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

You might also read

Related Articles

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

Sort by
Same author

Risk of hypertension after CGRP antagonist treatment in migraine: A systematic review and meta-analysis.

Headache·2026
Same author

Safety and Radiological Outcomes of Posterior-Based Minimally Invasive Scoliosis Surgery in Young Adult Idiopathic Scoliosis: A Comparative Study Based on Age.

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

Sagittal Profiles and Their Reciprocal Changes Manifesting in Proximal Junctional Kyphosis Following Deformity Correction in Adolescent Idiopathic Scoliosis.

Global spine journal·2026
Same author

Influence of acetabular dysplasia and associated radiological indicators on hip joint motion in asymptomatic individuals.

Journal of hip preservation surgery·2026
Same author

Brain Serotonin Transporter Is Elevated in Obesity: Bayesian and Frequentist Meta-Analyses.

Diabetes, obesity & metabolism·2026
Same author

ZNF184 negatively regulates HR repair and predicts poor prognosis in acute lymphoblastic leukemia.

Nucleic acids research·2026

Related Experiment Video

Updated: Mar 19, 2026

Optimizing Minimally Invasive Spine Surgery: A Fully 3D CT O-Arm Navigated Workflow in MIS TLIF
08:34

Optimizing Minimally Invasive Spine Surgery: A Fully 3D CT O-Arm Navigated Workflow in MIS TLIF

Published on: October 17, 2025

783

High-Speed Instance Segmentation for Endoscopic Spine Surgery: Multicenter Validation and Inference Speed Evaluation.

Yoon Jae Cho1, Yong Jae Cho2, Yong Geon Park3

  • 1Department of Orthopaedic Surgery, Biomedical Research Institute, Pusan National University Hospital, Pusan National University, Busan, Republic of Korea.

Global Spine Journal
|March 18, 2026
PubMed
Summary
This summary is machine-generated.

This study developed an AI system for real-time segmentation in endoscopic spine surgery. The AI shows potential for improving surgical precision and efficiency across different hardware setups.

Keywords:
artificial intelligenceendoscopic spine surgeryinstance segmentationlumbarmulticenterrapid inference

More Related Videos

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.7K
Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery
09:53

Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery

Published on: July 5, 2021

4.4K

Related Experiment Videos

Last Updated: Mar 19, 2026

Optimizing Minimally Invasive Spine Surgery: A Fully 3D CT O-Arm Navigated Workflow in MIS TLIF
08:34

Optimizing Minimally Invasive Spine Surgery: A Fully 3D CT O-Arm Navigated Workflow in MIS TLIF

Published on: October 17, 2025

783
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.7K
Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery
09:53

Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery

Published on: July 5, 2021

4.4K

Area of Science:

  • Spinal Surgery
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Endoscopic spine surgery requires precise visualization of anatomical structures.
  • Current visualization methods may have limitations in complex surgical scenarios.
  • AI-powered tools can potentially enhance surgical guidance and safety.

Purpose of the Study:

  • To develop and validate an AI-based high-speed multi-class instance segmentation system for lumbar spinal endoscopic surgery.
  • To assess the system's performance across various hardware environments (CPU and GPU).
  • To evaluate the AI's effectiveness using multicenter surgical video data.

Main Methods:

  • A retrospective multicenter cohort study analyzed endoscopic videos from 112 patients across 5 hospitals.
  • A Segment Anything Model (SAM)-assisted workflow was used for efficient annotation of 58,087 images across 7 classes.
  • A YOLOv11-seg model was trained and validated, with performance metrics including precision, recall, F1-score, and mAP50.
  • Inference speed was benchmarked on different CPU and GPU configurations.

Main Results:

  • The AI system achieved high performance metrics, with notable variations between biportal and uniportal approaches.
  • Specific classes like instruments showed high accuracy (mAP50=0.949) in uniportal settings, while vessels were better detected (mAP50=0.863) in biportal settings.
  • Inference speeds ranged from ~22 FPS on CPU to ~117 FPS on high-end GPUs, enabling real-time application.

Conclusions:

  • High-speed, multi-class instance segmentation using AI holds significant potential for endoscopic spine surgery.
  • The AI system demonstrates feasibility across different surgical approaches and hardware.
  • Future research should focus on enhancing model robustness in visually challenging environments and prioritizing precision and speed for clinical integration.