Deep Learning for Automated Measurement of Patellofemoral Anatomic Landmarks.
Deep Learning for Automated Measurement of Patellofemoral Anatomic Landmarks.
复制标题
DOI：
10.3390/bioengineering10070815
复制
发表时间：
2023-07-08
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
背景：髌股解剖结构尚未得到很好的表征。应用深度学习自动测量膝关节解剖结构可以更好地了解解剖结构，这可能是改善结果的关键因素。研究方法：从计划进行膝关节置换术的队列和膝关节解剖结构健康的队列中选择了来自6家中心的483例膝关节CT成像患者（2017年4月至2022年5月）。在14，652张图像上共注释了7个髌股标志，并由高级肌肉骨骼放射科医生批准。使用RadImageNet上的自监督学习预训练权重初始化的修改后的ResNet 50架构，训练两阶段深度学习模型来预测地标坐标。用平均绝对误差评价地标预测，用Bland-Altman图分析髌股测量值。通过配对t检验评估测量的统计学显著性。结果：在健康/关节成形术队列中，预测和真实界标坐标之间的平均绝对误差为0.20/0.26 cm。计算了四个膝关节参数，包括经上髁轴长、经上髁-股骨后轴角、股骨内侧不对称和沟角。除了健康队列的沟角外，两个队列的预测值和真实测量值之间没有统计学显著性差异（p > 0.05）。结论：我们的模型准确地识别了关键的trophilar标志，精度约为0.20-0.26 cm，并在健康和病理膝盖上产生了人类可比的测量结果。这项工作代表了第一个深度学习回归模型，用于在生理和病理CT成像上训练自动髌股注释。这种新的模型可以提高我们的能力，分析髌股间室的解剖规模。
Background: Patellofemoral anatomy has not been well characterized. Applying deep learning to automatically measure knee anatomy can provide a better understanding of anatomy, which can be a key factor in improving outcomes. Methods: 483 total patients with knee CT imaging (April 2017–May 2022) from 6 centers were selected from a cohort scheduled for knee arthroplasty and a cohort with healthy knee anatomy. A total of 7 patellofemoral landmarks were annotated on 14,652 images and approved by a senior musculoskeletal radiologist. A two-stage deep learning model was trained to predict landmark coordinates using a modified ResNet50 architecture initialized with self-supervised learning pretrained weights on RadImageNet. Landmark predictions were evaluated with mean absolute error, and derived patellofemoral measurements were analyzed with Bland–Altman plots. Statistical significance of measurements was assessed by paired t-tests. Results: Mean absolute error between predicted and ground truth landmark coordinates was 0.20/0.26 cm in the healthy/arthroplasty cohort. Four knee parameters were calculated, including transepicondylar axis length, transepicondylar-posterior femur axis angle, trochlear medial asymmetry, and sulcus angle. There were no statistically significant parameter differences (p > 0.05) between predicted and ground truth measurements in both cohorts, except for the healthy cohort sulcus angle. Conclusion: Our model accurately identifies key trochlear landmarks with ~0.20–0.26 cm accuracy and produces human-comparable measurements on both healthy and pathological knees. This work represents the first deep learning regression model for automated patellofemoral annotation trained on both physiologic and pathologic CT imaging at this scale. This novel model can enhance our ability to analyze the anatomy of the patellofemoral compartment at scale.
登录
查看更多内容
影响因子：
3.8
作者：
Rosa, Sergio Barroso;Hazratwala, Kaushik;Wilkinson, Matthew P. R.
通讯作者：
Wilkinson, Matthew P. R.
影响因子：
2.3
作者：
Li Z;Liu G;Tian R;Kong N;Li Y;Li Y;Wang K;Yang P
通讯作者：
Yang P
影响因子：
4.2
作者：
Iranpour, Farhad;Merican, Azhar M.;Cobb, Justin P.
通讯作者：
Cobb, Justin P.
影响因子：
3.8
作者：
Koh, Yong-Gon;Nam, Ji-Hoon;Kang, Kyoung-Tak
通讯作者：
Kang, Kyoung-Tak
影响因子：
3.4
作者：
Roussot, Mark Anthony;Haddad, Fares Sami
通讯作者：
Haddad, Fares Sami