Objective To investigate the accuracy of artificial intelligence three-dimensional planning software in the selection of prosthetic size in total hip arthroplasty and analyze the factors affecting the accuracy.Methods A total of 57 patients (20 males and 37 females) who underwent unilateral primary total hip arthroplasty were selected.The X-ray and CT 3D reconstruction image data of the affected hip joint were collected from August 2021 to June 2022 before operation.A resident make a preoperative planning for each total hip arthroplasty using both the traditional templating and artificial intelligence three-dimensional preoperative planning software.We analyzed the accuracy of implant size prediction using two methods.The coincidence rate of the two methods was compared.At the same time,whether the BMI and leg length discrepancy of patients were the factors affecting the accuracy of measurement.Results The coincidence rates of 0,±1 and ±2 prosthesis size measurements of artificial intelligence planning on the acetabular side were 82.46%,10.53% and 7.01%,respectively.The acetabular concordance rate of traditional template was 42.11%,43.86% and 14.03%.The difference between the two groups was statistically significant (P<0.05).The concordance rate of artificial intelligence femoral side measurement in 0,±1,±2 model was 77.19%,19.30%,3.51%.The coincidence rate of traditional template was 54.39%,36.84% and 8.77%.The difference between the two groups was statistically significant (P<0.05).The prediction of acetabular cup model by artificial intelligence 3D programming system was highly correlated with the actual model(r=0.886,P<0.05),and a high correlation between prediction of femur prosthesis size and actual application type (r=0.874,P<0.05).There was no significant correlation between BMI and the accuracy of artificial intelligence measurement of mortar cup and femoral stem prosthesis (P>0.05).And no significant correlation between the lower limb length difference and the accuracy of artificial intelligence measurement of socket and femoral stem prosthesis (P>0.05).Conclusion Artificial intelligence three-dimensional planning has a better predictive effect on the selection of prosthesis size in total hip arthroplasty than film template measurement.There is no significant correlation between BMI and lower limb length difference and measurement accuracy.
[1]郭盛君,周一新,张亮等.327例初次人工髋关节置换术失败原因探讨[J].中华外科杂志,2009,47(3):168-171.
[2]何斌,章淼锋,沈跃,等.人工髋关节置换术后初次翻修的原因分析及翻修术疗效评估[J].中华骨科杂志,2019,39(15):909-917.
[3]Tezuka T,Inaba Y,Kobayashi N,et al.Effects of hip joint center location and femoral offset on abductor muscle strength after total hip arthroplasty[J].Mod Rheumatol,2015,25(4):630-636.
[4]De Thomasson E,Mazel C,Guingand O,et al.Value of preoperative planning in total hip arthroplasty[J].Rev Chir Orthop Reparatrice Appar Mot,2002,88(3):229-235.
[5]Bono JV.Digital templating in total hip arthroplasty[J].J Bone Joint Surg(Am),2004,86(2):118-122.
[6]陈要林,邵宏翊,郭盛杰,等.模板测量在全髋关节置换术前计划中的应用及可能影响测量准确性的因素探讨[J].中华骨与关节外科杂志,2018,11(7):512-517.
[7]Petretta R,Strelzow J,Ohly NE,et al.Acetate templating on digital images is more accurate than computer-based templating for total hip arthroplasty[J].Clin Orthop Relat Res,2015,473(12):3752-3759
[8]裴国献.数字骨科:骨科领域的第三次技术浪潮[J].中华创伤骨科杂 志,2019,21(1):3-5.
[9]徐征宇,杜俊炜,姜瑶等.全髋关节置换术术前模板测量与规划研究进展[J].中华关节外科杂志(电子版),2021,15(1):83-91.
[10]White SP,Bainbridge J,Smith EJ.Assessment of magnification of digital pelvic radiographs in total hip arthroplasty using templating software[J].Ann R Coll Surg Engl,2008,90(7):592-596.
[11]Shichman I,Factor S,Shaked O,et al.Effects of surgeon experience and patient characteristics on accuracy of digital pre-operative planning in total hip arthroplasty[J].Int Orthop,2020,44(10):1951-1956.
[12]聂茂,黄伟,梁熙等.全髋关节置换术前模板测量的准确性分析[J].中华创伤杂志,2009,25(8):705-708.
[13]Conn KS,Clarke MT,Hallett JP.A simple guide to determine the magnification of radiographs and to improve the accuracy of preoperative templating[J].J Bone Joint Surg(Br),2002,84(2):269-272.
[14]Mirghaderi SP,Sharifpour S,Moharrami A,et al.Determining the accuracy of preoperative total hip replacement 2D templating using the medi CAD software[J].J Orthop Surg Res,2022,17(1):222.
[15]Osmani F,Thakkar S,Ramme A,et al.Variance in predicted cup size by 2-dimensional vs 3-dimensional computerized tomography-based templating in primary total hip arthroplasty[J].Arthroplast Today,2017,3(4):289-293.
[16]Wako Y,Nakamura J,Miura M,et al.Interobserver and intraobserver reliability of three-dimensional preoperative planning software in total hip arthroplasty[J].J Arthroplasty,2018,33(2):601-607.
[17]吴东,刘星宇,张逸凌,等.人工智能辅助全髋关节置换术三维规划系统的研发及临床应用研究[J].中国修复重建外科志,2020,34(9):1077-1084.
[18]Adamczyk A,Laboudie P,Nessek H,et al.Accuracy of digital templating in uncemented primary total hip arthroplasty:Which factors are associated with accuracy of preoperative planning?[J].Hip Int,2022(19):11207000221082026.
[19]Imai N,Takubo R,Suzuki H,Shimada H,et al.Accuracy of acetabular cup placement using CT-based navigation in total hip arthroplasty:Comparison between obese and nonobese patients[J].J Orthop Sci,2019,24(3):482-487.
[20]芦北极,孙俊英,施勤等.全髋关节成形术后的偏心距测量对临床功能的影响[J].中国矫形外科杂志,2012,20(14):1282-1286.
[21]Sheha ED,Steinhaus ME,Kim HJ,et al.Leglength discrepancy,Functional scoliosis,and low back pain[J].JBJS Rev,2018,6(8):e6.
[22]张跃国,杨柳,刘传伟,等.全髋关节置换后的双下肢不等长与假体选择置入位置及软组织张力等因素的关系[J].中国组织工程研究与临床康复,2008,12(17):3305-3308.
[23]Jablonski M,Posturzyńska A,Gorzelak M,et al.Problem and tolerance of leg lengthening after total hip replacement[J].Chir Narzadow Ruchu Ortop Pol,2008,73(6):351-354.