中国组织工程研究 ›› 2025, Vol. 29 ›› Issue (33): 7055-7062.doi: 10.12307/2025.714

• 骨与关节有限元分析Finite element analysis of bones and joints • 上一篇    下一篇

基于半自动分割技术的膝关节有限元建模

阎  峰,张  楠,孟庆华,鲍春雨,叶礼新,喻  佳   

  1. 天津体育学院,天津市  301617
  • 收稿日期:2024-06-11 接受日期:2024-09-12 出版日期:2025-11-28 发布日期:2025-04-12
  • 通讯作者: 孟庆华,博士,教授,天津体育学院,天津市 301617
  • 作者简介:阎峰,男,1975年生,天津市人,汉族,1994年天津师范大学毕业,讲师,主要从事有限元及体育大数据技术研究。
  • 基金资助:
    国家自然科学基金项目(11372223,11102135),项目负责人:孟庆华;天津市自然科学基金项目(17JCZDJC36000),项目负责人:鲍春雨;天津市自然科学基金项目(18JCZDJC35900),项目负责人:孟庆华;国家体育总局科技创新项目(22KJCX077),项目负责人:鲍春雨;天津市研究生创新项目(2022SKYZ318),项目负责人:张楠

Finite element modeling of knee joint based on semi-automatic segmentation technology

Yan Feng, Zhang Nan, Meng Qinghua, Bao Chunyu, Ye Lixin, Yu Jia   

  1. Tianjin University of Sport, Tianjin 301617, China
  • Received:2024-06-11 Accepted:2024-09-12 Online:2025-11-28 Published:2025-04-12
  • Contact: Meng Qinghua, PhD, Professor, Tianjin University of Sport, Tianjin 301617, China
  • About author:Yan Feng, Lecturer, Tianjin University of Sport, Tianjin 301617, China
  • Supported by:
    National Natural Science Foundation of China, Nos. 11372223, 11102135 (to MQH); Tianjin Natural Science Foundation, No. 17JCZDJC36000 (to BCY), 18JCZDJC35900 (to MQH); Science and Technology Innovation Project of General Administration of Sport of China, No. 22KJCX077 (to BCY); Tianjin Graduate Innovation Project, No. 2022SKYZ318 (to ZN)

摘要:


文题释义:

3D Swin UNETR:一种新的基于3D变压器的模型,称为Swin UNEt Transformer(Swin UNETR),具有用于自我监督前训练的分层编码器,为学习人体解剖学的基本模式定制代理任务。
统计形状模型:一组形状(训练集)的“统计模型”能够精简地表达组内形状的变化模式。统计模型最初用于图像自动分割,随后又在模式识别、计算机动画和医疗诊断等领域获得了十分广泛的应用。创建统计模型归结为搜寻所有形状的对应状态,进而又转为一个优化问题,其目标函数是形状对应质量的度量。在优化迭代的过程中,形状对应状态的更新是通过在参数域内的重新参数化实现的。


背景:膝关节有限元建模可以深入了解膝关节力学,但其复杂的图像分割工作对于研究人员来说较为困难。随着深度学习技术的发展,深度学习技术已经广泛应用于膝关节有限元建模中。

目的:使用3D Swin UNETR结合统计形状模型半自动分割技术来代替膝关节有限元建模中人工分割的步骤。
方法:基于MR建立手动(人工)膝关节有限元模型和3D Swin UNETR+统计形状模型分割的半自动膝关节有限元模型,对2个模型施加相同的载荷与边界条件,通过计算Dice相似系数、平均距离以及比较2个模型的等效应力峰值、最大主应力和最大剪切应力来进行验证。

结果与结论:①半自动分割模型股骨和胫骨的Dice相似系数均超过98%,平均距离均≤(0.35±0.08) mm;②对手动和半自动有限元模型股骨顶端施加纵向荷载750 N及10 Nm内翻力矩,手动有限元模型半月板等效应力峰值、最大主应力、最大剪切应力为14.12,18.54,7.35 MPa;股骨软骨等效应力峰值、最大主应力、最大剪切应力为2.22,2.15,1.18 MPa;胫骨软骨等效应力峰值、最大主应力、最大剪切应力为2.50,1.91,1.41 MPa;半自动有限元模型半月板等效应力峰值、最大主应力、最大剪切应力为14.93,18.53,7.75 MPa;股骨软骨等效应力峰值、最大主应力、最大剪切应力为2.26,2.18,1.20 MPa;胫骨软骨等效应力峰值、最大主应力、最大剪切应力为2.60,1.91,1.46 MPa;手动和半自动有限元模型等效应力峰值、最大主应力和最大剪切应力之间基本一致,差异无显著性意义(P > 0.05);③此次研究所提出的半自动分割技术在创建准确的膝关节有限元模型方面可代替人工分割。

https://orcid.org/0009-0002-6856-1608(阎峰)

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: 膝关节, 有限元模型, 3D Swin UNETR, 统计形状模型, 半自动分割, 人工分割

Abstract: BACKGROUND: Knee finite element modelling can provide insight into knee mechanics, but its complex image segmentation is more difficult for researchers. With the development of deep learning techniques, deep learning techniques have been widely used in knee joint finite element modelling. 
OBJECTIVE: To replace the manual segmentation step in finite element modelling of the knee joint by using 3D Swin UNETR in combination with a semi-automatic segmentation technique for statistical shape models.
METHODS: Manual (artificial) knee joint finite element model was developed based on MR and semi-automatic knee joint finite element model was developed based on 3D Swin UNETR+ statistical shape model segmentation. The same loads and boundary conditions were applied to both models. Validation was performed by calculating the Dice similarity coefficient, mean distance, and comparing the peak equivalent stresses, maximum principal stresses, and maximum shear stresses of the two models.
RESULTS AND CONCLUSION: (1) The Dice similarity coefficients of the manual and semi-automatic segmented femur and tibia were more than 98%, and the average distances were less than or equal to (0.35±0.08) mm. (2) With the longitudinal load of 750 N and 10 Nm internal overturning moment applied to the femur tip of both manual and semi-automatic finite element models, the peak equivalent stress, maximum principal stress, and maximum shear stresses of meniscus in manual finite element model were 14.12, 18.54, and 7.35 MPa; peak equivalent force, maximum principal stress, and maximum shear stress of femoral cartilage were 2.22, 2.15, and 1.18 MPa; peak equivalent force, maximum principal stress, and maximum shear stress of tibial cartilage were 2.50, 1.91, and 1.41 MPa; semi-automatic finite element model of meniscus: peak equivalent force, maximum principal stress, and maximum shear stress were 14.93, 18.53, and 7.75 MPa. The peak equivalent force, maximum principal stress, and maximum shear stress of femoral cartilage were 2.26, 2.18, and 1.20 MPa; the peak equivalent stress, maximum principal stress, and maximum shear stress of tibial cartilage were 2.60, 1.91, and 1.46 MPa. The peak equivalent stress, maximum principal stress, and maximum shear stress of manual and semi-automatic finite element models were basically consistent, with no significant difference (P > 0.05). (3) The semi-automatic segmentation technique proposed in this study can replace manual segmentation in creating accurate finite element models of the knee joint.

Key words: knee joint, finite element model, 3D Swin UNETR, statistical shape model, semi-automatic segmentation, manual segmentation

中图分类号: