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: Jul 7, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Development and multi-institutional validation of a deep learning algorithm for predicting cervical cord compression

Sung Cheol Park1,2, Wounsuk Rhee3,4, Bong-Soon Chang1,5

  • 1College of Medicine, Seoul National University, Seoul, Republic of Korea.

Scientific Reports
|June 20, 2026
PubMed
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

Optimization of spine surgery outcomes in patients with osteoporosis: a comprehensive narrative review.

Asian spine journal·2026
Same author

A Quantitative CT-Based Analysis of Vertebral Rotational Asymmetry and Pulmonary Function in Scoliosis.

Journal of clinical medicine·2026
Same author

Hidden Blood Loss in Full-Endoscopic Lumbar Decompression Compared with Biportal Endoscopic and Open Microscopic Surgery for Single-Segment Lumbar Stenosis.

Journal of clinical medicine·2026
Same author

Comparison of multistage and single-stage framework for automated landmark localization and radiologic measurement: a case of the C1-2 complex on cervical spine lateral radiographs.

BMC medical imaging·2026
Same author

Feasibility and oncologic outcome of en resection with intentional tumor transgression in primary spinal sarcoma: The Korean Society of Spinal Tumors multicenter study (KSST 2024-02).

Journal of bone oncology·2026
Same author

Facet Effusion-Incorporating Grading System: A Modified Magnetic Resonance Imaging-Based Classification That Enhances Surgical Prognostication in Lumbar Foraminal Stenosis.

Clinics in orthopedic surgery·2026
This summary is machine-generated.

Deep learning models using convolutional neural networks (CNNs) can predict spinal cord compression (SCC) from cervical radiographs, offering a cost-effective screening tool for degenerative cervical myelopathy (DCM). This approach enhances diagnostic efficiency and potentially improves patient outcomes.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neurosurgery

Background:

  • Magnetic resonance imaging (MRI) is the gold standard for diagnosing degenerative cervical myelopathy (DCM), but its high cost and limited availability can impede timely diagnosis.
  • Plain radiographs are more accessible but less sensitive for detecting spinal cord compression (SCC).
  • Deep learning (DL) presents a potential avenue for leveraging radiographic data to screen for DCM-related SCC.

Purpose of the Study:

  • To develop and validate a CNN-based DL algorithm for predicting SCC using dynamic cervical lateral radiographs.
  • To assess the algorithm's performance across multi-institutional datasets.
  • To identify features contributing to SCC prediction using Grad-CAM analysis.

Main Methods:

  • A dataset of 7878 patients with cervical radiographs and MRI was used, with SCC status determined by MRI.
Keywords:
Artificial intelligenceConvolutional neural networkDeep learningDegenerative cervical myelopathyPlain radiographsSpinal cord compression

Related Experiment Videos

Last Updated: Jul 7, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

  • Ten ImageNet-pretrained CNN architectures were trained on single-position and combined radiographic views, with and without demographic data.
  • External validation was performed on 575 patients from an independent hospital.

    • Main Results:

    • The combined VGG-16 model achieved an area under the receiver operating characteristic curve (AUC) of 0.888 internally and 0.820 externally.
    • Grad-CAM analysis identified potential indicators of SCC, including disc herniations, osteophytes, ossification of the posterior longitudinal ligament, and segmental instability.
    • The DL algorithm demonstrated robust performance in predicting SCC from radiographs.

    Conclusions:

    • A CNN-based DL algorithm can effectively predict spinal cord compression from cervical radiographs.
    • This algorithm shows promise as a cost-effective screening tool for degenerative cervical myelopathy.
    • The developed tool has the potential to improve diagnostic efficiency and clinical outcomes for DCM patients.