (2026) · Molecular & Cellular Proteomics · doi:10.1016/j.mcpro.2026.101632 · Cited by 2
Mayo, E. D., Samuel, J. M., Guo, Y., Ciccone, A. B., Liang, Z., & Prentice, B. M. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.03.729902 · Cited by 1
“27, 28 We have previously presented a workflow that uses supervised and deep learning models to perform image fusion using MALDI imaging MS and H&E microscopy images acquired from the same tissue section.”
Mi, H., Wei, S., Fu, X., Xia, Z., Zhang, Y., Tang, Z., Wang, X., Tang, X., Liang, S., & Ding, X. (2026) · Analytical Chemistry · doi:10.1021/acs.analchem.5c06898
A Unified Transformer Architecture for 3D MSI-H&E Fusion
Imani, H., Das, N., & Styles, I. B. (2026) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi61048.2026.11515580
“3 compares our TransUniFERE-3D with bicubic interpolation and DeepFERE [8] on slice #23 of the human colorectal adenocarcinoma dataset.”
Zhang, T., Fu, X., Wei, S., Liang, S., Li, S., & Ding, X. L. (2026) · Journal of Pharmaceutical Analysis · doi:10.1016/j.jpha.2026.101669
Tian, Y., Lu, X., Cao, Y., Chen, K., Zhang, Q., Liu, W., Sun, C., Xu, X., Wang, Y., & Cao, C. (2026) · Analytica Chimica Acta · doi:10.1016/j.aca.2026.345706
Self-citationMohammed, S. A., Sammour, D. A., Hoffmann, D. C., Sievers, P., Bausbacher, T., Hahn, M., Uçal, Y., Mildenberger, I., Opitz, C. A., Schmidt, S., et al. (2026) · Advanced Intelligent Discovery · doi:10.1002/aidi.70134
Multimodal FRACTAL-MSI and Image Fusion Improves Detection and Resolution of Biomolecule Imaging
Westerhausen, M. T., Bergin, R. J., Phillips, C. R., Violi, J. P., Lockwood, T. E., Ridlen, R. M., & Bishop, D. (2026) · ACS Central Science · doi:10.1021/acscentsci.6c00422
Pang, Y., & Zhou, L. (2026) · The Analyst · doi:10.1039/d6an00706f
Guo, L., Zhu, X., Shi, Z., Lam, T. K. Y., Wang, J., Dong, J., & Cai, Z. (2026) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2026.119132
Self-citation
Metadata
- Authors
- Guo, L., Zhu, J., Wang, K., Cheng, K.-K., Xu, J., Dong, L., Xu, X., Chen, C., Shah, M., Peng, Z., Wang, J., Cai, Z., & Dong, J.
- Affiliations
- Xiamen University (CN)
- Shanxi University (CN)
- University of Technology Malaysia (MY)
- Xiamen University Malaysia (MY)
- The University of Sydney (AU)
- Fujian Medical University (CN)
- Second Military Medical University (CN)
- Hong Kong Baptist University (HK)
- Corresponding author
- Dong, Jiyang
- ORCID
- Venue
- Analytical Chemistry
- Publisher
- American Chemical Society (ACS)
- Published
- 2023-06-09
- Volume
- 95
- Issue
- 25
- Pages
- 9714-9721
- ISSN
- 0003-2700 (ISSN-L)
- 1520-6882
- OpenAlex
- W4380202397
- Cited by
- 36
- References
- 32
- Citations by year
- 2026: 14 · 2025: 9 · 2024: 13
- FWCI
- 3.30
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Licence
- Locations
- Analytical Chemistry (publishedVersion)
- ChemRxiv (acceptedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Funders
- National Key Research and Development Program of China (2017YFC1600505, 2017YFE0191000)
- Ministry of Higher Education, Malaysia (FRGS/1/2020/WAB13/UTM/02/1)
- Natural Science Foundation of Fujian Province (2022Y0003)
- National Natural Science Foundation of China (81871445)
- Topics
- Physical Sciences › Chemistry › Spectroscopy › Mass Spectrometry Techniques and Applications
- Physical Sciences › Engineering › Media Technology › Advanced Image Fusion Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Keywords
- mass spectrometry imaging, multimodal image fusion, spatial resolution enhancement, high-resolution reconstruction, H&E staining, multi-task optimization, image registration, spatial transcriptomics
- MeSH terms
- Image Processing, Computer-Assisted, Microscopy, Mass Spectrometry
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.