中国组织工程研究 ›› 2026, Vol. 30 ›› Issue (27): 7203-7209.doi: 10.12307/2026.427

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

深度学习与骨骼影像诊断

张  鑫,张美书,葛  淼,孙坚皓,吕龙龙,高  鹏   

  1. 潍坊市中医院,山东省潍坊市   261000
  • 收稿日期:2025-12-06 接受日期:2026-01-03 出版日期:2026-09-28 发布日期:2026-05-26
  • 通讯作者: 高鹏,硕士,主治医师,潍坊市中医院,山东省潍坊市 261000
  • 作者简介:张鑫,男,1996年生,山东省潍坊市人,汉族,硕士,主治医师,主要从事脊柱退行性病变及骨质疏松相关研究。

Deep learning in bone imaging diagnosis

Zhang Xin, Zhang Meishu, Ge Miao, Sun Jianhao, Lyu Longlong, Gao Peng   

  1. Weifang Hospital of Traditional Chinese Medicine, Weifang 261000, Shandong Province, China

  • Received:2025-12-06 Accepted:2026-01-03 Online:2026-09-28 Published:2026-05-26
  • Contact: Gao Peng, MS, Attending physician, Weifang Hospital of Traditional Chinese Medicine, Weifang 261000, Shandong Province, China
  • About author:Zhang Xin, MS, Attending physician, Weifang Hospital of Traditional Chinese Medicine, Weifang 261000, Shandong Province, China

摘要:

文题释义:

深度学习:通过构建多层神经网络模型,从海量的骨骼影像数据中自动学习和提取与疾病相关的深层特征,从而实现对骨折、骨肿瘤等病灶的智能检测、分割与分类,旨在提升诊断的效率与准确性。
骨骼影像诊断:主要利用X射线片、CT、MRI等成像技术获取骨骼、关节及相关软组织的图像,对骨折、骨肿瘤、骨质疏松、骨关节炎等多种骨骼系统疾病进行定性与定量评估,是骨科临床诊断和治疗决策的关键依据。

摘要
背景:深度学习方法在骨骼影像诊断领域取得了突破性进展,克服了传统骨骼影像诊断方法中容易误诊和效率低下的难题,有助于普及骨科智能化诊断方法。
目的:综述深度学习在常见骨骼疾病诊断中的应用及优缺点。
方法:检索中国知网、万方、PubMed、Web of Science数据库中2021年1月至2025年6月发表的有关深度学习辅助骨骼影像诊断的文献,中文检索词包括“人工智能,深度学习,机器学习,计算机辅助诊断,骨骼影像诊断,骨折,骨肿瘤,骨质疏松,骨关节炎,滑膜炎,脊柱,软骨,分类,检测,分割”;英文检索词包括“artificial intelligence,deep learning,machine learning,computer-aided diagnosis,skeletal imaging,fracture,bone tumor,osteoporosis,osteoarthritis,synovitis,spinal,cartilage,classification,detection,segmentation”。按照入选标准,最终纳入76篇文献进行综述。
结果与结论:深度学习模型已成为骨骼影像诊断的有力工具,逐渐获得了临床医师们的认可,提高了骨骼影像诊断效率。深度学习技术利用图像特征捕捉能力,有助于提升骨折、骨肿瘤、骨质疏松、骨关节炎、滑膜炎及脊柱病变等多种疾病的临床诊断效果,为临床医生决策提供参考依据。尽管深度学习诊断应用极具潜力,但容易出现模型泛化能力不足的问题,严重依赖大量标注数据,导致模型缺少信服力,从而阻碍了其临床推广应用。未来的研究应侧重于提升深度学习模型的鲁棒性,提升泛化能力。总之,深度学习应用于临床骨骼影像诊断有一定参考价值。


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: ">骨骼影像, 深度学习, 人工智能, 医学影像诊断, 骨科疾病, 综述

Abstract: BACKGROUND: Deep learning methods have made breakthrough progress in the field of bone imaging diagnosis. They have overcome the problems of easy misdiagnosis and low efficiency in traditional bone imaging diagnosis methods, and are conducive to the popularization of intelligent diagnosis methods in orthopedics.
OBJECTIVE: To review the application, advantages and disadvantages of deep learning in the diagnosis of common bone diseases. 
METHODS: Literature published from January 2021 to June 2025 on deep learning-assisted skeletal image diagnosis was retrieved from CNKI, WanFang, PubMed, and Web of Science databases. Chinese and English search terms included “artificial intelligence, deep learning, machine learning, computer-aided diagnosis, skeletal imaging, fracture, bone tumor, osteoporosis, osteoarthritis, synovitis, spinal, cartilage, classification, detection, segmentation.” According to the inclusion criteria, 76 articles were finally included in this review.
RESULTS AND CONCLUSION: Deep learning models have become powerful tools for bone imaging diagnosis and are gradually gaining recognition from clinicians, improving the efficiency of bone imaging diagnosis. Deep learning technology uses its image feature capture ability to help improve the clinical diagnosis of fractures, bone tumors, osteoporosis, osteoarthritis, synovitis, spinal lesions and other diseases, providing reference for clinicians to make decisions. Although deep learning diagnostic applications have great potential, they are prone to the problem of insufficient generalization ability of the model, relying heavily on a large amount of labeled data, which leads to a lack of credibility of the model and thus hinders its clinical promotion and application. Future research should focus on enhancing the robustness of models and improving their generalization ability. In conclusion, deep learning has certain reference value in clinical skeletal imaging diagnosis.

Key words: ">skeletal image, deep learning, artificial intelligence, medical imaging diagnosis, orthopedic diseases, review ,

中图分类号: