中国组织工程研究

中国组织工程研究 ›› 2026, Vol. 30 ›› Issue (21): 5589-5596.doi: 10.12307/2026.732

• 骨与关节图像与影像 bone and joint imaging • 上一篇    下一篇

AI算法分析后交叉韧带胫骨撕脱骨折CT三维图像诊断及精准评估

成永忠1，2，李  锐1，罗想利3，王  璠2，陈  洋1，闫  威1   

  1. 1中国中医科学院望京医院，北京市  100102；2南阳市中医院独山院区，河南省南阳市  473000；3甘肃省人民医院，甘肃省兰州市  730099
  • 接受日期:2025-07-29 出版日期:2026-07-28 发布日期:2026-03-05
  • 通讯作者: 闫威，硕士，副主任医师，中国中医科学院望京医院，北京市 100102
  • 作者简介:成永忠，男，1968年生，河北省唐山市人，汉族，2005年中国中医研究院毕业，博士，主任医师，主要从事CO接骨机器人相关研究。
  • 基金资助:
    中国中医科学院科技创新工程重点协同攻关项目医工交叉课题(CI2023C004YG)，项目负责人：成永忠；2023年南阳市科技攻关项目(23JCQY2060)，项目负责人：陈洋

AI algorithm analysis for CT three-dimensional diagnosis and accurate assessment of posterior cruciate ligament tibial avulsion fractures

Cheng Yongzhong1, 2, Li Rui1, Luo Xiangli3, Wang Fan2, Chen Yang1, Yan Wei1   

  1. 1Wangjing Hospital, China Academy of Chinese Medical Sciences, Beijing 100102, China; 2Dushan Branch of Nanyang Hospital of Traditional Chinese Medicine, Nanyang 473000, Henan Province, China; 3Gansu Provincial People's Hospital, Lanzhou 730099, Gansu Province, China
  • Accepted:2025-07-29 Online:2026-07-28 Published:2026-03-05
  • Contact: Yan Wei, MS, Associate chief physician, Wangjing Hospital, China Academy of Chinese Medical Sciences, Beijing 100102, China
  • About author:Cheng Yongzhong, MD, Chief physician, Wangjing Hospital, China Academy of Chinese Medical Sciences, Beijing 100102, China; Dushan Branch of Nanyang Hospital of Traditional Chinese Medicine, Nanyang 473000, Henan Province, China
  • Supported by:
    Key Collaborative Research Project on Medical-Engineering Interdisciplinary Research of Science and Technology Innovation Program of China Academy of Chinese Medical Sciences, No. CI2023C004YG (to CYZ); 2023 Nanyang City Science and Technology Project, No. 23JCQY2060 (to CY)

PDF

4

摘要：

文题释义：

AI算法：用于模拟、延伸和扩展人的智能的理论、方法、技术及应用系统，在医学领域常用于医学图像处理、预测治疗反应、辅助诊断。此次研究使用的算法应用场景为医学图像处理中的病灶自动定位与识别。
后交叉韧带胫骨撕脱骨折：指后交叉韧带在胫骨止点处受暴力牵拉导致的骨块分离，常用Meyers分型：Ⅰ型(无移位)、Ⅱ型(部分移位)、Ⅲ型(完全移位)。

摘要
背景：后交叉韧带附着点撕脱骨折的手术决策高度依赖影像学评估，传统方法依赖CT影像进行主观判读，存在三维空间位移参数量化困难、旋转角度评估精度不足等局限，鉴于AI技术的发展，有必要开发基于AI算法的自动化、智能化影像识别软件。
目的：探讨AI算法在CT三维图像中对后交叉韧带胫骨撕脱骨折的智能诊断能力及其对骨折块三维参数的精准评估效能。
方法：回顾性纳入2022-12-01/2024-08-30在中国中医科学院望京医院就诊的24例后交叉韧带胫骨撕脱骨折患者的膝关节CT数据，使用自主研发的AI影像识别软件进行三维重建、骨折点智能识别及模拟复位，获取骨折块在X、Y、Z轴上的平移和旋转参数。与传统放射阅片软件(PACS系统)测量结果进行对比，采用秩和检验、Bland-Altman分析及线性回归模型评估两种方法的一致性，并计算变异系数验证软件稳定性。
结果与结论：①AI软件与传统方法测量的骨折块位移(X/Y/Z轴平移及旋转)差异均无显著性意义(P > 0.05)；②Bland-Altman分析显示两种方法一致性良好，差异均无显著性意义(P > 0.05)；③X、Y、Z轴位移、角度两组拟合情况线性回归模型R²值均> 0.99；④AI软件重复3次骨折点识别的变异系数显示：总骨折识别时21例影像资料的变异系数< 20%，识别关节面骨折点时18例变异系数< 20%；⑤表明AI影像识别软件可精准量化后交叉韧带撕脱骨折块的三维参数，其测量结果与传统方法一致且稳定性良好，可辅助医生判断移位程度，为术前规划提供精准数据支持；该软件在撕脱骨折中有良好的应用前景，未来需扩大样本量并进一步验证其对手术疗效的影响。



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: 后交叉韧带撕脱骨折, 人工智能, CT影像识别, 三维测量, 术前规划

Abstract: BACKGROUND: Surgical decision-making for posterior cruciate ligament avulsion fractures is highly dependent on imaging evaluation. Traditional methods rely on subjective interpretation of CT images, which suffer from limitations such as difficulties in quantifying three-dimensional spatial displacement parameters and insufficient precision in assessing rotational angles. Given the advancements in artificial intelligence (AI) technology, there is a need to develop automated, intelligent image recognition software based on AI algorithms.
OBJECTIVE: To investigate the intelligent diagnostic capabilities of AI algorithms for posterior cruciate ligament tibial avulsion fractures in 3D CT images and their effectiveness in accurately assessing 3D parameters of fracture fragments.
METHODS: Knee CT data from 24 patients with posterior cruciate ligament tibial avulsion fractures who were treated at the Wangjing Hospital of the China Academy of Chinese Medical Sciences between December 1, 2022, and August 30, 2024, were retrospectively collected. Three-dimensional reconstruction, intelligent fracture point recognition, and simulated reduction were performed using self-developed AI image recognition software. Translational and rotational parameters of the fracture fragments along the X, Y, and Z axes were obtained. The results were compared with those obtained using picture archiving and communication system (PACS system). The consistency of the two methods was assessed using the rank sum test, Bland-Altman analysis, and linear regression model. The coefficient of variation was calculated to assess software stability.
RESULTS AND CONCLUSION: (1) No statistically significant differences were observed in fracture fragment displacement (translation/rotation along X/Y/Z axes) between AI and traditional methods (P > 0.05). (2) Bland-Altman analysis indicated good consistency between the two methods, with no significant differences (P > 0.05). (3) The R² values of the linear regression models for X, Y, and Z axis displacement and angle fitting were all > 0.99. (4) The coefficient of variation of the AI software for three repeated fracture point identifications showed that the coefficient of variation was < 20% for 21 imaging samples for total fracture identification and < 20% for 18 imaging samples for articular surface fracture identification. (5) This indicates that the AI image recognition software can accurately quantify the three-dimensional parameters of posterior cruciate ligament avulsion fracture fragments. Its measurement results are consistent with those of traditional methods and are highly stable. It can assist physicians in determining the degree of displacement and provide accurate data support for preoperative planning. This software has promising application prospects in the treatment of avulsion fractures. Future studies should expand the sample size and validate its impact on surgical outcomes.

Key words: posterior cruciate ligament avulsion fracture, artificial intelligence, CT image recognition, three-dimensional measurement, preoperative planning

中图分类号: