Saun Tomas J
Division of Plastic and Reconstructive Surgery, Department of Surgery, University of Toronto, Ontario, Canada.
Plast Surg (Oakv). 2021 May;29(2):75-80. doi: 10.1177/2292550321997012. Epub 2021 Mar 5.
Hand X-rays are ordered in outpatient, inpatient, and emergency settings, the results of which are often initially interpreted by non-radiology trained health care providers. There may be utility in automating upper extremity X-ray analysis to aid with rapid initial analysis. Deep neural networks have been effective in several medical imaging analysis applications. The purpose of this work was to apply a deep learning framework to automatically classify the radiographic positioning of hand X-rays.
A 152-layer deep neural network was trained using the musculoskeletal radiographs data set. This data set contains 6003 hand X-rays. The data set was filtered to remove pediatric X-rays and atypical views. The X-rays were all labeled as either posteroanterior (PA), lateral, or oblique views. A subset of images was set aside for model validation and testing. Data set augmentation was performed, including horizontal and vertical flips, rotations, as well as modifications in image brightness and contrast. The model was evaluated, and performance was reported as a confusion matrix from which accuracy, precision, sensitivity, and specificity were calculated.
The augmented training data set consisted of 80 672 images. Their distribution was 38% PA, 35% lateral, and 27% oblique projections. When evaluated on the test data set, the model performed with overall 96.0% accuracy, 93.6% precision, 93.6% sensitivity, and 97.1% specificity.
Radiographic positioning of hand X-rays can be effectively classified by a deep neural network. Further work will be performed on localization of abnormalities, automated assessment of standard radiographic measures and eventually on computer-aided diagnosis and management guidance of skeletal pathology.
手部X线检查常用于门诊、住院和急诊环境，其结果通常最初由未接受过放射学培训的医护人员解读。自动化上肢X线分析可能有助于快速进行初步分析。深度神经网络在多种医学影像分析应用中已取得成效。本研究旨在应用深度学习框架对手部X线片的放射学定位进行自动分类。
使用肌肉骨骼X线片数据集训练一个152层的深度神经网络。该数据集包含6003张手部X线片。对数据集进行筛选，去除儿科X线片和非典型视图。所有X线片均被标记为后前位（PA）、侧位或斜位视图。留出一部分图像子集用于模型验证和测试。进行数据集增强，包括水平和垂直翻转、旋转以及图像亮度和对比度的调整。对模型进行评估，并以混淆矩阵报告性能，从中计算出准确率、精确率、灵敏度和特异性。
增强后的训练数据集由80672张图像组成。它们的分布为38% PA、35%侧位和27%斜位投影。在测试数据集上进行评估时，该模型的总体准确率为96.0%，精确率为93.6%，灵敏度为93.6%，特异性为97.1%。
深度神经网络可有效对手部X线片的放射学定位进行分类。后续将进一步开展关于异常病变定位、标准放射学测量的自动评估，最终实现骨骼病理学的计算机辅助诊断和管理指导等工作。
