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

Imaging Biological Samples with Optical Microscopy01:18

Imaging Biological Samples with Optical Microscopy

12.3K
Optical microscopy uses optic principles to provide detailed images of samples. Antonie van Leeuwenhoek designed the first compound optical microscope in the 17th century to visualize blood cells, bacteria, and yeast cells. In 1830, Joseph Jackson Lister created an essentially modern light microscope. The 20th century saw the development of microscopes with enhanced magnification and resolution.
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...
12.3K

You might also read

Related Articles

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

Sort by
Same author

Clinical outcomes of intravascular imaging-guided versus angiography-guided drug-coated balloon angioplasty for de novo coronary lesions.

International journal of cardiology·2026
Same author

Drug-coated balloon versus drug-eluting stent for isolated ostial side-branch bifurcation (Medina 0.0.1) lesions.

International journal of cardiology·2026
Same author

Voice features and deep learning models for identifying acute decompensated heart failure.

Digital health·2026
Same author

Lesion-Specific Prediction of Segmental Fractional Flow Reserve Using Deep Learning and Optical Coherence Tomography-Derived Features.

Circulation journal : official journal of the Japanese Circulation Society·2026
Same author

Prognostic significance of high Lipoprotein(a) levels in patients with coronary artery spasm.

Heart and vessels·2026
Same author

Label-free diagnosis across the thyroid nodule pathology spectrum using deep learning-enabled optical coherence tomography.

Biomedical optics express·2026

Related Experiment Video

Updated: Apr 14, 2026

Integrated Photoacoustic Ophthalmoscopy and Spectral-domain Optical Coherence Tomography
11:21

Integrated Photoacoustic Ophthalmoscopy and Spectral-domain Optical Coherence Tomography

Published on: January 15, 2013

12.1K

Automated lipid detection in spectroscopic optical coherence tomography using a weakly supervised deep learning

Jin Hwan Hwang1, Woojin Lee1, Jin Hyuk Kim2

  • 1Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea.

Biomedical Optics Express
|April 13, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a new deep learning method using spectroscopic OCT to automatically detect and map lipids in arteries. This advance improves coronary vulnerability assessment by enhancing lipid detection accuracy.

More Related Videos

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies
06:16

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

3.2K
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

3.7K

Related Experiment Videos

Last Updated: Apr 14, 2026

Integrated Photoacoustic Ophthalmoscopy and Spectral-domain Optical Coherence Tomography
11:21

Integrated Photoacoustic Ophthalmoscopy and Spectral-domain Optical Coherence Tomography

Published on: January 15, 2013

12.1K
Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies
06:16

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

3.2K
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

3.7K

Area of Science:

  • Cardiovascular Imaging
  • Artificial Intelligence in Medicine
  • Biomedical Optics

Background:

  • Accurate lipid distribution identification is crucial for assessing coronary artery vulnerability.
  • Conventional optical coherence tomography (OCT) lacks the compositional specificity needed for detailed lipid analysis.
  • Spectroscopic OCT (S-OCT) expands OCT's capabilities by incorporating spectral information for tissue characterization.

Purpose of the Study:

  • To develop a weakly supervised deep learning framework for automated lipid detection and localization using S-OCT data.
  • To minimize the requirement for extensive manual annotation in lipid mapping.
  • To enable composition-aware tissue characterization without hardware modifications.

Main Methods:

  • A ResNet-34 deep learning network with convolutional block attention modules (CBAMs) was trained using frame-level binary labels for lipid presence.
  • Gradient-weighted class activation mapping (Grad-CAM) was employed to generate interpretable activation maps highlighting lipid-rich areas.
  • Model performance was validated against Oil Red O-stained histology from rabbit aortas.

Main Results:

  • The developed framework accurately localized lipid regions, showing strong spatial correlation with histological findings.
  • An arc-level overlap agreement of 83.9% was achieved between the model's predictions and histology.
  • Spectroscopic information significantly enhanced lipid detection compared to conventional OCT imaging.

Conclusions:

  • The proposed weakly supervised deep learning framework demonstrates the feasibility of using S-OCT for automated lipid detection in intravascular imaging.
  • This approach facilitates efficient lipid screening and provides spatial interpretation for plaque characterization.
  • The framework offers a scalable foundation for assessing lipid burden and risk stratification in coronary artery disease.