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: Dec 27, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

3D Cascaded Convolutional Networks for Multi-vertebrae Segmentation.

Liu Xia¹, Liu Xiao¹, Gan Quan¹

¹School of Automation, Harbin University of Science and Technology, Harbin 150001, China.

Current Medical Imaging

|March 6, 2020

Summary

This summary is machine-generated.

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

DuoMod-Net: Logarithmic balancing and geometric refinement for imbalanced semi-supervised medical image segmentation.

Patterns (New York, N.Y.)·2026

Same author

18F-FDG Uptake Outperforms 68Ga-FAPI-04 in Papillary Renal Neoplasm With Reverse Polarity.

Clinical nuclear medicine·2026

Same author

The predictive value of early systemic inflammatory response index (SIRI), serum β<sub>2</sub>-microglobulin, and procalcitonin for acute kidney injury induced by wasp stings.

Renal failure·2026

Same author

Colloidal transport controlled by surface anchoring in active nematic fluids.

Soft matter·2026

Same author

Factors influencing treatment duration of oral propranolol in infantile hemangioma: a five-year retrospective analysis.

Frontiers in pediatrics·2026

Same author

Compound sulfamethoxazole for pediatric pertussis: a retrospective cohort study in a region with high macrolide resistance.

Frontiers in pediatrics·2025

Same journal

A simple method for locating and calibrating the keyhole for the retrosigmoid approach using CT plain scans.

Current medical imaging·2026

Same journal

Multimodal Imaging of a Giant Ovarian Mature Cystic Teratoma Featuring the Floating Ball Sign: A Case Report.

Current medical imaging·2026

Same journal

Accurate Segmentation and Three-dimensional Reconstruction Algorithm of Spinal Cord Injury Lesions Based on Multimodal Magnetic Resonance Imaging.

Current medical imaging·2026

Same journal

A Comprehensive Review of Radiomics in Pulmonary Nodule Management: Clinical Applications and Standardization Dilemmas.

Current medical imaging·2026

Same journal

The Value of a Predictive Model Based on Multimodal Ultrasound Imaging Biomarkers Combined with Clinical Features in the Diagnosis of Thyroid Nodules.

Current medical imaging·2026

Same journal

The Prognostic and Mutational Characteristics of Multiple Early-stage Lung Cancers Manifesting as Subsolid Nodules.

Current medical imaging·2026

See all related articles

This study presents an automatic 3D vertebrae segmentation method for CT images, achieving 94.84% Dice similarity coefficient. This advanced technique enhances clinical applications through accurate vertebrae region identification.

Area of Science:

Medical Imaging
Computer Vision
Artificial Intelligence

Background:

Automatic vertebrae segmentation from computed tomography (CT) images is crucial for clinical applications.
Challenges include intricate vertebral appearance, variable anatomy, nearby structures, pathology, and vertebrae-rib connections.
Existing 3D automatic segmentation methods face difficulties.

Purpose of the Study:

To propose an automatic multi-vertebrae segmentation method specifically for spinal CT images.
To enhance the accuracy and efficiency of vertebrae segmentation in clinical settings.
To provide a foundation for subsequent 3D reconstruction and printing applications.

Main Methods:

Preprocessing using CLAHE-Threshold-Expansion to improve image quality and reduce data.

Keywords:

3D vertebra segmentation CNN CT Image FCN ribs spine.

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: Dec 27, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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

Utilizing a 3D coarse segmentation fully convolutional network (FCN).

Employing a cascaded finely segmentation convolutional neural network (CNN) for segmentation and classification.

Main Results:

The proposed method achieved a Dice similarity coefficient (DSC) of 94.84%.
This performance surpasses existing methods like V-net and 3D U-net on the same datasets.
Demonstrated superior accuracy in segmenting vertebrae regions compared to other approaches.

Conclusions:

The developed method offers significant advantages for automatic and accurate vertebrae segmentation in CT images.
The ease of acquiring spine CT images makes this model highly conducive to clinical practice.
Integration with 3D reconstruction and printing facilitates advanced treatment planning and application.