摘要
目的研发基于人工智能深度学习技术的髋关节翻修术前CT影像分割算法,并进行验证及初步应用。方法回顾性分析2019年4月至2022年10月于中国人民解放军总医院收治的有清晰CT数据资料的翻修病例706例,其中男520例,年龄(58.45±18.13)岁;女186例,年龄(52.23±16.23)岁。均为单侧,左侧402髋、右侧304髋。搭建transformer_unet卷积神经网络并使用Tensorflow 1.15进行网络模型训练,实现对翻修髋关节CT影像的智能分割。基于已研发的全髋关节置换术三维规划系统,初步构建髋关节翻修手术智能规划系统。分别采用dice overlap coefficient(DOC)、average surface distance(ASD)、Hausdorff distance(HD)参数对transformer_unet、全卷积网络(fully convolutional networks,FCN)、2D U-Net、和Deeplab v3+的分割精度进行评估,统计分割耗时对上述网络的分割效率进行评估。结果与FCN、2D U-Net和Deeplab v3+学习曲线相比,transformer_unet网络可通过较少的训练量实现更优的训练效果。Transformer_unet的DOC为95%±4%,HD为(3.35±1.03)mm,ASD为(1.38±0.02)mm;FCN分别为94%±4%、(4.83±1.90)mm、(1.42±0.03)mm;2D U-Net分别为93%±5%、(5.27±2.20)mm、(1.46±0.02)mm;Deeplab v3+分别为92%±4%、(6.12±1.84)mm、(1.52±0.03)mm。Transformer_unet各系数均优于其他三种卷积神经网络,差异有统计学意义(P<0.05)。在分割时间方面,transformer_unet分割耗时为(0.031±0.001)s,FCN为(0.038±0.002)s,2D U-Net为(0.042±0.001)s,Deeplab v3+为(0.048±0.002)s。Transformer_unet分割耗时少于其他三种卷积神经网络,差异有统计学意义(P<0.05)。将transformer_unet与全髋关节置换术三维规划系统相结合,可初步完成髋关节翻修手术智能规划系统的构建。结论与FCN、2D U-Net和Deeplab v3+相比,transformer_unet卷积神经网络可更精准、高效地完成对翻修髋关节CT影像的分割,有望为人工智能髋关节翻修手术术前规划及手术机器人相关领域的研究提供技术支撑。
Objective To develop a preoperative CT image segmentation algorithm based on artificial intelligence deep learning technology for total hip arthroplasty(THA)revision surgery,and to verify and preliminarily apply it.Methods A total of 706 revision cases with clear CT data from April 2019 to October 2022 in Chinese PLA General Hospital were retrospectively analyzed,including 520 males,aged 58.45±18.13 years,and 186 females,aged 52.23±16.23 years.All of them were unilateral,and there were 402 hips on the left and 304 hips on the right.The transformer_unet convolutional neural network was constructed and trained using Tensorflow 1.15 to achieve intelligent segmentation of the revision THA CT images.Based on the developed three-dimensional planning system of total hip arthroplasty,an intelligent planning system for revision hip arthroplasty was preliminarily constructed.Dice overlap coefficient(DOC),average surface distance(ASD)and Hausdorff distance(HD)parameters were used to evaluate the segmentation accuracy of transformer_unet,full convolution network(FCN),2D U-shaped Net and Deeplab v3+,and segmentation time was used to evaluate the segmentation efficiency of these networks.Results Compared with the FCN,2D U-Net,and Deeplab v3+learning curves,the transformer_unet network could achieve better training effect with less training amount.The DOC of transformer_unet was 95%±4%,the HD was 3.35±1.03 mm,and the ASD was 1.38±0.02 mm;FCN was 94%±4%,4.83±1.90 mm,1.42±0.03 mm;2D U-Net was 93%±5%,5.27±2.20 mm,and 1.46±0.02 mm,respectively.Deeplab v3+was 92%±4%,6.12±1.84 mm,1.52±0.03 mm,respectively.The transformer_unet coefficients were better than those of the other three convolutional neural networks,and the differences were statistically significant(all P<0.05).The segmentation time of transformer_unet was 0.031±0.001 s,FCN was 0.038±0.002 s,2D U-Net was 0.042±0.001 s,Deeplab v3+was 0.048±0.002 s.The segmentation time of transformer_unet was less than that of the other three convolutional neural networks,and the difference was statistically significant(P<0.05).Based on the results of previous studies,an artificial intelligence assisted preoperative planning system for THA revision surgery was initially constructed.Conclusion Compared with FCN,2D U-Net and Deeplab v3+,the transformer_unet convolutional neural network can complete the segmentation of the revision THA CT image more accurately and efficiently,which is expected to provide technical support for preoperative planning and surgical robots.
作者
吴东
孔祥朋
杨敏之
刘星宇
张逸凌
柴伟
Wu Dong;Kong Xiangpeng;Yang Minzhi;Liu Xingyu;Zhang Yiling;Chai Wei(Department of Orthopaedic,the First Medical Centre,Chinese PLA General Hospital,Beijing 100853,China;The Medical District South of Beijing,Chinese PLA General Hospital,Beijing 100071,China;School of Life Sciences,Tsinghua University,Beijing 100084,China;Harvard Medical School,Boston 02138,USA)
出处
《中华骨科杂志》
CAS
CSCD
北大核心
2023年第1期62-71,共10页
Chinese Journal of Orthopaedics
基金
北京市自然科学基金(M22016)。
关键词
关节成形术
置换
髋
再手术
人工智能
神经网络
计算机
多探头的计算机断层扫描
Arthroplasty,replacement,hip
Reoperation
Artificial intelligence
Neural networks,computer
Multidetector computed tomography