Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Matrix Factorization Techniques for Analysis of Imaging Mass Spectrometry Data.

Peter W Siy1, Richard A Moffitt2, R Mitchell Parry3

  • 1School of Electrical and Computer Engineering, Georgia Tech, Atlanta, GA 30332 USA ( petersiy@gatech.edu ).

Proceedings. IEEE International Symposium on Bioinformatics and Bioengineering
|April 11, 2017
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Monocular Markerless Motion Capture Enables Quantitative Assessment of Upper Extremity Reachable Workspace.

Sensors (Basel, Switzerland)·2026
Same author

Polygenic Stroke Risk and Autoimmune Disease: Associations and Clinical Modifiers.

IEEE transactions on bio-medical engineering·2026
Same author

LIPID MAPS: Powering discovery in lipidomics.

Science signaling·2026
Same author

Governing real-world health data as a public utility.

Science (New York, N.Y.)·2026
Same author

Multi-level Asymmetric Contrastive Learning for Medical Image Segmentation Pre-training.

IEEE journal of biomedical and health informatics·2026
Same author

BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers.

Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing·2026
This summary is machine-generated.

Automated analysis of imaging mass spectrometry data is crucial for extracting molecular information. Independent component analysis and non-negative matrix factorization show superior performance over principal component analysis for feature discovery.

Area of Science:

  • Biomedical imaging
  • Molecular imaging
  • Data analysis

Background:

  • Imaging mass spectrometry (IMS) provides molecular distribution data in 2D samples.
  • IMS generates large datasets, making manual analysis challenging.
  • Automated methods are needed to identify key spatial and spectral features in IMS data.

Purpose of the Study:

  • To explore and compare automated data analysis techniques for IMS.
  • To evaluate the effectiveness of Independent Component Analysis (ICA) and Non-negative Matrix Factorization (NMF) for feature discovery in IMS data.
  • To contrast ICA and NMF with Principal Component Analysis (PCA).

Main Methods:

  • Independent Component Analysis (ICA)
  • Non-negative Matrix Factorization (NMF)

Related Experiment Videos

  • Principal Component Analysis (PCA)
  • Application to a mouse cerebellum IMS dataset

    • Main Results:

    • ICA and NMF were investigated as tools for identifying underlying factors in IMS data.
    • These methods were compared and contrasted with PCA.
    • ICA and NMF demonstrated greater effectiveness than PCA for analyzing IMS data.

    Conclusions:

    • Automated analysis methods like ICA and NMF are essential for extracting meaningful information from complex IMS datasets.
    • ICA and NMF are more effective than PCA for identifying important spatial and spectral features in IMS.
    • These findings facilitate more efficient and comprehensive molecular distribution analysis in biological samples.