Automated detection, 3D segmentation and analysis of high resolution spine MR images using statistical shape models

Abstract

Recent advances in high resolution magnetic resonance (MR) imaging of the spine provide a basis for the automated assessment of intervertebral disc (IVD) and vertebral body (VB) anatomy. High resolution three-dimensional (3D) morphological information contained in these images may be useful for early detection and monitoring of common spine disorders, such as disc degeneration. This work proposes an automated approach to extract the 3D segmentations of lumbar and thoracic IVDs and VBs from MR images using statistical shape analysis and registration of grey level intensity profiles. The algorithm was validated on a dataset of volumetric scans of the thoracolumbar spine of asymptomatic volunteers obtained on a 3T scanner using the relatively new 3D T2-weighted SPACE pulse sequence. Manual segmentations and expert radiological findings of early signs of disc degeneration were used in the validation. There was good agreement between manual and automated segmentation of the IVD and VB volumes with the mean Dice scores of 0.89 ± 0.04 and 0.91 ± 0.02 and mean absolute surface distances of 0.55 ± 0.18 mm and 0.67 ± 0.17 mm respectively. The method compares favourably to existing 3D MR segmentation techniques for VBs. This is the first time IVDs have been automatically segmented from 3D volumetric scans and shape parameters obtained were used in preliminary analyses to accurately classify (100% sensitivity, 98.3% specificity) disc abnormalities associated with early degenerative changes.

Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: A grand challenge

“…The reported Dice coefficients of this method were 91.6% for normal and 87.2% for degenerated discs. A statistical shape models-based method was proposed by Neubert et al (2012) for automated three-dimensional (3D) segmentation of high resolution spine MR images. Their method required an interactive placement of a set of initial rectangles along spine curve.…”

“…segmentation of lumbar and thoracic IVDs from magnetic resonance (MR) images of the spine (Neubert et al, 2012). The initial version of this algorithm was developed for high-resolution volumetric MR images acquired in the axial plane.…”

“…The original ASM approach was successfully applied to the segmentation of lumbar IVDs from TSE scans by developing a novel initialization scheme. Specifically, an automated localization approach using multi-atlas registration and probabilistic shape regression was used to initialize volumetric ASM segmentation driven by grey-level intensity models, as presented in their previous work (Neubert et al, 2012). For details, we refer to (Neubert et al, 2015).…”

A Framework on a Computer Assisted and Systematic Methodology for Detection of Chronic Lower Back Pain Using Artificial Intelligence and Computer Graphics Technologies

“…There has been limited progress in this regard, including one by Neubert et. al [17] who claimed that 3-dimensional MR images have the potential to help physicians to detect and monitor the spine disorder at an early stage. Consequently, we argue that this is one of the most promising areas of research in which computer technologies can play significant part in solving the problem.…”

Explorando superpixels para a segmentação semiautomática de imagens médicas para recuperação por conteúdo

“…Os autores em [Neubert et al 2012] apresentam uma abordagem para a extração automática de segmentações volumétricas de discos intervertebrais e corpos vertebrais em imagens de RM utilizando análises estatísticas de forma e registro dos perfis de intensidade de nível de cinza. O algoritmo proposto por eles pode ser dividido em duas etapas principais: (1) localização da espinha, baseada no algoritmo proposto em [Vrtovec et al 2007], e (2) segmentação dos discos intervertebrais e corpos vertebrais com uma estratégia baseada no conceito de modelo de forma ativo (do inglês active shape model) [Heimann e Meinzer 2009].…”