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: Jan 17, 2026

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

A CNN Autoencoder for Learning Latent Disc Geometry from Segmented Lumbar Spine MRI.

Mattia Perrone1, D'Mar M Moore1, Daisuke Ukeba1

  • 1Rush University Medical Center, 1620 W Harrison St., Chicago, IL, 60612, USA.

Annals of Biomedical Engineering
|September 22, 2025
PubMed
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

Feasibility and accuracy of AI-assisted 3D MRI/CT fusion imaging for preoperative simulation of full-endoscopic transforaminal discectomy.

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2026
Same author

Lumbar ossification of the posterior longitudinal ligament as a distinct phenotype of diffuse spinal ligament ossification.

The spine journal : official journal of the North American Spine Society·2026
Same author

Full-Endoscopic Spine Surgery for Adjacent Segment Disease Using Artificial Intelligence-Assisted 3-Dimensional MRI/CT Fusion Imaging: A Case Report.

JBJS case connector·2026
Same author

Only One Occurrence of Postoperative White Cord Syndrome in Sequential 244 Cases of Cervical Spine Laminoplasty in 20 Years in a Single Institute.

Clinical spine surgery·2025
Same author

Visceral Fat and Ossification of the Posterior Longitudinal Ligament: Insights From a Japanese Cohort.

JB & JS open access·2025
Same author

Gait-to-Contact (G2C): A Novel Deep Learning Framework to Predict Total Knee Replacement Wear from Gait Patterns.

Annals of biomedical engineering·2025
Same journal

Pulsatile Hemodynamics of Prehypertension and Hypertension: Associations with Pressure and Sex.

Annals of biomedical engineering·2026
Same journal

A Pressure Difference-Based Strategy for Blood Oxygen Control in Membrane Oxygenators: Reduced Modeling, Computational Simulation, and Exploratory In Vivo Evaluation.

Annals of biomedical engineering·2026
Same journal

Multidirectional Optical Bone Densitometry Using a Simulation-Based Machine Learning Model: Experimental Validation with Bone Phantoms.

Annals of biomedical engineering·2026
Same journal

Numerical Study of Human Torso Mechanical Response and Injury Assessment Under Blast Loading with Bulletproof Protection.

Annals of biomedical engineering·2026
Same journal

Immediate and Mid-Long-Term Effects of Foot Orthoses on Gait Biomechanics and Clinical Characteristics in Medial Knee Osteoarthritis: A Systematic Review and Meta-analysis.

Annals of biomedical engineering·2026
Same journal

Screening and Evaluation of Post-stroke Dysphagia: Insights from Neurology, Artificial Intelligence and Data Science-A Scoping Review.

Annals of biomedical engineering·2026
See all related articles

A novel convolutional neural network (CNN) autoencoder effectively extracts latent geometric features from lumbar MRI, improving disc narrowing prediction. These features offer new insights into disc pathology beyond traditional measurements.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Spine Biomechanics

Background:

  • Low back pain is a leading cause of disability globally.
  • Lumbar intervertebral disc pathology is a frequent pain driver.
  • Disc geometry is crucial for understanding mechanical behavior and pathology.

Purpose of the Study:

  • To develop a convolutional neural network (CNN) autoencoder for extracting latent features from segmented lumbar disc MRI.
  • To interpret these latent features and assess their utility in identifying disc pathology.
  • To complement standard geometric measures with novel feature insights.

Main Methods:

  • Examined 195 sagittal T1-weighted lumbar spine MRIs.
  • Developed a pipeline involving MRI segmentation and CNN autoencoder training.
Keywords:
AutoencoderConvolutional neural networks (CNN)Features interpretabilityLatent featuresMRI segmentation

More Related Videos

3D Printing Model of a Patient's Specific Lumbar Vertebra
07:30

3D Printing Model of a Patient's Specific Lumbar Vertebra

Published on: April 14, 2023

2.5K

Related Experiment Videos

Last Updated: Jan 17, 2026

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
3D Printing Model of a Patient's Specific Lumbar Vertebra
07:30

3D Printing Model of a Patient's Specific Lumbar Vertebra

Published on: April 14, 2023

2.5K
  • Extracted latent geometric features and compared them with standard geometric measures for predicting disc narrowing.

    • Main Results:

    • Achieved high segmentation accuracy (IoU 0.82, DSC 0.90).
    • The CNN autoencoder effectively extracted latent features, with optimal convergence at a 4x1 bottleneck.
    • Combined latent and geometric features significantly improved disc narrowing prediction compared to using either set alone.
    • Latent features captured disc shape and angular orientation.

    Conclusions:

    • A CNN autoencoder successfully extracts interpretable latent features from lumbar disc MRI.
    • This approach enhances the prediction of disc narrowing.
    • Future research will incorporate voxel intensity for compositional analysis.