Bimodal CT/MRI-Based Segmentation Method for Intervertebral Disc Boundary Extraction

Pantelis A. Asvestas,George K. Matsopoulos,Meletios Liaskos,Marios G. Lykissas,Michalis A. Savelonas

doi:10.3390/info11090448

Abstract

Intervertebral disc (IVD) localization and segmentation have triggered intensive research efforts in the medical image analysis community, since IVD abnormalities are strong indicators of various spinal cord-related pathologies. Despite the intensive research efforts to address IVD boundary extraction based on MR images, the potential of bimodal approaches, which benefit from complementary information derived from both magnetic resonance imaging (MRI) and computed tomography (CT), has not yet been fully realized. Furthermore, most existing approaches rely on manual intervention or on learning, although sufficiently large and labelled 3D datasets are not always available. In this light, this work introduces a bimodal segmentation method for vertebrae and IVD boundary extraction, which requires a limited amount of intervention and is not based on learning. The proposed method comprises various image processing and analysis stages, including CT/MRI registration, Otsu-based thresholding and Chan–Vese-based segmentation. The method was applied on 98 expert-annotated pairs of CT and MR spinal cord images with varying slice thicknesses and pixel sizes, which were obtained from 7 patients using different scanners. The experimental results had a Dice similarity coefficient equal to 94.77(%) for CT and 86.26(%) for MRI and a Hausdorff distance equal to 4.4 pixels for CT and 4.5 pixels for MRI. Experimental comparisons with state-of-the-art CT and MRI segmentation methods lead to the conclusion that the proposed method provides a reliable alternative for vertebrae and IVD boundary extraction. Moreover, the segmentation results are utilized to perform a bimodal visualization of the spine, which could potentially aid differential diagnosis with respect to several spine-related pathologies.

Highlights

Intervertebral disc (IVD) localization and segmentation has triggered activity in the medical image analysis community, since IVD abnormalities are strongly associated with various chronic diseases, including disk herniation and slipped vertebrae [1]
computed tomography (CT) and magnetic resonance imaging (MRI) segmentation methods lead to the conclusion that the proposed method provides a reliable alternative for vertebrae and IVD boundary extraction
Linear gray level normalization and Otsu thresholding with 3 gray levels are applied at this stage, (3) vertebral region projection on MRI, using the rules derived in stage 1, (4) IVD localization by means of a simple heuristic, (5) CT/MRI-based segmentation for IVD boundary extraction, using the boundaries defined by the vertebra projected in stage 3, the coarse IVD regions obtained in stage 4, and the Chan–Vese active contour, (6) CT/MRI image fusion, offering a bimodal visualization of the spine

Summary

Introduction

Intervertebral disc (IVD) localization and segmentation has triggered activity in the medical image analysis community, since IVD abnormalities are strongly associated with various chronic diseases, including disk herniation and slipped vertebrae [1]. There is a lack of bimodal approaches, based on complementary information derived from both MRI and CT imaging. Zheng et al employed the Hough transform (HT) to localize discs in videofluoroscopic CT images, only to refine the manually determined IVD location [6]. Peng et al employed MRI-derived intensity profiles to localize the articulated vertebrae based on a manual selection of the ‘best’ MRI sagittal slice [7]. Schmidt et al proposed a part-based, probabilistic inference method for spine detection and labelling [8]. Their method uses a tree classifier and relies on a set of manually marked lumbar region disc from MRI images.

Methods

Results

Conclusion