Unsupervised boundary delineation of spinal neural foramina using a multi-feature and adaptive spectral segmentation

Xiaoxu He; Heye Zhang; Mark Landis; Manas Sharma; James Warrington; Shuo Li

doi:10.1016/j.media.2016.10.009

Unsupervised boundary delineation of spinal neural foramina using a multi-feature and adaptive spectral segmentation

Med Image Anal. 2017 Feb:36:22-40. doi: 10.1016/j.media.2016.10.009. Epub 2016 Oct 29.

Authors

Xiaoxu He¹, Heye Zhang², Mark Landis¹, Manas Sharma¹, James Warrington¹, Shuo Li³

Affiliations

¹ The Digital Imaging Group of London, Department of Medical Imaging, Western University, London, ON N6A 3K7, Canada.
² Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518 055, China. Electronic address: hy.zhang@siat.ac.cn.
³ The Digital Imaging Group of London, Department of Medical Imaging, Western University, London, ON N6A 3K7, Canada. Electronic address: slishuo@gmail.com.

PMID: 27816860
DOI: 10.1016/j.media.2016.10.009

Abstract

As a common disease in the elderly, neural foramina stenosis (NFS) brings a significantly negative impact on the quality of life due to its symptoms including pain, disability, fall risk and depression. Accurate boundary delineation is essential to the clinical diagnosis and treatment of NFS. However, existing clinical routine is extremely tedious and inefficient due to the requirement of physicians' intensively manual delineation. Automated delineation is highly needed but faces big challenges from the complexity and variability in neural foramina images. In this paper, we propose a pure image-driven unsupervised boundary delineation framework for the automated neural foramina boundary delineation. This framework is based on a novel multi-feature and adaptive spectral segmentation (MFASS) algorithm. MFASS firstly utilizes the combination of region and edge features to generate reliable spectral features with a good separation between neural foramina and its surroundings, then estimates an optimal separation threshold for each individual image to separate neural foramina from its surroundings. This self-adjusted optimal separation threshold, estimated from spectral features, successfully overcome the diverse appearance and shape variations. With the robustness from the multi-feature fusion and the flexibility from the adaptively optimal separation threshold estimation, the proposed framework, based on MFASS, provides an automated and accurate boundary delineation. Validation was performed in 280 neural foramina MR images from 56 clinical subjects. Our method was benchmarked with manual boundary obtained by experienced physicians. Results demonstrate that the proposed method enjoys a high and stable consistency with experienced physicians (Dice: 90.58% ± 2.79%; SMAD: 0.5657 ± 0.1544 mm). Therefore, the proposed framework enables an efficient and accurate clinical tool in the diagnosis of neural foramina stenosis.

Keywords: Boundary delineation; Multi-feature combination; Neural foramina stenosis; Spectral segmentation.

MeSH terms

Algorithms*
Humans
Magnetic Resonance Imaging / methods*
Spinal Canal / diagnostic imaging*
Spinal Canal / pathology
Spinal Stenosis / diagnostic imaging*
Spinal Stenosis / pathology
Unsupervised Machine Learning*