人工智能辅助全髋关节置换三维术前规划准确性评价

doi:10.3877/cma.j.issn.1674-134X.2024.04.001

中华关节外科杂志(电子版) ›› 2024, Vol. 18 ›› Issue (04) : 431 -438. doi: 10.3877/cma.j.issn.1674-134X.2024.04.001

临床论著

人工智能辅助全髋关节置换三维术前规划准确性评价

孔德铭¹, 刘铮¹, 李睿², 钱文伟³, 王飞⁴, 蔡道章⁵, 柴伟²^,^†(

)

^1. 100853　北京，解放军医学院;100853　北京，解放军总医院第四医学中心骨科医学部;100853　北京，国家骨科与运动康复临床医学研究中心
^2. 100853　北京，解放军总医院第四医学中心骨科医学部;100853　北京，国家骨科与运动康复临床医学研究中心
^3. 100853　中国医学科学院北京协和医学院北京协和医院骨科
^4. 050000　石家庄，河北医科大学第三医院骨科
^5. 510630　广州，南方医科大学第三附属医院

收稿日期:2023-12-22 出版日期:2024-08-01
通信作者: 柴伟
基金资助:
国家自然科学基金联合重点项目(U22A20355)

Accuracy evaluation of artificial-intelligence assisted three dimensional preoperative planning for total hip arthroplasty

Deming Kong¹, Zheng Liu¹, Rui Li², Wenwei Qian³, Fei Wang⁴, Daozhang Cai⁵, Wei Chai²^,^†()

^1. Medical School of Chinese PLA, Beijing 100853, China;Senior Department of Orthopedics, the Fourth Medical Center of Chinese PLA General Hospital, Beijing 100853, China;National Clinical Research Center for Orthopedics, Sports Medicine & Rehabilitation, Beijing 100853, China
^2. Senior Department of Orthopedics, the Fourth Medical Center of Chinese PLA General Hospital, Beijing 100853, China;National Clinical Research Center for Orthopedics, Sports Medicine & Rehabilitation, Beijing 100853, China
^3. Department of Orthopaedics, Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing 100853, China
^4. Department of Orthopaedics, The Third Hospital of Hebei Medical University, Shijiazhuang 050000, China
^5. The Third Affiliated Hospital of Southern Medical University, Guangzhou 510630, China

Received:2023-12-22 Published:2024-08-01
Corresponding author: Wei Chai

全文 ( ) 下载PDF ( ) 导出引用

引用本文：

孔德铭, 刘铮, 李睿, 钱文伟, 王飞, 蔡道章, 柴伟. 人工智能辅助全髋关节置换三维术前规划准确性评价[J]. 中华关节外科杂志(电子版), 2024, 18(04): 431-438.

Deming Kong, Zheng Liu, Rui Li, Wenwei Qian, Fei Wang, Daozhang Cai, Wei Chai. Accuracy evaluation of artificial-intelligence assisted three dimensional preoperative planning for total hip arthroplasty[J]. Chinese Journal of Joint Surgery(Electronic Edition), 2024, 18(04): 431-438.

目的

基于人工智能技术辅助全髋关节置换术的三维规划系统（AI HIP）的临床应用准确性仍需进一步的验证，本文旨在研究在初次全髋关节置换术前使用AI HIP系统进行术前规划预测假体型号的准确性。

方法

纳入了解放军总医院第一医学中心、中国医学科学院北京协和医院、河北医科大学第三医院、南方医科大学第三附属医院在2021年8月至2022年8月拟行初次全髋关节置换术（THA）的患者作为研究对象，共纳入80位因髋关节疾病需行初次THA的患者，且术前影像符合规划要求，排除妊娠哺乳期妇女等不适合参加实验的患者。最终75例患者完成实验。实验组患者使用AI HIP进行THA术前规划，对照组患者使用传统基于X线模板测量方法。术前规划结果与术中实际使用假体型号进行比较，使用卡方检验和Fisher精确检验等进行统计学检验，以评价AI HIP系统规划髋臼杯以及股骨柄型号的准确性。

结果

实验组37例：其中男性22例，女性15例；左髋20例，右髋17例；年龄52（38，65）岁。对照组38例：男性25例、女性13例；左髋18例，右髋20例；年龄56（39，62）岁。实验组规划髋臼杯和股骨柄假体型号的完全准确率为89.19%（33/37）；其中髋臼杯规格准确率为97.30%（36/37），股骨柄规格准确率为89.19%（33/37）。对照组术前计划完全准确率为2.63%（1/38）；其中髋臼杯规格准确率为42.11%（16/38），股骨柄规格准确率为21.05%（8/38）。两组完全准确率差异均具有统计学意义（χ²=35.12 P<0.05）。

结论

与传统基于X线片模板测量方法相比，AI HIP 系统进行THA术前规划假体型号方面具有较高准确率和可重复性，能较准确地预测成人初次THA术使用的假体型号。

关键词: 关节成形术，置换，髋, 人工智能, 深度学习, 规划技术

Objective

To further verify the clinical application accuracy of the three-dimensional planning system assisted by artificial intelligence(AI HIP) in total hip arthroplasty (THA)by investigating the accuracy of AI HIP system for prosthesis size prediction before primary THA.

Methods

Patients who were scheduled for primary THA at PLA General Hospital First Medical Center, Peking Union Medical College Hospital, the Third Hospital of Hebei Medical University, and the Third Affiliated Hospital of Southern Medical University from August 2021 to August 2022 were included as research subjects. A total of 80 patients who needed primary THA due to hip joint diseases were included, and their preoperative imaging met the planning requirements. The patients who were pregnant or lactating and other reasons not suitable for the experiment were excluded. Finally, 75 patients completed the experiment. The experimental group used AI HIP system for pre-operative planning of THA, while the control group used the traditional X-ray template measurement method. The pre-operative planning results were compared with the actual prosthesis size used during surgery. Statistical tests such as chi square test and Fisher's exact test were used to evaluate the accuracy of the AI HIP system in planning the acetabular cup and femoral stem size.

Results

There were 37 cases in the experimental group: 22 males and 15 females, 20 left hips and 17 right hips, median age 52 (38, 65) years. There were 38 cases in the control group: 25 males and 13 females, 18 left hips and 20 right hips, median age 56 (39, 62) years. The overall accuracy rate of the experimental group in planning the acetabular cup and femoral stem prosthesis size was 89.19% (33/37); the acetabular cup size accuracy rate was 97.30% (36/37), and the femoral stem size accuracy rate was 89.19% (33/37). The overall accuracy rate of the control group in pre-operative planning was 2.63% (1/38); the acetabular cup size accuracy rate was 42.11% (16/38), and the femoral stem size accuracy rate was 21.05% (8/38). The difference in the overall accuracy rates between the two groups was statistically significant (χ²=35.12, P<0.05).

Conclusion

Compared to the traditional Xray template measurement method, the AI HIP system has higher accuracy and reproducibility in planning prosthesis size for pre-operative THA. It can accurately predict the prosthesis size used in primary THA in adults.

Key words: Arthroplasty, replacement, hip, Artificial intelligence, Deep learning, Planning technic

图1 纳入评估流程图

Figure 1 The flow chart of inclusion evaluation

图2 各中心病例数

Figure 2 Number of cases from different centers

图3 AI HIP软件术前规划流程图。图A为根据术前CT重建三维模型；图B为 AI HIP系统骨盆矫正图；图C为 AI HIP系统放置髋臼杯；图D 为AI HIP系统放置股骨柄；图E 为AI HIP系统进行模拟截骨及规划结果展示

Figure 3 Illustrations of preoperative planning performed by AI HIP system. A is reconstruction of 3D model according to CT before surgery; B is pelvic correction by AI HIP system; C is acetabular cups placed in the AI HIP system; D is femoral component placement in AIHIP system ; E is osteotomy simulation by AI HIP system and the planning results

表1 两组患者术前资料

Table 1 Preoperative data between the two groups

组别 Groups	例数 Number of case	年龄［岁，M（P₂₅，P₇₅）］ Age（year）	性别（男/女） Gender （male/female）	术侧（左/右） Surgical side （left/right）	术前诊断Diagnosis
组别 Groups	例数 Number of case	年龄［岁，M（P₂₅，P₇₅）］ Age（year）	性别（男/女） Gender （male/female）	术侧（左/右） Surgical side （left/right）	ONFH	OA	DDH	FNF	AS
实验组 Experimental group	37	52（38，65）	22/15	20/17	24	9	3	1	0
对照组 Control group	38	56（39，62）	25/13	18/20	23	10	2	2	1
统计值 Statistical value		Z=-0.558	χ²=0.072	χ²=0.335	χ²=1.594
P值		>0.05	>0.05	>0.05	>0.05

表1 两组患者术前资料

Table 1 Preoperative data between the two groups

组别 Groups	例数 Number of case	年龄［岁，M（P₂₅，P₇₅）］ Age（year）	性别（男/女） Gender （male/female）	术侧（左/右） Surgical side （left/right）	术前诊断Diagnosis
组别 Groups	例数 Number of case	年龄［岁，M（P₂₅，P₇₅）］ Age（year）	性别（男/女） Gender （male/female）	术侧（左/右） Surgical side （left/right）	ONFH	OA	DDH	FNF	AS
实验组 Experimental group	37	52（38，65）	22/15	20/17	24	9	3	1	0
对照组 Control group	38	56（39，62）	25/13	18/20	23	10	2	2	1
统计值 Statistical value		Z=-0.558	χ²=0.072	χ²=0.335	χ²=1.594
P值		>0.05	>0.05	>0.05	>0.05

图4 两组术前计划与术中实际应用假体型号匹配准确的例数。图A为髋臼侧；图B为股骨侧

Figure 4 The number of accurate matching cases of preoperative plan and actual prosthesis type in the two groups. A is acetabular side; B is femur side

表2 两组术前计划与术中实际应用假体型号

Table 2 Comparison of preoperative plan and actual application of prosthesis size between the two groups

组别 Groups	例数 Number of case	髋臼侧 Acetabular side			股骨侧 Femoral side
组别 Groups	例数 Number of case	0	±1	±2	0	±1	±2
实验组 Experimental group	37	36	1	0	33	2	2
对照组 Control group	38	16	14	8	8	13	17
χ²值		26.950			35.146
P值		<0.001			<0.001

表2 两组术前计划与术中实际应用假体型号

Table 2 Comparison of preoperative plan and actual application of prosthesis size between the two groups

组别 Groups	例数 Number of case	髋臼侧 Acetabular side			股骨侧 Femoral side
组别 Groups	例数 Number of case	0	±1	±2	0	±1	±2
实验组 Experimental group	37	36	1	0	33	2	2
对照组 Control group	38	16	14	8	8	13	17
χ²值		26.950			35.146
P值		<0.001			<0.001

［1］	Cross M，Smith E，Hoy D，et al. The global burden of hip and knee osteoarthritis: estimates from the global burden of disease 2010 study［J］. Ann Rheum Dis，2014,73(7):1323-1330.
［2］	Dimitriou D，Antoniadis A，Flury A，et al. Total hip arthroplasty improves the quality-adjusted life years in patients who exceeded the estimated life expectancy［J］. J Arthroplasty，2018,33(11):3484-3489.
［3］	Hegde V，Stambough JB，Levine BR，et al. Highlights of the 2022 American joint replacement registry annual report［J/OL］. Arthroplast Today，2023,21:101137. DOI: 10.1016/j.artd.2023.101137.
［4］	Gómez LFU，Gaitán-Lee H，Duarte MA，et al. Precision and accuracy of pre-surgical planning of non-cemented total hip replacement with calibrated digital images and acetates［J/OL］. J Orthop Surg Res，2021,16(1):431. DOI: 10.1186/s13018-021-02584-2.
［5］	Sidler-Maier CC，Waddell JP. Incidence and predisposing factors of periprosthetic proximal femoral fractures: a literature review［J］. Int Orthop，2015,39(9):1673-1682.
［6］	Lindberg-Larsen M，Jørgensen CC，Solgaard S，et al. Increased risk of intraoperative and early postoperative periprosthetic femoral fracture with uncemented stems［J］. Acta Orthop，2017,88(4):390-394.
［7］	Flecher X，Ollivier M，Argenson JN. Lower limb length and offset in total hip arthroplasty［J］. Orthop Traumatol Surg Res，2016,102(1 Suppl):S9-S20.
［8］	Rowan FE，Benjamin B，Pietrak JR，et al. Prevention of dislocation after total hip arthroplasty［J］. J Arthroplasty，2018,33(5):1316-1324.
［9］	Della Valle AG，Padgett DE，Salvati EA. Preoperative planning for primary total hip arthroplasty［J］. J Am Acad Orthop Surg，2005,13(7):455-462.
［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］	Linclau L，Dokter G，Peene P. Radiological aspects in preoperative planning and postoperative assessment of cementless total hip arthroplasty［J］. Acta Orthop Belg，1993,59(2):163-167.
［12］	Mainard D，Barbier O，Knafo Y，et al. Accuracy and reproducibility of preoperative three-dimensional planning for total hip arthroplasty using biplanar low-dose radiographs: a pilot study［J］. Orthop Traumatol Surg Res，2017,103(4):531-536.
［13］	Sariali E，Mauprivez R，Khiami F，et al. Accuracy of the preoperative planning for cementless total hip arthroplasty. A randomised comparison between three-dimensional computerised planning and conventional templating［J］. Orthop Traumatol Surg Res，2012,98(2):151-158.
［14］	Zeng Y，Lai OJ，Shen B，et al. Three-dimensional computerized preoperative planning of total hip arthroplasty with high-riding dislocation developmental dysplasia of the hip［J］. Orthop Surg，2014,6(2):95-102.
［15］	Ellapparadja P，Mahajan V，Deakin AH，et al. Reproduction of hip offset and leg length in navigated total hip arthroplasty: how accurate are we?［J］. J Arthroplasty，2015,30(6):1002-1007.
［16］	Wang X，Peng Y，Lu L，et al. ChestX-Ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases［C］//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）. Honolulu，HI，USA. IEEE，2017:3462-3471.
［17］	吴东，刘星宇，张逸凌，陈继营，唐佩福，柴伟. 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］. 中国修复重建外科杂志，2020,34(9):1077-1084.
［18］	Sugano N，Ohzono K，Nishii T，et al. Computed-tomography-based computer preoperative planning for total hip arthroplasty［J］. Comput Aided Surg，1998,3(6):320-324.
［19］	Wu P，Liu Q，Fu M，et al. Value of computed tomography-based three-dimensional pre-operative planning in cup placement in total hip arthroplasty with dysplastic acetabulum［J］. J Invest Surg，2019,32(7):607-613.
［20］	Inoue D，Kabata T，Maeda T，et al. Value of computed tomography-based three-dimensional surgical preoperative planning software in total hip arthroplasty with developmental dysplasia of the hip［J］. J Orthop Sci，2015,20(2):340-346.
［21］	Schiffner E，Latz D，Jungbluth P，et al. Is computerised 3D templating more accurate than 2D templating to predict size of components in primary total hip arthroplasty?［J］. Hip Int，2019,29(3):270-275.
［22］	Hassani H，Cherix S，Ek ET，et al. Comparisons of preoperative three-dimensional planning and surgical reconstruction in primary cementless total hip arthroplasty［J］. J Arthroplasty，2014,29(6):1273-1277.
［23］	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.
［24］	Zhang B，Li W，Li M，et al. The role of 3-dimensional preoperative planning for primary total hip arthroplasty based on artificial intelligence technology to different surgeons: a retrospective cohort study［J/OL］. Medicine，2023,102(25):e34113. DOI: 10.1097/MD.0000000000034113.
［25］	夏天卫，刘星宇，刘金柱，等. 人工智能术前规划系统辅助人工全髋关节置换术治疗成人 Crowe Ⅳ型节先天性髋关发育不良的疗效研究［J］. 中国修复重建外科杂志，2021,35(10):1265-1272.
［26］	Huo J，Huang G，Han D，et al. Value of 3D preoperative planning for primary total hip arthroplasty based on artificial intelligence technology［J/OL］. J Orthop Surg Res，2021,16(1):156. DOI: 10.1186/s13018-021-02294-9.
［27］	米尔阿地力·麦麦提依明，依力哈木江·吾斯曼，孙荣鑫，艾尔西丁·阿不来提. 人工智能术前规划系统在人工全髋关节置换术治疗成人发育性髋关节发育不良中的应用研究［J］. 中国修复重建外科杂志，2023,37(1):25-30.
［28］	席立成，方怀玺. 全髋关节置换人工智能三维术前规划的临床应用［J］. 中国矫形外科杂志，2024,32(1):18-23.
［29］	杨滨，张克，袁亮，等. 三维术前规划在全髋关节置换术中的应用［J］. 中国矫形外科杂志，2022,30(7):653-656.
［30］	吴迪. 人工智能三维规划软件在全髋关节置换术假体测量中的临床研究［D］. 合肥: 安徽医科大学，2023.

[1]	李洋, 蔡金玉, 党晓智, 常婉英, 巨艳, 高毅, 宋宏萍. 基于深度学习的乳腺超声应变弹性图像生成模型的应用研究[J]. 中华医学超声杂志（电子版）, 2024, 21(06): 563-570.
[2]	杨敬武, 周美君, 陈雨凡, 李素淑, 何燕妮, 崔楠, 刘红梅. 人工智能超声结合品管圈活动对低年资超声医师甲状腺结节风险评估能力的作用[J]. 中华医学超声杂志（电子版）, 2024, 21(05): 522-526.
[3]	罗刚, 泮思林, 孙玲玉, 李志新, 陈涛涛, 乔思波, 庞善臣. 一种新型语义网络分析模型对室间隔完整型肺动脉闭锁和危重肺动脉瓣狭窄胎儿右心发育不良程度的评价作用[J]. 中华医学超声杂志（电子版）, 2024, 21(04): 377-383.
[4]	伯小皖, 郭乐杭, 余松远, 李明宙, 孙丽萍. 甲状腺结节人工智能自动分割和分类系统的建立和验证[J]. 中华医学超声杂志（电子版）, 2024, 21(03): 304-309.
[5]	刘晓凡. 老年股骨头坏死髋关节置换术后康复应用多维度干预[J]. 中华关节外科杂志(电子版), 2024, 18(03): 314-319.
[6]	刘正宇, 刘春风, 王振. 改良后外侧入路半髋置换治疗股骨颈骨折的早期疗效[J]. 中华关节外科杂志(电子版), 2024, 18(03): 409-413.
[7]	苏博兴, 肖博, 李建兴. 2024年美国泌尿外科学会年会结石领域手术治疗相关热点研究及解读[J]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(04): 303-308.
[8]	莫林键, 杨舒博, 农卫赟, 程继文. 人工智能虚拟数字医师在钬激光前列腺剜除日间手术患教管理中的应用[J]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(04): 318-322.
[9]	阮星星, 黄智渊, 刘芙香, 狄金明. 从临床医师诊治患者的思路出发撰写临床研究论文[J]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(04): 397-401.
[10]	李梦阳, 张恩犁, 吴俊杰, 赵之明. 人工智能视觉图像分割在腔镜外科教学中的应用[J]. 中华腔镜外科杂志(电子版), 2024, 17(03): 129-134.
[11]	彭子洋, 王志博, 王丹, 彭浩茜, 王蕾, 彭薇, 王娟娟, 李宇, 刘学民, 吴荣谦, 向俊西, 吕毅. 智能化辅助图像实时去雾技术在腹腔镜胆囊切除术中的应用[J]. 中华肝脏外科手术学电子杂志, 2024, 13(03): 328-333.
[12]	陈健, 周静洁, 夏开建, 王甘红, 刘罗杰, 徐晓丹. 基于卷积神经网络实现结直肠息肉的实时检测与自动NICE分型（附视频）[J]. 中华结直肠疾病电子杂志, 2024, 13(03): 217-228.
[13]	胡兵. 食道早癌内镜黏膜下剥离术(ESD)[J]. 中华胃肠内镜电子杂志, 2024, 11(03): 216-216.
[14]	张玮玮, 霍晓川. 人工智能时代医学生批判性思维培养的重要性[J]. 中华脑血管病杂志(电子版), 2024, 18(04): 357-359.
[15]	林一鑫, 董晶, 贾建文, 黄菊梅, 武军元, 王双坤, 柳云鹏, 汪阳. 基于人工智能分析颈内动脉颅外段迂曲特征及对称性的应用性评价[J]. 中华脑血管病杂志(电子版), 2024, 18(03): 202-209.

阅读次数

全文

摘要

选择文件类型/文献管理软件名称

选择包含的内容

Accuracy evaluation of artificial-intelligence assisted three dimensional preoperative planning for total hip arthroplasty

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

Accuracy evaluation of artificial-intelligence assisted three dimensional preoperative planning for total hip arthroplasty