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

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

Biportal Endoscopic Posterior Cervical Foraminotomy.

JBJS essential surgical techniques·2026

Same author

Trends in Patient Portal Messages, Office Visits, and Telephone Encounters.

JAMA·2026

Same author

Psychologic readiness for adult spinal deformity surgery: practical screening and optimization pathways.

Spine deformity·2026

Same author

The Variability of MCID, SCB, and PASS Thresholds in the Adult Spinal Deformity Literature: A Systematic Review.

Spine·2026

Same author

Open superior mesenteric artery thrombectomy of dislodged aortic valve causing acute mesenteric ischemia.

Journal of vascular surgery cases and innovative techniques·2026

Same author

CNS-Obsidian: A Neurosurgical Vision-Language Model Built From Scientific Publications.

Neurosurgery·2026

Same journal

Testosterone Replacement Therapy in Posterior Lumbar Fusion Patients: A Propensity Score-Matched Analysis of Long-Term Outcomes.

Global spine journal·2026

Same journal

Forgotten Spine Surgery Score Cervical (FS3-C): A Patient-Reported Outcome Measure for Assessing the Impact of Motion Preservation in Cervical Spine Surgery.

Global spine journal·2026

Same journal

The First Wave: National Adoption and Economic Shifts of Posterior Cervical Decompression and Fusion in Hospital-Owned Ambulatory Surgery Centers.

Global spine journal·2026

Same journal

Smoking, Alcohol Use, and Low Back Pain: A Large-Scale Study Identifying a Synergistic Lifestyle Risk.

Global spine journal·2026

Same journal

Clinical Outcomes Following Three- and Four-Level Anterior Cervical Discectomy and Fusion: A Systematic Review and Meta-Analysis.

Global spine journal·2026

Same journal

Radiation-free Assessment of Scoliosis: A Reliability and Validity Study for Ultrasound Angles.

Global spine journal·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 14, 2025

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

Published on: March 23, 2019

Automated Measurement of Lumbar Lordosis on Radiographs Using Machine Learning and Computer Vision.

Brian H Cho^1,2, Deepak Kaji^1,2, Zoe B Cheung¹

¹Icahn School of Medicine at Mount Sinai, New York, NY, USA.

Global Spine Journal

|July 18, 2020

Summary

This summary is machine-generated.

This study introduces an AI and computer vision pipeline for measuring lumbar lordosis angles from radiographs. The automated system demonstrated comparable accuracy to manual surgeon measurements, offering clinical utility.

Keywords:

angle measurement artificial intelligence computer-assisted lordosis lumbar machine learning neural networks radiographic image interpretation radiography sagittal balance spinopelvic parameters

More Related Videos

Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation

Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation

Published on: December 13, 2024

Three-dimensional Navigation-guided, Prone, Single-position, Lateral Lumbar Interbody Fusion Technique

Three-dimensional Navigation-guided, Prone, Single-position, Lateral Lumbar Interbody Fusion Technique

Published on: July 15, 2021

Related Experiment Videos

Last Updated: Dec 14, 2025

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

Published on: March 23, 2019

Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation

Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation

Published on: December 13, 2024

Three-dimensional Navigation-guided, Prone, Single-position, Lateral Lumbar Interbody Fusion Technique

Three-dimensional Navigation-guided, Prone, Single-position, Lateral Lumbar Interbody Fusion Technique

Published on: July 15, 2021

Area of Science:

Medical Imaging
Artificial Intelligence
Spine Biomechanics

Background:

Accurate measurement of lumbar lordosis is crucial for diagnosing and managing spinal conditions.
Current methods for assessing lumbar lordosis often require manual input, which can be time-consuming and subjective.

Purpose of the Study:

To develop and validate a fully automated artificial intelligence (AI) and computer vision pipeline for the assisted evaluation of lumbar lordosis.
To assess the accuracy and efficiency of the AI pipeline in measuring lumbar lordosis angles compared to manual surgeon measurements.

Main Methods:

A segmentation neural network (U-Net) was developed using lateral lumbar radiographs (n=629) for automated vertebral identification.
A computer vision algorithm was applied to segmented radiographs to calculate lumbar lordosis angles.
The pipeline's validity was evaluated on an independent test set (n=151), with performance compared against manual measurements from orthopedic surgeons.

Main Results:

The AI pipeline achieved high performance in segmenting lumbar vertebrae, with a Dice score of 0.821 and an area under the receiver operating curve of 0.914.
The system accurately identified L1 and S1 vertebrae in 84.1% of cases and calculated angles with a mean absolute error of 8.055° compared to surgeon measurements (P > .05).
The automated measurement process was rapid, averaging 0.14 seconds per radiograph.

Conclusions:

This study presents the first combined AI and computer vision pipeline for automated measurement of sagittal spinopelvic parameters like lumbar lordosis.
The developed pipeline provides clinically relevant measurements with no statistically significant difference from manual surgeon assessments.
The AI system demonstrates significant clinical utility as an assistive tool for evaluating lumbar lordosis, with potential for future improvements in segmentation accuracy.