
浏览全部资源
扫码关注微信
1.陆军军医大学第二附属医院骨科关节疾病与运动医学部,重庆 400037
2.解放军联勤保障部队第964医院骨科,吉林 长春 130062
3.陆军军医大学生物医学工程与影像医学系,重庆 400038
张瑗,E-mail:zhangyuan@tmmu.edu.cn
收稿日期:2024-10-08,
纸质出版日期:2025-07-25
移动端阅览
程治铭,许中华,满孝军等.膝关节软骨厚度预测模型构建的可行性研究[J].局解手术学杂志,2025,34(07):563-569.
CHENG Zhi-ming,XU Zhong-hua,MAN Xiao-jun,et al.Feasibility study on the construction of predictive models of knee joint cartilage thickness[J].JOURNAL OF REGIONAL ANATOMY AND OPERATIVE SURGERY,2025,34(07):563-569.
程治铭,许中华,满孝军等.膝关节软骨厚度预测模型构建的可行性研究[J].局解手术学杂志,2025,34(07):563-569. DOI: 10.11659/jjssx.10E024013.
CHENG Zhi-ming,XU Zhong-hua,MAN Xiao-jun,et al.Feasibility study on the construction of predictive models of knee joint cartilage thickness[J].JOURNAL OF REGIONAL ANATOMY AND OPERATIVE SURGERY,2025,34(07):563-569. DOI: 10.11659/jjssx.10E024013.
目的
2
采用不同方法测定膝关节软骨厚度,探讨数据集数学统计模型预测软骨厚度的可行性。
方法
2
选取2023年3月至2024年3月于陆军军医大学第二附属医院诊断为膝关节骨关节炎(OA)合并内翻畸形、并实施单侧全膝关节置换术的304例患者纳入研究,患者手术前后临床资料齐全。选择患者股骨远端外髁、外侧胫骨平台、股骨后内髁和股骨后外髁4个解剖学部位的健康软骨,基于术前MRI分析、机器人导航系统示踪、手术标本组织切片和电子标尺测定膝关节软骨厚度。收集患者人口学、疾病学和影像学基线指标构建数据集,并建立膝关节软骨厚度线性回归分析、主成分分析、最小绝对收缩和选择算子(
LASSO
)回归分析和
K
-最近邻算法(
KNN
)模型,用以预测软骨厚度的准确度(
accuracy
)、决定系数(
R
2
)和均方根误差(
RMSE
),并建立可预测软骨厚度的回归方程。
结果
2
术前MRI分析、机器人导航系统示踪和手术标本组织切片测得的膝关节软骨厚度与电子标尺结果比较差异均无统计学意义(
P
>
0.05)。线性回归模型、主成分分析模型、
LASSO
回归模型对膝关节软骨厚度的预测效率均未达到预期(
R
2
<
0.3,
RMSE
>
0.03)。
KNN
模型对于股骨远端外髁和外侧胫骨平台软骨厚度的预测效果不理想(
R
2
=0.23,
RMSE
=0.29),但存在潜在可预测价值(
accuracy
=0.21,
accuracy
=0.15)。
结论
2
基于个体参数的膝关节软骨厚度型预测模具有一定科学性,
KNN
模型的可行性较高。但因样本量不足、个体参数权重不清等原因,四种预测模型的效能不太理想,未能提供确定的预测方程,因此预测模型构建方案尚待进一步优化。
Objective
2
To determine the knee joint cartilage thickness using different methods and explore the feasibility of mathematical statistical models of dataset for the prediction of cartilage thickness.
Methods
2
A total of 304 patients diagnosed as knee osteoarthritis (OA) combined with varus deformity and undergoing unilateral total knee arthroplasty at the Second Affiliated Hospital of Army Medical University from March 2023 to March 2024 were selected for the study. All patients had complete preoperative and postoperative clinical data. The healthy cartilage at four anatomical sites of patients,including the distal femur lateral condyle,lateral tibial plateau,posterior medial femoral condyle,and posterior lateral femoral condyle were selected,and the knee joint cartilage thickness was determined based on preoperative MRI analysis,robotic navigation system traci
ng,tissue section of surgical specimen and digital vernier caliper. The baseline indicators of demographics,disease and imaging ffor patients were collected to construct a dataset,and four models of linear regression analysis,principal component analysis,
Least Absolute Shrinkage and Selection Operator
(
LASSO
) regression analysis,and
K
-
nearest neighbors
(
KNN
) analysis were established for predicting the accuracy,determination coefficient (
R
2
) and
root mean square error
(
RMSE
),and the regression equation for predicting cartilage thickness was established.
Results
2
The knee joint cartilage thicknesses determined by preoperative MRI analysis,robotic navigation system tracing,tissue section of surgical specimen had no statistically significant difference with that by digital vernier caliper (
P
>
0.05). The predictive efficiencies of models of linear regression analysis,principal component analysis,and
LASSO
regression analysis for the knee joint cartilage thickness all failed to meet the expectations (
R
2
<
0.3,
RMSE
>
0.03). The predictive effect of
KNN
model on the cartilage thickness of the distal femur lateral condyle and lateral tibial plateau was not ideal (
R
2
=0.23,
RMSE
=0.29),while it had potential predictive value (
accuracy
=0.21,
accuracy
=0.15).
Conclusion
2
The prediction model of knee joint cartilage thickness based on individual parameters has certain scientificity,and the feasibility of
KNN
model is relatively high. However,due to insufficient sample size and unclear individual parameter weight,the efficiencies of the four established prediction models are not ideal,which fails to provide definite prediction equation
s. Therefore,the construction scheme of the prediction model still needs to be further optimized.
Katz JN , Arant KR , Loeser RF . Diagnosis and treatment of hip and knee osteoarthritis:a review [J]. JAMA , 2021 , 325 ( 6 ): 568 - 578 . doi: 10.1001/jama.2020.22171 http://dx.doi.org/10.1001/jama.2020.22171 .
Yao Q , Wu X , Tao C , et al . Osteoarthritis:pathogenic signaling pathways and therapeutic targets [J]. Signal Transduct Target Ther , 2023 , 8 ( 1 ): 56 . doi: 10.1038/s41392-023-01330-w http://dx.doi.org/10.1038/s41392-023-01330-w .
Giurazza G , Caria C , Campi S , et al . Femoral cartilage thickness measured on MRI varies among individuals:time to deepen one of the principles of kinematic alignment in total knee arthroplasty:a systematic review [J]. Knee Surg Sports Traumatol Arthrosc , 2025 , 33 ( 2 ): 634 - 645 . doi: 10.1002/ksa.12408 http://dx.doi.org/10.1002/ksa.12408 .
Nam JH , Koh YG , Kim PS , et al . Effect of the presence of the articular cartilage on the femoral component rotation in total knee arthroplasty in female and varus osteoarthritis knees [J]. J Orthop Surg Res , 2020 , 15 ( 1 ): 499 . doi: 10.1186/s13018-020-02030-9 http://dx.doi.org/10.1186/s13018-020-02030-9 .
Niinimäki TT , Eskelinen A , Mann BS , et al . Survivorship of high tibial osteotomy in the treatment of osteoarthritis of the knee [J]. J Bone Joint Surg Br , 2012 , 94 ( 11 ): 1517 - 1521 . doi: 10.1302/0301-620x.94b11. 29601 http://dx.doi.org/10.1302/0301-620x.94b11.29601 .
Carr AJ , Robertsson O , Graves S , et al . Knee replacement [J]. Lancet , 2012 , 379 ( 9823 ): 1331 - 1340 . doi: 10.1016/s0140-6736(11)60752-6 http://dx.doi.org/10.1016/s0140-6736(11)60752-6 .
胡娜 , 张燕 , 盛敏 , 等 . 基于磁共振分区的健康膝关节软骨T2图 [J]. 中国医学科学院学报 , 2011 , 33 ( 1 ): 66 - 70 . doi: 10.3881/j.issn.1000-503X.2011.01.014 http://dx.doi.org/10.3881/j.issn.1000-503X.2011.01.014 .
唐艳华 , 徐贤 , 江波 , 等 . 3.0T磁共振成像对健康青年人膝关节软骨T2值及厚度的定量分析 [J]. 中国医学科学院学报 , 2013 , 35 ( 2 ): 131 - 135 . doi: 10.3881/j.issn.1000-503X.2013.02.001 http://dx.doi.org/10.3881/j.issn.1000-503X.2013.02.001 .
Guo J , Yan P , Qin Y , et al . Automated measurement and grading of knee cartilage thickness: a deep learning-based approach [J]. Front Med (Lausanne) , 2024 , 11 : 1337993 . doi: 10.3389/fmed.2024. 1337993 http://dx.doi.org/10.3389/fmed.2024.1337993 .
Li S , Zhao S , Zhang Y , et al . Source-free unsupervised adaptive segmentation for knee joint MRI [J]. Biomed Signal Process Control , 2024 , 92 : 6028 . doi: 10.1016/j.bspc.2024.106028 http://dx.doi.org/10.1016/j.bspc.2024.106028 .
Si L , Xuan K , Zhong J , et al . Knee cartilage thickness differs alongside ages: a 3-T magnetic resonance research upon 2,481 subjects via deep learning [J]. Front Med (Lausanne) , 2021 , 7 : 600049 . doi: 10.3389/fmed.2020.600049 http://dx.doi.org/10.3389/fmed.2020.600049 .
Jansen MP , Turmezei TD , Dattani K , et al . Cartilage thickness distribution and its dependence on demographic,radiographic,and MRI structural pathology in knee osteoarthritis-data from the IMI-APPROACH cohort [J]. Skeletal Radiol , 2025 . doi: 10.1007/s00256-025-04907-4 http://dx.doi.org/10.1007/s00256-025-04907-4 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621