人工智能与颈椎图像识别:应用前景与挑战  

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

作　　者：王思敏 张德洲 赵静[1] 王超群 李琨 陈杰 白雪 赵海龙 张少杰 马渊 郝韵腾 杨洋 李志军 史君 王星 Wang Simin;Zhang Dezhou;Zhao Jing;Wang Chaoqun;Li Kun;Chen Jie;Bai Xue;Zhao Hailong;Zhang Shaojie;Ma Yuan;Hao Yunteng;Yang Yang;Li Zhijun;Shi Jun;Wang Xing(Graduate School of Inner Mongolia Medical University,Hohhot 010110,Inner Mongolia Autonomous Region,China;Department of Imaging,Affiliated Hospital of Inner Mongolia Medical University,Hohhot 010050,Inner Mongolia Autonomous Region,China;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;Physiology Teaching and Research Section,School of Basic Medicine,Inner Mongolia Medical University,Hohhot 010110,Inner Mongolia Autonomous Region,China)

机构地区：[1]内蒙古医科大学研究生院,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 [3]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 [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 [5]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

出　　处：《中国组织工程研究》2025年第33期7231-7240,共10页Chinese Journal of Tissue Engineering Research

基　　金：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。

摘　　要：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。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 develo

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 

分 类 号：R459.9[医药卫生—治疗学] R318[医药卫生—临床医学] TP18[自动化与计算机技术—控制理论与控制工程]