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: May 8, 2026

Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis
07:44

Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis

Published on: March 23, 2019

Benchmarking Multimodal Vision Frontier Models With Lumbar Spine MRIs for Grading Lumbar Spinal Stenosis.

Harry Gebhard1, Ahmet Kartal2, Noel F Manalil2

  • 1Department of Neurosurgery, Medical University Lausitz - Carl Thiem, Cottbus, Germany.

Global Spine Journal
|May 7, 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

Advancing Cranioplasty Techniques Through Exoscopic Magnification: A Case-Series and Single-Center Experience.

Operative neurosurgery (Hagerstown, Md.)·2026
Same author

Identifying an X-Ray Threshold for Cage Subsidence After Single-Level Minimally Invasive Transforaminal Lumbar Interbody Fusion: A Diagnostic Threshold Study Using Intraoperative CT as the Reference Standard.

Journal of clinical medicine·2026
Same author

Cage Overhang Ratio and Increased Radiographic Subsidence in Stand-Alone Lateral Lumbar Interbody Fusion.

World neurosurgery·2026
Same author

Administration of ketogenic intervention as a potential treatment during post-traumatic brain injury recovery: a scoping review.

Frontiers in nutrition·2026
Same author

The "one-and-a-half" minimally invasive transforaminal lumbar interbody fusion: a single-center retrospective case series.

Journal of neurosurgery. Spine·2026
Same author

Cervical Paraspinal Muscle Morphometry and Mechanical Failure: A Propensity-Matched Analysis.

World neurosurgery·2026

Google Gemini 3 Pro demonstrated fair agreement for grading lumbar spinal canal stenosis on video MRI. However, it significantly under-detected severe cases, indicating limitations for clinical decision support.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Radiology

Background:

  • Previous AI models for radiology decision support primarily used 2D images or text.
  • The capability of AI to interpret volumetric data, like video MRI, for complex diagnoses remained largely unassessed.
  • Lumbar spinal canal stenosis grading is crucial for patient management and requires accurate interpretation of MRI data.

Purpose of the Study:

  • To evaluate Google Gemini 3 Pro's diagnostic accuracy in grading lumbar spinal canal stenosis using video lumbar MRI.
  • To compare Gemini 3 Pro's performance against neuroradiologist consensus.
  • To assess the impact of localizer-assisted input on the AI model's diagnostic performance.

Main Methods:

  • Utilized the RSNA 2024 Lumbar Spine Degenerative Classification Dataset with ASNR consensus labels.
Keywords:
MRI cine videodiagnostic accuracyinter-rater reliabilitylumbar spinal canal stenosismultimodal vision frontier models

More Related Videos

The Third Channel-Assisted Unilateral Biportal Endoscopic Technique for Lumbar Spinal Stenosis Combined with Contralateral Disc Herniation
06:26

The Third Channel-Assisted Unilateral Biportal Endoscopic Technique for Lumbar Spinal Stenosis Combined with Contralateral Disc Herniation

Published on: November 17, 2023

Related Experiment Videos

Last Updated: May 8, 2026

Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis
07:44

Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis

Published on: March 23, 2019

The Third Channel-Assisted Unilateral Biportal Endoscopic Technique for Lumbar Spinal Stenosis Combined with Contralateral Disc Herniation
06:26

The Third Channel-Assisted Unilateral Biportal Endoscopic Technique for Lumbar Spinal Stenosis Combined with Contralateral Disc Herniation

Published on: November 17, 2023

  • Converted 100 lumbar MRI examinations into synchronized video montages for AI analysis.
  • Assessed Gemini 3 Pro's grading with and without localizer overlays, measuring overall accuracy and linearly weighted kappa (κw).

    • Main Results:

    • Without localizers, Gemini 3 Pro achieved 75.6% overall accuracy with fair agreement (κw = 0.39).
    • Sensitivity for detecting severe stenosis was low (41.8%), with a high rate of downgrading severe cases.
    • Localizer-assisted input did not significantly improve accuracy (73.2%, κw = 0.32) and further reduced severe stenosis detection.

    Conclusions:

    • Google Gemini 3 Pro exhibited fair agreement but clinically unacceptable under-detection of severe lumbar spinal canal stenosis.
    • The model's overall accuracy was misleading due to a high prevalence of normal/mild cases.
    • Localizer overlays did not enhance the AI's diagnostic performance for this task.