Department of Orthopaedic Surgery, Osaka University Graduate School of Medicine, 2-2 Yamadaoka, Suita, Osaka, 565-0871, Japan.
Division of Information Science, Nara Institute of Science and Technology, 8916-5 Takayama, Ikoma, Nara, 630-0192, Japan.
Sci Rep. 2021 Jul 27;11(1):15249. doi: 10.1038/s41598-021-94634-2.
The purpose of the study was to develop a deep learning network for estimating and constructing highly accurate 3D bone models directly from actual X-ray images and to verify its accuracy. The data used were 173 computed tomography (CT) images and 105 actual X-ray images of a healthy wrist joint. To compensate for the small size of the dataset, digitally reconstructed radiography (DRR) images generated from CT were used as training data instead of actual X-ray images. The DRR-like images were generated from actual X-ray images in the test and adapted to the network, and high-accuracy estimation of a 3D bone model from a small data set was possible. The 3D shape of the radius and ulna were estimated from actual X-ray images with accuracies of 1.05 ± 0.36 and 1.45 ± 0.41 mm, respectively.
本研究旨在开发一种深度学习网络，以便能够直接从实际 X 射线图像中准确估算和构建高精度的 3D 骨骼模型，并验证其准确性。所使用的数据是 173 个腕关节 CT 图像和 105 个实际 X 射线图像。为了弥补数据集较小的问题，我们使用从 CT 生成的数字射线照片（DRR）图像作为训练数据，而不是实际的 X 射线图像。我们从测试中的实际 X 射线图像生成了类似于 DRR 的图像，并对其进行了网络适配，从而能够从小数据集进行高精度的 3D 骨骼模型估算。我们从实际 X 射线图像中估算出桡骨和尺骨的 3D 形状，其精度分别为 1.05±0.36 和 1.45±0.41 毫米。
