Automatic Tissue Detection for Mass Spectrometry Imaging
Journal of the American Society for Mass Spectrometry · 2026
DOI: 10.1021/jasms.5c00158 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Society for Mass Spectrometry, 2026. Verfasst von James Denholm und 17 weiteren Autor:innen. Beteiligte Einrichtung: Integrated Bioanlaysis, Clinical Pharmacology and Safety Sciences (CPSS), AstraZeneca R&D, Cambridge CB4 0WG, U.K. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Mass Spectrometry. Die Arbeit nennt 63 Literaturangaben.
Abstract (Originalsprache)
Mass spectrometry imaging is a powerful technique which maps the spatial distribution of thousands of biomolecules across tissue sections. The clear delineation of tissue is an important preceding analysis step typically requiring manual intervention. We present an end-to-end method for the automatic detection of tissue in mass spectrometry images (MSIs) using same-tissue-section pairs MSIs and histological images. First, the histological tissue masks were annotated using QuPath. Second, manually acquired landmarks were used to fit to affine transforms and map the tissue masks into the MSI space. Third, we proposed metabolite-independent representations of MSIs─based on total-ion-current, root-mean-square and Shannon-entropy images─to fit a tissue-detection model. Finally, a convolutional neural network was trained to detect tissue using cross-validation in a set of 68 images featuring a variety of tissue types, organisms and spatial resolutions. Our model achieved a cross-validation accuracy, precision, recall, and Sørensen-Dice coefficient of 0.953 ± 0.030, 0.939 ± 0.047, 0.923 ± 0.056, and 0.930 ± 0.041, respectively. Using unseen test data from two different studies, our model obtained an accuracy, precision, recall, and Sørensen-Dice coefficient of 0.945 ± 0.007, 0.965 ± 0.009, 0.915 ± 0.027, and 0.935 ± 0.011, respectively.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Integrated Bioanlaysis, Clinical Pharmacology and Safety Sciences (CPSS), AstraZeneca R&D, Cambridge CB4 0WG, U.K.
- Department of Radiology, University of Cambridge School of Clinical Medicine, Cambridge Biomedical Campus, Cambridge CB2 0SP, U.K.
- Cambridge Stem Cell Institute, Jeffrey Cheah Biomedical Centre, University of Cambridge, Cambridge CB2 0AW, U.K.
- Pathology, Clinical Pharmacology and Safety Sciences (CPSS), AstraZeneca R&D, Cambridge CB4 0WG, U.K.
- Bioscience, Early Oncology, Oncology R&D, AstraZeneca, Cambridge CB4 0WG, U.K.
ORCID-Profile: James Denholm, Lucy E Flint, Andreas Dannhorn, Stephanie Ling
Zitieren
APA
Denholm, J., Flint, L. E., Richings, J., Yousefi, F., Williams, E. C., Hamidinekoo, A., Glynn, R., Birtles, D., Hagos, Y. B., Sushentsev, N., Horvat Menih, I., Dannhorn, A., Ling, S., Hamm, G., Hulme, H. E., Barry, S. T., Gallagher, F. A., & Goodwin, R. J. A. (2026). Automatic Tissue Detection for Mass Spectrometry Imaging. Journal of the American Society for Mass Spectrometry. https://doi.org/10.1021/jasms.5c00158
Vancouver
Denholm J, Flint LE, Richings J, Yousefi F, Williams EC, Hamidinekoo A, et al. Automatic Tissue Detection for Mass Spectrometry Imaging. Journal of the American Society for Mass Spectrometry. 2026. doi:10.1021/jasms.5c00158
BibTeX
@article{Denholm2026,
author = {Denholm, James and Flint, Lucy E and Richings, Jack and Yousefi, Fariba and Williams, Eleanor C and Hamidinekoo, Azam and Glynn, Rachel and Birtles, Daniel and Hagos, Yeman Brhane and Sushentsev, Nikita and Horvat Menih, Ines and Dannhorn, Andreas and Ling, Stephanie and Hamm, Gregory and Hulme, Heather E and Barry, Simon T and Gallagher, Ferdia A and Goodwin, Richard J A},
title = {Automatic Tissue Detection for Mass Spectrometry Imaging},
journal = {Journal of the American Society for Mass Spectrometry},
year = {2026},
doi = {10.1021/jasms.5c00158}
}
EUVIMED