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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

A Triple-Perception Adaptive Network for In Vivo Organ Recognition Using Diffuse Reflectance Hyperspectral Imaging.

Analytical chemistry·2026
Same author

Correction to "One for All, All for One: A Unified Framework for Free-Energy Calculations".

Accounts of chemical research·2026
Same author

Wavelet-Enhanced Data-Driven Collective Variables for Efficient Sampling of Protein Folding Landscapes.

Journal of chemical information and modeling·2026
Same author

Proline-mediated conformational rigidity governs the ice-binding behavior of antifreeze glycopeptides.

Physical chemistry chemical physics : PCCP·2026
Same author

Unveiling hidden intermediate states in protein folding with AI-based conditional transition clustering.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

One for All, All for One: A Unified Framework for Free-Energy Calculations.

Accounts of chemical research·2025
Same journal

Machine Learning-Assisted Nanopore for Enhanced Fingerprinting Analysis of Functional Glycans.

Analytical chemistry·2026
Same journal

Correction to "Maleylpyruvic Acid-Inducible Gene Expression System and Its Application for the Development of Gentisic Acid Biosensor".

Analytical chemistry·2026
Same journal

Computer-Aided Rational Hapten Design for Broad-Spectrum Monoclonal Antibody Development against Anthraquinones and Its Application in Lateral Flow Immunoassay.

Analytical chemistry·2026
Same journal

One-Step Chemoenzymatic Labeling and Oxime-Reversible Enrichment for O-GlcNAcylation Profiling under Oxidative Stress.

Analytical chemistry·2026
Same journal

Acid/NIR Dual-Responsive Nanoplatform with AND Logic-Gated Controlled Nitric Oxide Release for Companion Theranostics of Tumors.

Analytical chemistry·2026
Same journal

Multicharged Foldable Plasma Membrane Probes for Precise Cancer Cell Discrimination and Fluorescence-Guided Surgery.

Analytical chemistry·2026
See all related articles

Related Experiment Video

Updated: Jun 4, 2025

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
00:07

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.0K

Unmixing Autoencoder for Image Reconstruction from Hyperspectral Data.

Xuyang Liu1, Chaoshu Duan1, Wensheng Cai1

  • 1Research Center for Analytical Sciences, Tianjin Key Laboratory of Biosensing and Molecular Recognition, State Key Laboratory of Medicinal Chemical Biology, College of Chemistry, Nankai University, Tianjin 300071, China.

Analytical Chemistry
|December 18, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces an unmixing autoencoder (UAE) to effectively separate mixed spectra in hyperspectral imaging (HSI). The UAE successfully identifies chemical components, enabling applications like revealing hidden handwriting and mapping molecular distributions.

More Related Videos

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K
Measurement of 3-Dimensional cAMP Distributions in Living Cells using 4-Dimensional x, y, z, and λ Hyperspectral FRET Imaging and Analysis
08:22

Measurement of 3-Dimensional cAMP Distributions in Living Cells using 4-Dimensional x, y, z, and λ Hyperspectral FRET Imaging and Analysis

Published on: October 27, 2020

3.8K

Related Experiment Videos

Last Updated: Jun 4, 2025

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
00:07

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.0K
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K
Measurement of 3-Dimensional cAMP Distributions in Living Cells using 4-Dimensional x, y, z, and λ Hyperspectral FRET Imaging and Analysis
08:22

Measurement of 3-Dimensional cAMP Distributions in Living Cells using 4-Dimensional x, y, z, and λ Hyperspectral FRET Imaging and Analysis

Published on: October 27, 2020

3.8K

Area of Science:

  • Spectroscopy
  • Chemometrics
  • Image Analysis

Background:

  • Hyperspectral imaging (HSI) spectra are often mixtures, limiting univariate analysis.
  • Existing feature extraction methods lack interpretable chemical meaning.
  • Advanced methods are needed for accurate spectral component separation in HSI.

Purpose of the Study:

  • To develop and validate an unmixing autoencoder (UAE) for separating mixed spectra in HSI.
  • To enable the interpretation of chemical components within complex HSI data.
  • To demonstrate the UAE's utility in diverse HSI applications.

Main Methods:

  • An unmixing autoencoder (UAE) model was designed, comprising an encoder for spectral compression and a fully connected layer for reconstruction.
  • The model integrates reconstruction loss and sparse regularization to encode spectral profiles and component weights.
  • Performance was evaluated using simulated and experimental HSI datasets from near-infrared (NIR), Raman, and stimulated Raman scattering (SRS) imaging.

Main Results:

  • The UAE successfully separated mixed spectral components across various HSI datasets.
  • Hidden handwriting was revealed in NIR diffuse reflectance spectroscopy images.
  • Distinct images of lipids, proteins, and nucleic acids were reconstructed from Raman and SRS data.

Conclusions:

  • The unmixing autoencoder (UAE) provides an effective approach for spectral separation in complex HSI data.
  • The method allows for the extraction of chemically meaningful information from HSI.
  • UAE demonstrates significant potential for advancing HSI applications in various scientific fields.