文献速递关节外科创伤骨科

深度学习自动化全髋关节置换术前影像学参数与早期假体周围股骨骨折的关联

Deep-Learning Automation of Preoperative Radiographic Parameters Associated With Early Periprosthetic Femur Fracture After Total Hip Arthroplasty.
PubMed 文献 · J Arthroplasty · 2023-11-23

本研究利用深度学习算法自动化测量全髋关节置换术前的股骨影像学参数,并在包含50例早期假体周围股骨骨折患者和50例匹配对照的独立队列中比较。结果显示,骨折组的股骨髓腔骨距比率和髓腔骨比率高于对照组(P < .05),自动化参数与骨科医生测量值具有良好至优秀的相关性(Pearson相关系数0.76至0.96)。作者认为该算法有潜力辅助并改进患者特异性骨折风险预测工具。

要点

  • 深度学习算法可自动化分割股骨标志点并生成影像学参数,与医生测量值相关性良好至优秀。
  • 早期假体周围股骨骨折组的髓腔骨距比率和髓腔骨比率高于对照组(P < .05)。
  • 该算法有潜力辅助并改进患者特异性假体周围股骨骨折风险预测工具。

核心结论

  • 深度学习自动化参数在非骨水泥初次全髋关节置换术后发生与未发生早期假体周围股骨骨折的患者中存在差异。
  • 该算法有潜力辅助并改进患者特异性假体周围股骨骨折风险预测工具。

研究设计与样本

  • 研究使用公开数据库和一家高业务量机构2016年至2020年接受初次非骨水泥全髋关节置换术患者的X线片。
  • 训练U-Net算法分割股骨标志点以实现骨形态参数自动化。
  • 自动化参数与接受过专科培训的外科医生测量值进行比较,并在一个由100例全髋关节置换术患者组成的独立队列中比较(50例早期假体周围股骨骨折患者和50例对照,按股骨假体、年龄、性别、体重指数和手术入路匹配)。

主要发现

  • 在独立队列中,算法在22分钟内为95张图像生成了1710个独特测量值(5%的小转子识别失败)。
  • 髓腔宽度、股骨皮质宽度、髓腔喇叭指数、形态学皮质指数、髓腔骨比率和髓腔骨距比率与外科医生测量值具有良好至优秀的相关性(Pearson相关系数:0.76至0.96)。
  • 比较自动化参数时,假体周围股骨骨折组的髓腔骨距比率(0.43 ± 0.08 对比 0.40 ± 0.07)和髓腔骨比率(0.39 ± 0.06 对比 0.36 ± 0.06)更高(P < .05)。

关键数值与推荐

  • 髓腔骨距比率:假体周围股骨骨折组0.43 ± 0.08 对比 对照组0.40 ± 0.07,骨折组更高(P < .05)。
  • 髓腔骨比率:假体周围股骨骨折组0.39 ± 0.06 对比 对照组0.36 ± 0.06,骨折组更高(P < .05)。
  • 自动化参数与外科医生测量值的Pearson相关系数为0.76至0.96。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: The radiographic assessment of bone morphology impacts implant selection and fixation type in total hip arthroplasty (THA) and is important to minimize the risk of periprosthetic femur fracture (PFF). We utilized a deep-learning algorithm to automate femoral radiographic parameters and determined which automated parameters were associated with early PFF. METHODS: Radiographs from a publicly available database and from patients undergoing primary cementless THA at a high-volume institution (2016 to 2020) were obtained. A U-Net algorithm was trained to segment femoral landmarks for bone morphology parameter automation. Automated parameters were compared against that of a fellowship-trained surgeon and compared in an independent cohort of 100 patients who underwent THA (50 with early PFF and 50 controls matched by femoral component, age, sex, body mass index, and surgical approach). RESULTS: On the independent cohort, the algorithm generated 1,710 unique measurements for 95 images (5% lesser trochanter identification failure) in 22 minutes. Medullary canal width, femoral cortex width, canal flare index, morphological cortical index, canal bone ratio, and canal calcar ratio had good-to-excellent correlation with surgeon measurements (Pearson's correlation coefficient: 0.76 to 0.96). Canal calcar ratios (0.43 ± 0.08 versus 0.40 ± 0.07) and canal bone ratios (0.39 ± 0.06 versus 0.36 ± 0.06) were higher (P < .05) in the PFF cohort when comparing the automated parameters. CONCLUSIONS: Deep-learning automated parameters demonstrated differences in patients who had and did not have early PFF after cementless primary THA. This algorithm has the potential to complement and improve patient-specific PFF risk-prediction tools.

来源:J Arthroplasty,查看原文。版权归原作者所有。

引用

  1. Jang SJ, Alpaugh K, Kunze KN, et al. Deep-Learning Automation of Preoperative Radiographic Parameters Associated With Early Periprosthetic Femur Fracture After Total Hip Arthroplasty. J Arthroplasty. 2023. PMID: 38007206. doi:10.1016/j.arth.2023.11.021

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。