Two dimensional paraspinal muscle segmentation in CT images

Abstract

Paraspinal muscles support the spine and are the source of movement force. The size, shape, density, and volume of the paraspinal muscles cross-section area (CSA) are affected by many factors, such as age, health condition, exercise, and low back pain. It is invaluable to segment the paraspinal muscle regions in images in order to measure and study them. Manual segmentation of the paraspinal muscle CSA is time-consuming and inaccurate. In this work, an atlas-based image segmentation algorithm is proposed to segment the paraspinal muscles in CT images. To address the challenges of variations of muscle shape and its relative spatial relationship to other organs, mutual information is utilized to register the atlas and target images, followed by gradient vector flow contour deformation. Experimental results show that the proposed method can successfully segment paraspinal muscle regions in CT images in both intrapatient and interpatient cases. Furthermore, using mutual information to register atlas and target images outperforms the method using spine-spine registration. It segments the muscle regions accurately without the need of the computationally expensive iterative local contour optimization. The results can be used to evaluate paraspinal muscle tissue injury and postoperative back muscle atrophy of spine surgery patients.