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

Computed Tomography01:10

Computed Tomography

6.4K
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...
6.4K

You might also read

Related Articles

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

Sort by
Same author

Burden and Forecast of Early-Onset Colorectal Cancer (1990-2038) in Five East Asian Populations: A Systematic Analysis Based on the GBD 2023 Study.

Cancer medicine·2026
Same author

A geometry aware framework enhances noninvasive mapping of whole human brain dynamics.

Nature biomedical engineering·2026
Same author

Elucidating temporal variations in non-volatile metabolites during black tea rolling process via metabolomics combined with multivariate statistical analysis.

Food chemistry·2026
Same author

17β-Estradiol alleviates cognitive deficits by modulating fear memory reconsolidation in a PTSD rat model.

Psychopharmacology·2026
Same author

Application of deep learning-clinical baseline feature fusion model to predict postoperative mortality in elderly patients with hip fracture: a multicenter study.

Frontiers in medicine·2026
Same author

Photoelectrochemical oxidation for biomass valorization: Upgrading biorefinery-derived feedstocks into value-added chemicals.

Bioresource technology·2026

Related Experiment Video

Updated: Sep 18, 2025

Semiautomated Longitudinal Microcomputed Tomography-based Quantitative Structural Analysis of a Nude Rat Osteoporosis-related Vertebral Fracture Model
07:12

Semiautomated Longitudinal Microcomputed Tomography-based Quantitative Structural Analysis of a Nude Rat Osteoporosis-related Vertebral Fracture Model

Published on: September 28, 2017

8.3K

Enabling Early Identification of Malignant Vertebral Compression Fractures Through 2.5D Convolutional Neural Network

Chengbin Huang1, Enli Li1, Jiasen Hu2

  • 1Department of Orthopaedics, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, Zhejiang Province, China.

Spine
|June 23, 2025
PubMed
Summary

This study developed a 2.5D convolutional neural network (CNN) model for non-invasive detection of malignant vertebral compression fractures (MVCFs). The CNN model significantly improved clinicians' ability to identify MVCFs, offering a promising alternative to invasive biopsies.

Keywords:
2.5D convolutional neural networkCTbiopsydeep learningmalignant vertebral compression fractures

More Related Videos

Author Spotlight: Improving Percutaneous Vertebroplasty Surgical Accuracy and Efficiency Through Advanced Puncture Techniques
09:29

Author Spotlight: Improving Percutaneous Vertebroplasty Surgical Accuracy and Efficiency Through Advanced Puncture Techniques

Published on: August 9, 2024

349
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K

Related Experiment Videos

Last Updated: Sep 18, 2025

Semiautomated Longitudinal Microcomputed Tomography-based Quantitative Structural Analysis of a Nude Rat Osteoporosis-related Vertebral Fracture Model
07:12

Semiautomated Longitudinal Microcomputed Tomography-based Quantitative Structural Analysis of a Nude Rat Osteoporosis-related Vertebral Fracture Model

Published on: September 28, 2017

8.3K
Author Spotlight: Improving Percutaneous Vertebroplasty Surgical Accuracy and Efficiency Through Advanced Puncture Techniques
09:29

Author Spotlight: Improving Percutaneous Vertebroplasty Surgical Accuracy and Efficiency Through Advanced Puncture Techniques

Published on: August 9, 2024

349
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Vertebral histopathological biopsy is the gold standard for differentiating osteoporotic and malignant vertebral compression fractures (VCFs).
  • The invasive nature and high cost of biopsy limit its widespread application, necessitating alternative diagnostic methods.
  • Early and accurate identification of malignant VCFs (MVCFs) is crucial for timely treatment and improved patient outcomes.

Purpose of the Study:

  • To introduce a novel 2.5D convolutional neural network (CNN) model utilizing CT imaging for the early detection of MVCFs.
  • To develop and validate a CNN model as a non-invasive tool to reduce reliance on traditional biopsy methods.
  • To assess the performance of the 2.5D CNN model in differentiating MVCFs from osteoporotic VCFs (OVCFs).

Main Methods:

  • Retrospective analysis of clinical, imaging, and pathological data from patients undergoing vertebral augmentation and biopsy.
  • Development and comparison of 2D, 2.5D, and 3D CNN models based on vertebral CT images.
  • Validation of the 2.5D CNN model through external cohort testing and reader studies involving clinicians of varying experience levels.

Main Results:

  • The 2.5D CNN model demonstrated superior performance in identifying MVCF patients compared to 2D and 3D models, achieving an AUC of 0.996 and F1 score of 0.915 in the training set.
  • In external testing, the 2.5D CNN model achieved an AUC of 0.815 and an F1 score of 0.714.
  • Assistance from the 2.5D CNN model significantly enhanced clinicians' diagnostic accuracy, improving AUC and F1 scores for both senior (0.882, 0.774) and junior (0.784, 0.667) clinicians.

Conclusions:

  • The developed 2.5D CNN model represents a significant advancement in the non-invasive identification of MVCF patients.
  • This AI-powered tool shows potential to aid clinicians in more accurately diagnosing MVCFs, thereby improving patient management.
  • The model offers a promising non-invasive alternative to vertebral biopsy for MVCF detection.