中国组织工程研究 ›› 2025, Vol. 29 ›› Issue (33): 7231-7240.doi: 10.12307/2025.837

• 骨与关节综述 bone and joint review • 上一篇    下一篇

人工智能与颈椎图像识别:应用前景与挑战

王思敏1,张德洲1,赵  静1,王超群2,李  琨3,4,陈  杰3,白  雪4,赵海龙4,张少杰3,4,马  渊4,郝韵腾4,杨  洋3,李志军3,4,史  君5,王  星3,4   

  1. 内蒙古医科大学,1研究生院,3基础医学院解剖学教研室,5基础医学院生理学教研室,内蒙古自治区呼和浩特市   010110;2内蒙古医科大学附属医院影像科,内蒙古自治区呼和浩特市   010050; 4内蒙古医科大学基础医学院数字医学中心/内蒙古自治区数字转化医学工程技术研究中心,内蒙古自治区呼和浩特市   010059
  • 收稿日期:2024-07-17 接受日期:2024-09-05 出版日期:2025-11-28 发布日期:2025-04-15
  • 通讯作者: 王星,博士,副教授,内蒙古医科大学基础医学院解剖学教研室,内蒙古自治区呼和浩特市 010110;内蒙古医科大学基础医学院数字医学中心/内蒙古自治区数字转化医学工程技术研究中心,内蒙古自治区呼和浩特市 010059 史君,副教授,内蒙古医科大学基础医学院生理学教研室,内蒙古自治区呼和浩特市 010110
  • 作者简介:王思敏,女,1996年生,山西省吕梁市人,内蒙古医科大学在读硕士,主要从事脊柱与脊髓的数字化研究。 张德洲,男,1998年生,贵州省铜仁市人,土家族,内蒙古医科大学在读硕士,主要从事脊柱与脊髓的数字化研究。
  • 基金资助:
    内蒙古自治区高等学校青年科技英才支持计划资助(NJYT22009),项目负责人:王星;内蒙古医科大学科研重点项目(YKD2021ZD011),项目负责人:王星;内蒙古自治区卫生健康委医疗卫生科技计划项目(202201217),项目负责人:王星;内蒙古医科大学博士启动基金项目(YKD2023BSQD014),项目负责人:王星;内蒙古自治区硕士研究生科研创新计划(S20231186Z),项目负责人:王思敏;内蒙古自治区硕士研究生科研创新计划(S20231182Z),项目负责人:郝韵腾

Artificial intelligence and cervical spine image recognition: application prospects and challenges

Wang Simin1, Zhang Dezhou1, Zhao Jing1, Wang Chaoqun2, Li Kun3, 4, Chen Jie3, Bai Xue4, Zhao Hailong4, Zhang Shaojie3, 4, Ma Yuan4, Hao Yunteng4, Yang Yang3, Li Zhijun3, 4, Shi Jun5, Wang Xing3, 4   

  1. 1Graduate School of Inner Mongolia Medical University, Hohhot 010110, Inner Mongolia Autonomous Region, China; 2Department of Imaging, Affiliated Hospital of Inner Mongolia Medical University, Hohhot 010050, Inner Mongolia Autonomous Region, China; 3Anatomy Teaching and Research Section, School of Basic Medicine, Inner Mongolia Medical University, Hohhot 010110, Inner Mongolia Autonomous Region, China; 4Digital Medicine Center/Inner Mongolia Autonomous Region Digital Translational Medicine Engineering Technology Research Center, School of Basic Medicine, Inner Mongolia Medical University, Hohhot 010059, Inner Mongolia Autonomous Region, China; 5Physiology Teaching and Research Section, School of Basic Medicine, Inner Mongolia Medical University, Hohhot 010110, Inner Mongolia Autonomous Region, China
  • Received:2024-07-17 Accepted:2024-09-05 Online:2025-11-28 Published:2025-04-15
  • Contact: Wang Xing, MD, Associate professor, Anatomy Teaching and Research Section, School of Basic Medicine, Inner Mongolia Medical University, Hohhot 010110, Inner Mongolia Autonomous Region, China; Digital Medicine Center/Inner Mongolia Autonomous Region Digital Translational Medicine Engineering Technology Research Center, School of Basic Medicine, Inner Mongolia Medical University, Hohhot 010059, Inner Mongolia Autonomous Region, China Shi Jun, Associate professor, Physiology Teaching and Research Section, School of Basic Medicine, Inner Mongolia Medical University, Hohhot 010110, Inner Mongolia Autonomous Region, China
  • About author:Wang Simin, Master candidate, Graduate School of Inner Mongolia Medical University, Hohhot 010110, Inner Mongolia Autonomous Region, China Zhang Dezhou, Master candidfate, Graduate School of Inner Mongolia Medical University, Hohhot 010110, Inner Mongolia Autonomous Region, China
  • Supported by:
    Inner Mongolia Autonomous Region College Young Science and Technology Talent Support Program, No. NJYT22009 (to WX); Key Research Project of Inner Mongolia Medical University, No. YKD2021ZD011 (to WX); Inner Mongolia Autonomous Region Health Commission Medical and Health Science and Technology Plan Project, No. 202201217 (to WX); Inner Mongolia Medical University Doctoral Start-up Fund Project, No. YKD2023BSQD014 (to WX); Inner Mongolia Autonomous Region Master's Research Innovation Program, No. S20231186Z (to WSM); Inner Mongolia Autonomous Region Master's Research Innovation Program, No. S20231182Z (to HYT)

摘要:


文题释义:

人工智能:是一门新兴的技术科学,致力于研究开发用于模拟、延伸和扩展人类智能理论、方法、技术及应用系统。作为智能学科的重要组成部分,人工智能旨在理解智能的本质,并开发类似于人类并能够做出反应的智能机器。
深度学习:是机器学习领域中一个新的研究方向,它的最终目标是让机器能够像人一样具有分析学习能力,能够识别文字、图像和声音等数据。


背景:颈椎病是一种慢性退行性疾病,已经成为威胁人类健康的常见病和多发病之一。目前对颈椎及其周围结构病变的初步诊断主要倚赖于放射科医师对医学影像的解读,这不仅对操作人员技术要求较高,而且存在主观性较强、劳动强度高、效率低等缺点。随着人工智能技术的快速发展,其强大的数据处理和图像识别能力使其在医疗领域展现出广阔的应用前景,深度学习也在脊柱疾病的研究中取得了一定的进展。

目的:综述近年来人工智能技术在颈椎影像图像中的应用现状和研究进展,评估人工智能模型的表现以及未来的发展趋势及需要克服的挑战。
方法:由第一作者在 2024 年 6 月以“人工智能,深度学习,颈椎” 为 中 文 检 索 词,以“Artificial Intelligence,AI,Cervical Vertebrae,Cervical”为英文检索词分别在万方数据库、中国知网和PubMed数据库进行检索,最终纳入101篇文章进行综述分析。

结果与结论:①人工智能技术可通过对医学图像部位进行分割、分类、关键点识别等技术实现对颈椎椎体的自动分割及曲度改变的测量,检测颈椎骨折、神经根和脊髓型颈椎病,识别颈椎后纵韧带骨化,预测手术后相关危险因素以及颈椎成熟度分类等;②尽管人工智能技术在颈椎研究领域已展现出巨大潜力,但其仍处于初期探索与快速发展阶段,有无限的发展与创新空间。

https://orcid.org/0000-0003-0059-4921 (王星) 

中国组织工程研究杂志出版内容重点:人工关节;骨植入物;脊柱;骨折;内固定;数字化骨科;组织工程

关键词: 人工智能, 人工智能模型, 深度学习, 颈椎, 医学图像, 研究进展, 临床应用, 工程化组织构建

Abstract: BACKGROUND: Cervical spondylosis is a chronic degenerative disease that has become one of the most common and frequent diseases threatening human health. At present, the initial diagnosis of the cervical spine and its surrounding structures mainly relies on the interpretation of medical images by radiologists, which not only requires a high level of technical requirements for operators, but also has the disadvantages of strong subjectivity, high labor intensity, and low efficiency. With the rapid development of artificial intelligence technology, its powerful data processing and image recognition capabilities have shown broad application prospects in the medical field. Deep learning has also made certain progress in the research of spinal diseases. 
OBJECTIVE: To summarize the current status and research progress in the application of artificial intelligence technology in cervical spine imaging images in recent years, evaluating the performance of artificial intelligence models as well as future trends and challenges to be overcome. 
METHODS: The first author searched the relevant articles in WanFang, CNKI, and PubMed in June 2024. The Chinese search terms were “artificial intelligence, deep learning, cervical spine.” English serach terms were “artificial intelligence, AI, cervical vertebrae, cervical.” Finally, 101 articles were included and analyzed.
RESULTS AND CONCLUSION: (1) Artificial intelligence technology can realize automatic segmentation of cervical vertebrae and measurement of curvature change by segmentation, classification, landmarks recognition of medical image parts, detect cervical vertebral fracture, nerve root, and spinal cord type cervical spondylosis, identify cervical spine ossification of posterior longitudinal ligament, and predict post-surgery related risk factors and cervical vertebra maturation classification. (2) Although artificial intelligence technology has shown great potential in the field of cervical spine research, it is still in the early stages of exploration and rapid development, with unlimited room for development and innovation.

Key words: artificial intelligence, artificial intelligence model, deep learning, cervical spine, medical imaging, research advance, clinical application, engineered tissue construction

中图分类号: