An automated estimator for Cobb angle measurement using multi-task networks
An automated estimator for Cobb angle measurement using multi-task networks
复制标题
使用多任务网络进行科布角测量的自动估计器
DOI：
10.1007/s00521-020-05533-y
复制
发表时间：
2020-11-27
影响因子：
6
通讯作者：
Wu, Ji
中科院分区：
文献类型：
--
作者：
Fu, Xiangling;Yang, Guosheng;Wu, Ji
脊柱侧弯是一种脊柱侧弯的医学状况。量化脊柱弯曲程度的Cobb角是脊柱侧弯评估的金标准。近年来，基于分割的深度学习方法和基于界标估计的深度学习方法在X射线Cobb角自动测量中都取得了较高的性能。然而，我们注意到这些方法分别利用分割和地标信息。在这一点上，我们提出了一种自动化的体系结构，使用分割和地标信息相结合的方法来估计17个椎骨的68个地标。此外，我们还考虑了由68个地标描述的脊柱曲率作为估计Cobb角的约束。对240条X射线的大量实验结果表明，该方法有效地提高了标志点估计的性能，减小了Cobb角误差。
Scoliosis is a medical condition where a person's spine has a sideways curve. The Cobb angle quantifying the degree of spinal curvature is the gold standard for a scoliosis assessment. Recently, the deep learning methods based on segmentation and landmark estimation both achieve high performance for automated Cobb angle measurement on X-rays. However, we notice that these methods utilize segmentation and landmark information separately. In this light, we propose an automated architecture that uses combined segmentation with landmark information to estimate 68 landmarks of 17 vertebrae. In addition, we consider spinal curvature described by 68 landmarks as a constraint to estimate the Cobb angle. Extensive experiment results which test on 240 X-rays demonstrate that our method improves the landmark estimation performance effectively and reduces the Cobb angle error.