A Coarse-to-Fine Deep Heatmap Regression Method for Adolescent Idiopathic Scoliosis Assessment

摘要

Spinal anterior-posterior x-ray CT imaging is an appealing tool to aid diagnosis and elucidate Adolescent Idiopathic Scoliosis (AIS) Assessment. In this paper, we propose an automatic detection method for AIS assessment from X-ray CT images. Our deep learning based coarse-to-fine heatmaps regression method achieves symmetric mean absolute percentage error (SMAPE) of 24.7987 in the grand challenge AASCE 2019.