Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Computed Tomography

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

You might also read

Related Articles

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

Sort by

Same author

Reply to I Jannasz et al: DIETFITS cohort, modeling, and molecules.

The American journal of clinical nutrition·2026

Same author

Sex and gender classification in clinical decision-support tools: a cross-sectional review of tools on MDCalc.

Biology of sex differences·2026

Same author

Antithetic Sampling Enhanced Probabilistic Diffusion for Denoising Cardiac Time Series.

IEEE journal of biomedical and health informatics·2026

Same author

Sustained Reduction in Cardiopulmonary Fitness in Long COVID: A Report from the RECOVER-adult Cohort Study.

JACC. Advances·2026

Same author

Impact of guideline definitions on right ventricular diameter in echocardiography: an automated analysis in controls and patients with pulmonary hypertension.

Echo research and practice·2026

Same author

International practices and variability in right heart echocardiography: results from the RVNet(Work) international survey.

Echo research and practice·2026

Same journal

Phase-specific turbulence index derived from vector flow imaging for identifying intraplaque neovascularization in carotid plaques.

Frontiers in cardiovascular medicine·2026

Same journal

The association of remnant cholesterol inflammatory index with the risk of major adverse cardiovascular events in patients with angina undergoing percutaneous coronary intervention: a retrospective study.

Frontiers in cardiovascular medicine·2026

Same journal

Psychological stress and diastolic blood pressure in cardiology outpatients: a multicenter cross-sectional study (from the ABC2X-2026 study).

Frontiers in cardiovascular medicine·2026

Same journal

Long-term efficacy and renal safety of SGLT2 inhibitors in patients with heart failure and advanced chronic kidney disease (stage 4): a propensity score-matched retrospective cohort study.

Frontiers in cardiovascular medicine·2026

Same journal

Multimodal echocardiographic techniques in the diagnosis of cardiac tumors: applications and recent advances.

Frontiers in cardiovascular medicine·2026

Same journal

Association of the apolipoproteins with retinal arteriosclerosis in a health examination population.

Frontiers in cardiovascular medicine·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 13, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Segmenting computed tomograms for cardiac ablation using machine learning leveraged by domain knowledge encoding.

Ruibin Feng¹, Brototo Deb¹, Prasanth Ganesan¹

¹Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, United States.

Frontiers in Cardiovascular Medicine

|October 18, 2023

Summary

This summary is machine-generated.

This study introduces a novel method combining machine learning (ML) with cardiac geometry knowledge to improve computed tomography (CT) segmentation for cardiac procedures like atrial fibrillation (AF) ablation. The approach significantly reduces training data needs and segmentation time while maintaining high accuracy.

Keywords:

ablation atrial fibrillation cardiac CT segmentation domain knowledge machine learning mathematical modeling

More Related Videos

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

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

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

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jul 13, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

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

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

Published on: November 30, 2022

Area of Science:

Medical Imaging and Machine Learning
Cardiovascular Disease Management
Computational Anatomy

Background:

Accurate segmentation of cardiac computed tomography (CT) is crucial for clinical procedures such as personalized cardiac ablation for arrhythmias.
Current machine learning (ML) approaches for CT segmentation require extensive labeled training data, which is often difficult to acquire.
A need exists for methods that reduce data dependency while maintaining segmentation accuracy for clinical applications.

Purpose of the Study:

To develop and validate a novel approach combining ML with domain knowledge of cardiac geometry for CT segmentation.
To reduce the requirement for large training datasets in ML-based cardiac CT segmentation.
To assess the accuracy and efficiency of the proposed method in independent datasets and a prospective clinical study for atrial fibrillation (AF) ablation.

Main Methods:

A mathematical model representing atrial anatomy using geometric shapes was developed ('virtual dissection').
This model was used to train an ML algorithm on a small dataset (N=6 digital hearts).
The ML model was subsequently tested on independent datasets (N=160) and in a prospective AF ablation study (N=42).

Main Results:

The 'virtual dissection' model achieved high segmentation accuracy in independent test cohorts, with Dice scores of 96.7% internally and 93.5% externally.
Expert agreement was strong (r=0.99, p<0.0001).
In a prospective study, the method reduced segmentation time by 85% (2.3 min vs. 15.0 min) with accuracy comparable to expert segmentation (93.9% vs. 94.4%).

Conclusions:

Integrating cardiac geometry into ML models significantly accelerates CT segmentation training, overcoming the need for large datasets.
The combined approach maintains high accuracy in independent testing and prospective clinical use.
This method holds potential for broad applications in medical image analysis by combining ML with domain-specific knowledge.