文献速递关节外科

人工智能可自主测量髋臼杯方位、校正骨盆方位并从骨盆正位X线片识别髋臼杯后倾

Artificial Intelligence Autonomously Measures Cup Orientation, Corrects for Pelvis Orientation, and Identifies Retroversion From Antero-Posterior Pelvis Radiographs.
PubMed 文献 · J Arthroplasty · 2023-03-08

本研究基于2012至2019年2945例患者全髋关节置换术后的504份CT扫描,构建人工智能程序从骨盆正位X线片自主测量髋臼杯方位、校正骨盆方位并识别髋臼杯后倾。在690张测试X线片上,AI测量与CT测量的相关系数为0.976和0.984,手测为0.650和0.687,AI更接近CT(P < .001)。

要点

  • AI测量与CT的相关系数为0.976(前倾角)和0.984(外展角),手测为0.650和0.687。
  • AI前倾角、AI外展角、手测前倾角、手测外展角与CT测量的平均偏差分别为0.04 ± 2.21°、0.14 ± 1.66°、-0.31 ± 8.35°、6.48° ± 7.43°。
  • AI识别17张后倾X线片准确率100.0%(后倾总数n = 45)。

核心结论

  • AI算法在X线片上测量髋臼杯方位时可能校正骨盆方位,表现优于手测,并可能及时投入应用。
  • 这是首个从单张骨盆正位X线片识别髋臼杯后倾的方法。

研究设计与样本

  • 研究纳入2012至2019年间2945例患者全髋关节置换术后的504份CT扫描。
  • 对所有CT进行三维重建,以骨盆前平面为参考测量髋臼杯方位。
  • 患者随机分配至训练组(4000张X线片)、验证组(511张X线片)和测试组(690张X线片)。
  • 对训练集(n = 4,000,000)应用数据增强以提高模型稳健性。
  • 仅在测试组进行与CT测量准确性的统计分析。

主要发现

  • AI对单张X线片预测平均耗时0.22 ± 0.03秒。
  • AI测量与CT的皮尔逊相关系数前倾角为0.976、外展角为0.984,手测前倾角为0.650、外展角为0.687。
  • AI测量较手测更接近CT扫描(P < .001)。
  • AI前倾角、AI外展角、手测前倾角、手测外展角与CT测量的平均偏差分别为0.04 ± 2.21°、0.14 ± 1.66°、-0.31 ± 8.35°、6.48° ± 7.43°。
  • AI预测识别17张后倾X线片,准确率100.0%(后倾总数n = 45)。

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: Measuring cup orientation is time consuming and inaccurate, but orientation influences the risk of impingement and dislocation following total hip arthroplasty (THA). This study designed an artificial intelligence (AI) program to autonomously determine cup orientation, correct for pelvis orientation, and identify cup retroversion from an antero-posterior pelvic radiographs. METHODS: There were 2,945 patients between 2012 and 2019 identified to have 504 computed tomographic (CT) scans of their THA. A 3-dimensional (3D) reconstruction was performed on all CTs, where cup orientation was measured relative to the anterior pelvic plane. Patients were randomly allocated to training (4,000 x-rays), validation (511 x-rays), and testing (690 x-rays) groups. Data augmentation was applied to the training set (n = 4,000,000) to increase model robustness. Statistical analyses were performed only on the test group in their accuracy with CT measurements. RESULTS: AI predictions averaged 0.22 ± 0.03 seconds to run on a given radiograph. Pearson correlation coefficient was 0.976 and 0.984 for AI measurements with CT, while hand measurements were 0.650 and 0.687 for anteversion and inclination, respectively. The AI measurements more closely represented CT scans when compared to hand measurements (P < .001). Measurements averaged 0.04 ± 2.21°, 0.14 ± 1.66°, -0.31 ± 8.35°, and 6.48° ± 7.43° from CT measurements for AI anteversion, AI inclination, hand anteversion, and hand inclination, respectively. AI predictions identified 17 radiographs as retroverted with 100.0% accuracy (total retroverted, n = 45). CONCLUSION: The AI algorithms may correct for pelvis orientation when measuring cup orientation on radiographs, outperform hand measurements, and may be implemented in a timely fashion. This is the first method to identify a retroverted cup from a single AP radiograph.

来源:J Arthroplasty,查看原文。版权归原作者所有。

引用

  1. Murphy MP, Killen CJ, Winfrey SR, et al. Artificial Intelligence Autonomously Measures Cup Orientation, Corrects for Pelvis Orientation, and Identifies Retroversion From Antero-Posterior Pelvis Radiographs. J Arthroplasty. 2023. PMID: 36893991. doi:10.1016/j.arth.2023.02.076

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。