Deep learning model for measurement of shoulder critical angle and acromion index on shoulder radiographs.
Deep learning model for measurement of shoulder critical angle and acromion index on shoulder radiographs.
复制标题
DOI：
10.1016/j.xrrt.2022.03.002
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Maradit Kremers, Hilal
中科院分区：
文献类型：
--
作者：
Shariatnia, M Moein;Ramazanian, Taghi;Sanchez-Sotelo, Joaquin;Maradit Kremers, Hilal
已经提出了几个骨形态参数，包括肩峰前形态、肩峰外侧角、喙肱间距、关节盂倾斜度、肩峰指数（AI）和肩关节临界角（CSA），以影响肩袖撕裂和盂肱骨关节炎的发展。本研究旨在开发一种深度学习工具，以自动测量肩关节前后位X线片上的CSA和AI。我们使用了MURA数据集v1.1，这是来自斯坦福大学医学院的大型公开可用的肌肉骨骼X光片数据集。所有正常肩关节前后位X光片均由经验丰富的骨科医生提取并注释。注释的图像被分成训练集（1004）、验证集（174）和测试集（93）。我们使用pytorch_segmentation_models进行U-Net实现，使用PyTorch框架训练模型。测试集用于模型的最终评估。在包含93张图像的测试集上，人工测量和机器测量之间CSA和AI的平均绝对误差分别为1.68°（95% CI 1.406°-1.979°）和0.03（95% CI 0.02 - 0.03）。深度学习模型可以精确和准确地测量肩关节前后位X光片中的CSA和AI。这种性质的工具使得大规模的研究项目可行，如果与放射学软件程序集成，则有望成为临床应用。
Several bone morphological parameters, including the anterior acromion morphology, the lateral acromial angle, the coracohumeral interval, the glenoid inclination, the acromion index (AI), and the shoulder critical angle (CSA), have been proposed to impact the development of rotator cuff tears and glenohumeral osteoarthritis. This study aimed to develop a deep learning tool to automate the measurement of CSA and AI on anteroposterior shoulder radiographs. We used MURA Dataset v1.1, which is a large publicly available musculoskeletal radiograph dataset from the Stanford University School of Medicine. All normal shoulder anteroposterior radiographs were extracted and annotated by an experienced orthopedic surgeon. The annotated images were divided into train (1004), validation (174), and test (93) sets. We use pytorch_segmentation_models for U-Net implementation and PyTorch framework for training the model. The test set was used for final evaluation of the model. The mean absolute error for CSA and AI between human-performed and machine-performed measurements on the test set with 93 images was 1.68° (95% CI 1.406°-1.979°) and 0.03 (95% CI 0.02 - 0.03), respectively. A deep learning model can precisely and accurately measure CSA and AI in shoulder anteroposterior radiographs. A tool of this nature makes large-scale research projects feasible and holds promise as a clinical application if integrated with a radiology software program.