An automated estimator for Cobb angle measurement using multi-task networks

Xiangling Fu, Guosheng Yang, Kailai Zhang, Nanfang Xu, Ji Wu

Abstract: 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.