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

Search research articles

Related Experiment Video

Updated: Sep 29, 2025

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

Automatic Cardiac Structure Contouring for Small Datasets with Cascaded Deep Learning Models.

L B van den Oever^1,2, D S Spoor³, A P G Crijns³

¹Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, Hanzeplein 1, 9713GZ, Groningen, The Netherlands. l.b.van.den.oever@umcg.nl.

Journal of Medical Systems

|March 26, 2022

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

The added value of 3.0 T quantitative multivoxel proton <sup>1</sup>H-MR spectroscopy in the diagnostic work-up of breast lesions.

European journal of radiology·2026

Same author

Nutritional prehabilitation in head and neck cancer patients (PreHead) - A randomized controlled trial study protocol.

PloS one·2026

Same author

Prevalence of cardiac dysfunction and longitudinal changes in cardiac function after breast cancer treatment with chemotherapy with/without radiation therapy compared with controls.

Breast (Edinburgh, Scotland)·2026

Same author

A multi-toxicity deep learning approach for normal tissue complication probability modelling in head and neck cancer patients receiving radiotherapy.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2026

Same author

Corrigendum to "Regional differences in predictive biomarker testing rates for patients with metastatic NSCLC in the Netherlands" [Eur J Cancer 205 (2024)114125].

European journal of cancer (Oxford, England : 1990)·2026

Same author

Predicting acute coronary events after breast cancer radiotherapy: Integrating baseline cardiovascular risk, systemic therapy, and cardiac radiation dose in the MEDIRAD BRACE study.

European journal of cancer (Oxford, England : 1990)·2025

Same journal

Predicting the Predictor: Unresolved Validity Threats in LLM-Based ASA Classification.

Journal of medical systems·2026

Same journal

Development and Internal Validation of a Vectorcardiography-Augmented Model for 12-Month Major Adverse Cardiovascular Events in Chronic Heart Failure.

Journal of medical systems·2026

Same journal

Development and Validation of an Automated Acute Kidney Injury E-Alert System Integrated with Clinical Decision Support for Hospitalized Patients.

Journal of medical systems·2026

Same journal

Calibration of Self-Reported Confidence and Accuracy of Large Language Models in Medical Question Answering.

Journal of medical systems·2026

Same journal

Throughput Benchmarking and Throughput Variance Analysis to Evaluate the Efficiency of an Outpatient Endoscopy Unit.

Journal of medical systems·2026

Same journal

MTA-Swin: A Multi-Token Attention Swin Transformer for Brain Tumor Classification with Leakage-Free MRI Benchmarking.

Journal of medical systems·2026

See all related articles

This summary is machine-generated.

This study introduces an automated cardiac structure segmentation pipeline using deep learning for radiation therapy planning. The pipeline accurately segments cardiac structures on low-dose CT scans, even with small datasets, improving efficiency.

Area of Science:

Medical Imaging
Radiotherapy
Artificial Intelligence

Background:

Manual cardiac structure contouring is time-consuming and tedious for radiotherapy planning.
Accurate segmentation is crucial for dose toxicity planning.

Purpose of the Study:

To develop an automatic cardiac structure segmentation pipeline using deep learning for low-dose, non-contrast planning CT scans.
To validate the pipeline's performance on small datasets.

Main Methods:

A two-stage deep learning pipeline utilizing InceptionResNetV2 was developed.
Segmentation models were trained on axial, coronal, and sagittal images and combined for final prediction.
Performance was evaluated using Dice Similarity Coefficient (DC) and 95% Hausdorff Distance (95% HD).

Keywords:

Artificial Intelligence Heart Structure segmentation X-ray computed tomography

More Related Videos

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: Sep 29, 2025

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

Main Results:

The pipeline achieved high accuracy, with median DC values of 0.96 for the whole heart and 0.88-0.92 for ventricles and atria.
Median 95% HD values ranged from 1.86 to 6.46.
Volume differences were within acceptable ranges (-4% to +5% for whole heart and ventricles).

Conclusions:

The automatic contouring pipeline demonstrates robust performance for whole heart and ventricle segmentation.
Deep learning-based automatic contouring is a viable solution for centers with limited datasets.