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 Video

Updated: Dec 26, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

Adaptive deep learning for head and neck cancer detection using hyperspectral imaging.

Ling Ma1,2, Guolan Lu1, Dongsheng Wang3

  • 11Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA 30322 USA.

Visual Computing for Industry, Biomedicine, and Art
|March 20, 2020
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

High-speed optical tracking and augmented reality platform for image-guided interventions.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

Enhancing 1p/19q Classification in Brain Gliomas Using IDH Status: A Deep Learning Study.

AJNR. American journal of neuroradiology·2026
Same author

Polarized hyperspectral and polarized light microscopic imaging for enhanced visualization of white blood cells.

Journal of biomedical optics·2026
Same author

Medical hyperspectral imaging: an updated review of technology advancements and biomedical applications.

Journal of biomedical optics·2026
Same author

Development and validation of a high-resolution hyperspectral imaging system for the retina.

Journal of biomedical optics·2026
Same author

A spatial-spectral vision transformer model for head and neck cancer detection with hyperspectral, RGB, and synthesized RGB histologic images.

Proceedings of SPIE--the International Society for Optical Engineering·2026

This study introduces an adaptive deep learning method for precise cancer detection using hyperspectral imaging. The technique accurately identifies tumor boundaries, improving surgical resection outcomes.

Area of Science:

  • Medical imaging
  • Artificial intelligence
  • Oncology

Background:

  • Accurate detection of tumor margins during surgery is critical for complete resection.
  • Hyperspectral imaging (HSI) offers rich spectral information for tissue characterization.
  • Existing methods may struggle with indistinct or irregular tumor boundaries.

Purpose of the Study:

  • To develop a novel adaptive deep learning method for improved cancer detection using HSI.
  • To differentiate between tumor and benign tissue adaptively for enhanced surgical guidance.
  • To evaluate the performance of the proposed method in an animal model.

Main Methods:

  • An auto-encoder network was trained on HSI data to extract deep features.
  • A pixel-wise prediction of cancerous and benign tissue was generated.
Keywords:
Adaptive learningDeep learningHyperspectral imagingNoninvasive cancer detection

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K

Related Experiment Videos

Last Updated: Dec 26, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K
  • Misclassified pixels were reclassified using adaptive weights, and the network was retrained.
  • The adaptive learning focused on improving the identification of challenging tissue types.

    • Main Results:

    • The adaptive deep learning method accurately highlighted tumor regions in HSI.
    • The method achieved a sensitivity of 92.32% and a specificity of 91.31% in animal experiments.
    • The adaptive approach demonstrated improved detection performance for indistinct tumor margins.

    Conclusions:

    • The developed adaptive deep learning method shows high accuracy in detecting tumor boundaries on HSI.
    • This non-invasive tool has significant potential for improving intraoperative tumor detection.
    • The adaptive learning strategy enhances the ability to distinguish cancerous from benign tissues.