Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Long-Term Clinical and Radiographic Osseointegration Outcomes of a Highly Porous 3D-Printed Titanium Collar Compared with a Hydroxyapatite-Coated Collar in Megaprostheses.

Journal of functional biomaterials·2026
Same author

Screening for Distress and Sources of Distress in Parents with Advanced Cancer and their Coparents.

Journal of pain and symptom management·2026
Same author

Intramedullary osteoblastoma of the femur: a case report.

Skeletal radiology·2026
Same author

Challenging the Paradigm: Fascia Iliaca Blocks May Not be Necessary for All Neck of Femur Fractures.

The Journal of emergency medicine·2026
Same author

The "CHARKAJ line": A novel radiographic parameter for the evaluation of adult hip dysplasia.

Clinical imaging·2026
Same author

Relationships of actual and expected levels of income with GP job satisfaction: a repeated cross-sectional study.

The British journal of general practice : the journal of the Royal College of General Practitioners·2026
Same journal

Diagnostic value of an S1-normalized CT hounsfield unit ratio for identifying acute fractures in complex thoracolumbar osteoporotic deformities.

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 journal

A novel inflammatory-nutritional nomogram for predicting survival after minimally invasive surgery for spinal metastases: a comparison with the Katagiri and SORG systems.

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 journal

Reduced paraspinal muscle endurance and electromyographic fatigability are associated with greater global spinal imbalance in symptomatic lumbar spinal stenosis.

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 journal

Instrumentation failure after lumbar spondylectomy for spinal tumors: a systematic review and pooled individual patient analysis.

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 journal

Evaluation of a mixed reality navigation simulator for training of minimally invasive interventions of the spine: a pilot didactic plan.

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 journal

Asymmetrical sacroiliac joint degeneration in degenerative lumbar scoliosis and its association with clinical outcomes and spinopelvic parameters.

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
查看所有相关文章

相关实验视频

Updated: Feb 22, 2026

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

1.2K

大型语言模型与图像处理在自动化的科布角度.

Jonathan Gibson1, Sanika Kharwadkar2, Chuck Lam1

  • 1College of Medical and Dental Sciences, University of Birmingham, Birmingham, UK.

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
|February 20, 2026
PubMed
概括
此摘要是机器生成的。

目前的大型语言模型 (LLM) 在测量科布角以评估脊椎形时显示出有限的准确性. 在用于脊柱形分析的临床整合之前,人工智能工具需要进一步开发.

关键词:
人工智能,脊椎病,科布角度,大型语言模型,技术技术.

更多相关视频

Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control
05:47

Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control

Published on: August 29, 2025

484
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.3K

相关实验视频

Last Updated: Feb 22, 2026

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

1.2K
Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control
05:47

Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control

Published on: August 29, 2025

484
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.3K

科学领域:

  • 医学成像分析分析 医学成像分析
  • 医疗保健中的人工智能
  • 脊柱形评估 脊柱形评估

背景情况:

  • 脊柱病的严重程度是用X射线图上测量的科布角来量化.
  • 人工智能 (AI) 融入临床工作流程引发了关于其在脊柱形分类中的有用性的问题.
  • 在临床应用中评估领先的大型语言模型 (LLM) 的能力至关重要.

研究的目的:

  • 评估四个著名的LLM (ChatGPT,Gemini,Perplexity,Grok) 在计算脊柱脊椎病X射线图中的科布角的诊断准确度.
  • 将这些LLM的性能与放射科医生的测量进行比较.
  • 评估AI在科布角确定中的可用性和临床适用性.

主要方法:

  • 一项涉及122名脊椎病患者X射线图的横截面研究.
  • 由经过培训的放射科医生使用Horos软件作为参考标准进行独立的科布角计算.
  • 放射图由四名LLM分析,以识别脊椎病类型,生成叠加,并计算科布角,随后进行统计分析.

主要成果:

  • 双子座和ChatGPT显示出显著的局限性,双子座未能产生测量结果,ChatGPT显示出很大的误差 (MAE 58.6° ± 45.9°).
  • 困惑和Grok为所有案例提供了估计值,但平均差异分别为18.8° (±13.3°) 和24.2° (±18.3°).
  • 没有AI模型能够准确地识别S形脊椎病,也没有达到科布角测量的临床可接受差异 (≤10%).

结论:

  • 商业上可用的LLM目前对临床科布角测量在脊椎病的准确性不够.
  • 虽然Perplexity和Grok在测试模型中表现更好,但没有一个模型达到临床上可接受的准确性.
  • 开发专门的AI工具是必要的,以确保可靠的临床整合在脊柱形评估.