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

Atherosclerosis I: Introduction01:30

Atherosclerosis I: Introduction

904
Atherosclerosis is a progressive disorder characterized by the buildup of plaques on the arterial inner wall, causing them to narrow and harden over time. These plaques comprise lipids, calcium, blood components, carbohydrates, and fibrous tissue. The process primarily affects the intima of large and medium-sized arteries, reducing blood flow in any artery.Etiology and risk factorsThe cause of atherosclerosis is multifactorial, involving a complex interplay among endothelial injury, lipid...
904

You might also read

Related Articles

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

Sort by
Same author

Poly-D,L-Lactide-co-Glycolide and Sodium Enoxaparin Composition - an Advanced Coating for Vascular Stents: Biocompatibility and Efficiency Assessment of Stent-Grafts in an Experiment on Large Animals.

Sovremennye tekhnologii v meditsine·2026
Same author

National Results of Revascularization for Acute Coronary Syndrome in 2023.

Kardiologiia·2024
Same author

Anti-adhesive Properties of Epoxy-Treated Xenopericardium Modified with Polyvinyl Alcohol: <i>in vitro</i> Study of Leukocyte Adhesion in the Pulsatile Flow Model.

Sovremennye tekhnologii v meditsine·2024
Same author

New Tissue-Engineered Vascular Matrix Based on Regenerated Silk Fibroin: <i>in vitro</i> Study.

Sovremennye tekhnologii v meditsine·2024
Same author

Randomized Clinical Trial of Hybrid vs. Surgical vs. Percutaneous Multivessel Coronary Revascularization: 5‑year Follow-up of HREVS Trial.

Kardiologiia·2023
Same author

Effect of the "door-to-balloon" time on the results of treatment of patients with ST-segment elevation myocardial infarction, depending on the duration of the pre-hospital delay.

Kardiologiia·2023

Related Experiment Video

Updated: Jan 14, 2026

Three-Dimensional Imaging of Aortic Tissues in Atherosclerosis
09:55

Three-Dimensional Imaging of Aortic Tissues in Atherosclerosis

Published on: October 25, 2024

1.4K

Segmentation of Structural Components of Atherosclerotic Plaques on OCT Images Using Deep Machine Learning.

V V Laptev1, V V Danilov2, E A Ovcharenko1

  • 1Research Institute of Complex Issues of Cardiovascular Diseases, Kemerovo.

Kardiologiia
|October 23, 2025
PubMed
Summary

This study developed an optimal method for segmenting atherosclerotic plaque components in optical coherence tomography (OCT) images using an ensemble of deep learning models. The weighted ensemble significantly improved segmentation accuracy for key plaque features, aiding cardiovascular disease diagnosis.

More Related Videos

A Method to Study the Correlation Between Local Collagen Structure and Mechanical Properties of Atherosclerotic Plaque Fibrous Tissue
13:45

A Method to Study the Correlation Between Local Collagen Structure and Mechanical Properties of Atherosclerotic Plaque Fibrous Tissue

Published on: November 11, 2022

2.5K
Imaging and Analysis of Oil Red O-Stained Whole Aorta Lesions in an Aneurysm Hyperlipidemia Mouse Model
07:57

Imaging and Analysis of Oil Red O-Stained Whole Aorta Lesions in an Aneurysm Hyperlipidemia Mouse Model

Published on: May 2, 2022

15.1K

Related Experiment Videos

Last Updated: Jan 14, 2026

Three-Dimensional Imaging of Aortic Tissues in Atherosclerosis
09:55

Three-Dimensional Imaging of Aortic Tissues in Atherosclerosis

Published on: October 25, 2024

1.4K
A Method to Study the Correlation Between Local Collagen Structure and Mechanical Properties of Atherosclerotic Plaque Fibrous Tissue
13:45

A Method to Study the Correlation Between Local Collagen Structure and Mechanical Properties of Atherosclerotic Plaque Fibrous Tissue

Published on: November 11, 2022

2.5K
Imaging and Analysis of Oil Red O-Stained Whole Aorta Lesions in an Aneurysm Hyperlipidemia Mouse Model
07:57

Imaging and Analysis of Oil Red O-Stained Whole Aorta Lesions in an Aneurysm Hyperlipidemia Mouse Model

Published on: May 2, 2022

15.1K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Cardiovascular Research

Background:

  • Atherosclerotic plaque segmentation in OCT images is crucial for cardiovascular disease diagnosis and treatment.
  • Accurate segmentation of plaque components like lumen, fibrous cap, lipid core, and microvessels remains challenging.
  • Deep learning models offer potential for automated and accurate segmentation of complex biological structures.

Purpose of the Study:

  • To develop an optimal automated method for segmenting atherosclerotic plaque structural components in OCT images.
  • To compare the performance of nine artificial neural network architectures for this segmentation task.
  • To create a weighted ensemble of deep learning models to enhance overall segmentation accuracy.

Main Methods:

  • Utilized a multidisciplinary OCT dataset from 103 patients with pixel-level annotations for lumen, fibrous cap, lipid core, and microvessels.
  • Implemented and compared nine deep learning models, including U-Net and DeepLabV3, for segmentation.
  • Employed Bayesian optimization for hyperparameter tuning and assessed performance using the Dice Similarity Coefficient (DSC).

Main Results:

  • Achieved high DSC for vascular lumen (0.987) and moderate DSC for fibrous cap (0.736) and lipid core (0.751).
  • Microvessel segmentation showed lower accuracy (DSC: 0.61), indicating segmentation challenges.
  • A weighted ensemble model achieved an average DSC of 88.2%, significantly outperforming individual models and improving overall accuracy.

Conclusions:

  • The proposed strategy of using specialized models and a weighted ensemble is effective for atherosclerotic plaque segmentation in OCT images.
  • This approach successfully addressed the challenge of uneven class representation and morphological complexity.
  • The findings can contribute to developing decision support systems for improved cardiovascular disease diagnosis and treatment.