Department of Computer Science, Xiamen University, Xiamen 361005, China.
Department of Medical Imaging, Western University, ON, Canada; Digital Image Group, London, ON, Canada.
Med Image Anal. 2019 Dec;58:101542. doi: 10.1016/j.media.2019.101542. Epub 2019 Aug 9.
Accurate automated quantitative Cobb angle estimation that quantitatively evaluates scoliosis plays an important role in scoliosis diagnosis and treatment. It solves the problem of the traditional manual method, which is the current clinical standard for scoliosis assessment, but time-consuming and unreliable. However, it is very challenging to achieve highly accurate automated Cobb angle estimation because it is difficult to utilize the information of Anterior-posterior (AP) and Lateral (LAT) view X-rays efficiently. We therefore propose a Multi-View Extrapolation Net (MVE-Net) that provides accurate automated scoliosis estimation in multi-view (both AP and LAT) X-rays. The MVE-Net consists of three parts: Joint-view net learning AP and LAT angles jointly based on landmarks learned from joint representation; Independent-view net learning AP and LAT angles independently based on landmarks learned from unique independent feature of AP or LAT angles; Inter-error correction net learning a combination function adaptively to offset the first two nets' errors for accurate angle estimation. Experimental results on 526 X-rays show 7.81 and 6.26 Circular Mean Absolute Error in AP and LAT angle estimation, which shows the MVE-Net provides an accurate Cobb angle estimation in multi-view X-rays. Our method therefore provides effective framework for automated, accurate, and reliable scoliosis estimation.
准确的自动定量 Cobb 角估计对定量评估脊柱侧弯起着重要作用，它解决了传统手动方法的问题，目前是脊柱侧弯评估的临床标准，但耗时且不可靠。然而，要实现高度准确的自动 Cobb 角估计非常具有挑战性，因为很难有效地利用前后位（AP）和侧位（LAT）X 射线的信息。因此，我们提出了一种多视图外推网络（MVE-Net），该网络可在多视图（AP 和 LAT）X 射线中提供准确的自动脊柱侧弯估计。MVE-Net 由三部分组成：基于关节表示中学习到的地标，共同学习 AP 和 LAT 角度的联合视图网络；基于从 AP 或 LAT 角度的独特独立特征学习到的地标，独立学习 AP 和 LAT 角度的独立视图网络；学习自适应组合函数的误差校正网络，以抵消前两个网络的误差，从而进行准确的角度估计。在 526 张 X 射线上的实验结果表明，AP 和 LAT 角度估计的圆形均方根误差分别为 7.81 和 6.26，这表明 MVE-Net 可在多视图 X 射线中提供准确的 Cobb 角估计。因此，我们的方法为自动、准确、可靠的脊柱侧弯估计提供了有效的框架。
