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 29, 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

Automatic Segmentation of Multiple Organs on 3D CT Images by Using Deep Learning Approaches.

Xiangrong Zhou1

  • 1Gifu University, Gifu-shi, Gifu, Japan. zxr@gifu-u.ac.jp.

Advances in Experimental Medicine and Biology
|February 8, 2020
PubMed
Summary

Deep learning models, specifically 3D and 2D convolutional neural networks (CNNs), significantly improve automatic organ segmentation on 3D CT images. These advanced deep learning techniques outperform traditional methods, enhancing accuracy for medical applications.

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

Benzophenone-2 disrupts craniofacial cartilage development via esr2a-Dependent inhibition of endothelin signaling in zebrafish larvae.

Environmental research·2026
Same author

Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with a Structured Output (SLSO) Framework.

Diagnostics (Basel, Switzerland)·2026
Same author

Environmentally relevant lanthanum chloride exposure induces hepatic steatosis in zebrafish larvae via PPARα-dependent ApoB suppression.

Communications biology·2026
Same author

[Site-specific Segmentation of Skeletal Muscles in Body CT Images via Comprehensive Muscular Consideration].

Nihon Hoshasen Gijutsu Gakkai zasshi·2026
Same author

Mitochondrial NADH dehydrogenase subunit Ⅳ supports CncC-mediated detoxification genes to confer dimefluthrin resistance in Aedes albopictus.

Journal of insect physiology·2026
Same author

Detection and dual-label classification of tooth number and condition in dental panoramic radiographs including deciduous teeth.

Radiological physics and technology·2025

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Computed tomography (CT) images are crucial for visualizing 3D human anatomy in clinical medicine.
  • Accurate segmentation of multiple organs in CT scans is fundamental for computer-aided diagnosis, surgery, and radiation therapy.
  • Conventional image processing techniques have limitations in achieving precise organ segmentation.

Purpose of the Study:

  • To introduce and evaluate novel deep learning techniques for automatic multiple organ segmentation on 3D CT images.
  • To compare the performance of 2D and 3D deep convolutional neural networks (CNNs) against a conventional probabilistic atlas algorithm.
  • To demonstrate the effectiveness of deep learning for enhancing precision and personalized medicine.

Main Methods:

Keywords:
2D-FCNCNNCT imageDeep learningImage segmentationMajority votingMultiple organsPatch-based training

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

704

Related Experiment Videos

Last Updated: Dec 29, 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
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

704
  • Development and application of 2D and 3D deep CNNs for organ segmentation.
  • Utilizing a dataset of 240 CT scans for training and validation.
  • Comparison with a baseline probabilistic atlas algorithm using the ratio of intersection over union (IoU) metric.
  • Segmentation of up to 17 organ types per CT scan.

Main Results:

  • The proposed 3D deep CNN achieved a mean IoU of 79%, while the 2D deep CNN achieved 67% across 17 organ types.
  • Deep learning approaches demonstrated superior accuracy and robustness compared to the conventional probabilistic atlas method.
  • IoU was used as the criterion for validating segmentation performance against human annotations.

Conclusions:

  • Deep learning, particularly 3D CNNs, offers a powerful and effective approach for automated multiple organ segmentation in 3D CT images.
  • These methods provide significant improvements over traditional techniques, paving the way for more precise medical interventions.
  • The study validates the utility of deep learning in advancing computer-aided diagnosis and treatment planning.