基于CT数据的人工智能辅助术前规划在全髋关节置换术中的应用  

Application of artificial intelligence-assisted preoperative planning based on CT data in total hip arthroplasty

作　　者：容向宾[1] 曾平[2] 刘金富 孙斌 田照 丁强 陆智豪 RONG Xiangbin;ZENG Ping;LIU Jinfu;SUN Bin;TIAN Zhao;DING Qiang;LU Zhihao(Graduate School of Guangxi University of Chinese Medicine,Nanning,Guangxi 530200,China)

机构地区：[1]广西中医药大学研究生院,广西南宁530200 [2]广西中医药大学第一附属医院仙葫院区骨二科,广西南宁530000

出　　处：《中国骨与关节损伤杂志》2024年第6期571-578,共8页Chinese Journal of Bone and Joint Injury

基　　金：国家自然科学基金项目(82160913);广西中医药大学博士研究生创新项目(YCBZ2023155)。

摘　　要：目的观察基于CT数据的人工智能辅助术前规划在全髋关节置换术中的应用效果。方法回顾性分析自2021-01-2022-12采用基于CT数据的人工智能辅助术前规划与传统测量规划方法行全髋关节置换术的240例髋部疾病患者,根据术前规划方法不同分为两组,观察组(n=120)采用人工智能AIHIP系统进行术前规划,对照组(n=120)采用传统测量方式进行术前规划。比较两组术中出血量、手术时间、术后并发症发生率、术前规划与术中实际假体型号选择符合率,以及术后尖肩距、双下肢长度差、股骨偏心距、联合偏心距、旋转中心位移差、髋关节功能Harris评分。结果所有患者均获得随访,随访时间6~20个月,平均14个月。观察组术中出血量、手术时间均少于对照组且并发症发生率低于对照组,差异有统计学意义(P<0.05)。观察组假体型号规划与实际符合率比对照组高,而且术后尖肩距、双下肢长度差、股骨偏心距、联合偏心距均小于对照组,差异有统计学意义(P<0.05)。观察组术后1、3个月髋关节功能Harris评分高于对照组,差异有统计学意义(P<0.05),两组术后6个月髋关节功能Harris评分差异无统计学意义(P>0.05)。结论基于CT数据的人工智能辅助术前规划在全髋关节置换术中的应用效果满意,使手术更具微创化、精准化,不仅术后并发症发生率更低,而且术后髋关节功能恢复更优。Objective To observe the application effect of preoperative planning assisted by artificial intelligence based on CT data in total hip arthroplasty.Methods A retrospective analysis was performed on 240 patients with hip diseases who underwent total hip arthroplasty from January 2021 to December 2022 using artificial intelligence assisted preoperative planning based on CT data and the traditional measurement planning method.According to different preoperative planning methods,they were divided into two groups.The observation group(n=120)used artificial intelligence AIHIP system for preoperative planning and in the control group(n=120),the traditional measurement method was used for preoperative planning.The intraoperative blood loss,operation time,incidence of postoperative complications,coincidence rate of preoperative planning and actual prosthesis selection during operation,and postoperative apical shoulder distance,leg length difference,femoral offset,combined offset,rotation center displacement difference,hip joint function Harris score were compared between the two groups.Results All patients were followed up for 6 to 20 months,with an average of 14 months.The intraoperative blood loss and operation time of the observation group were less than those of the control group,and the incidence of complications was lower than that of the control group,and the differences were statistically significant(P<0.05).The coincidence rate of prosthesis size planning and actual selection in the observation group was higher than that in the control group,and the postoperative cusp-shoulder distance,the length difference of both lower limbs,femoral offset and combined offset were lower than those in the control group,and the differences were statistically significant(P<0.05).The Harris score of hip joint function at 1 and 3 months after operation in the observation group was higher than that in the control group,and the differences were statistically significant(P<0.05).There was no statistically significant difference in the

关 键 词：全髋关节置换 CT数据 人工智能 术前规划 传统测量 

分 类 号：R687.1[医药卫生—骨科学]