A Structure-Affinity Dual Attention-based Network to Segment Spine for Scoliosis Assessment

Ultrasound volume projection imaging has shown great promise to visualize spine features and diagnose scoliosis thanks to its harmlessness, cheapness, and efficiency. The key to measuring spine deformity and assessing scoliosis is to accurately segment the spine bone features. In this paper, we propose a novel structure-affinity dual attention-based network (SADANet) for effective spine segmentation. Global channel attention module and spatial criss-cross attention module are combined in a parallel manner to generate rich global context of spine images. Meanwhile, we present a structure-affinity strategy to encode the structural knowledge of spine bones into the semantic representations. By this means, the network can capture both contextual and structural information. Experiments show that our proposed algorithm achieves promising performance on spine segmentation as compared with other state-of-the-art candidates, which makes it an appealing approach for intelligent scoliosis assessment.

I. Introduction

Scoliosis is a medical condition in which the spinal cord gets severely deformed over time. It not only affects the appearance and cardiopulmonary function of the patient, but can also be a cause of psychological impact [1]. Currently, the common practice of scoliosis diagnosis involves measuring the Cobb Angle via radiography [2]. However, the ionizing radiation of X-rays is harmful to the patients. Specifically, radiographic measurements are required not only preoperatively but also postoperatively during the whole treatment [3]. A radiation-free measurement alternative to X-rays suitable for mass screening has become crucial.