Automatic Global Level Set Approach for Lumbar Vertebrae CT Image Segmentation

Abstract

Vertebrae computed tomography (CT) image automatic segmentation is an essential step for Image-guided minimally invasive spine surgery. However, most of state-of-the-art methods still require human intervention due to the inherent limitations of vertebrae CT image, such as topological variation, irregular boundaries (double boundary, weak boundary), and image noise. Therefore, this paper intentionally designed an automatic global level set approach (AGLSA), which is capable of dealing with these issues for lumbar vertebrae CT image segmentation. Unlike the traditional level set methods, we firstly propose an automatically initialized level set function (AILSF) that comprises hybrid morphological filter (HMF) and Gaussian mixture model (GMM) to automatically generate a smooth initial contour which is precisely adjacent to the object boundary. Secondly, a regularized level set formulation is introduced to overcome the weak boundary leaking problem, which utilizes the region correlation of histograms inside and outside the level set contour as a global term. Ultimately, a gradient vector flow (GVF) based edge-stopping function is employed to guarantee a fast convergence rate of the level set evolution and to avoid level set function oversegmentation at the same time. Our proposed approach has been tested on 115 vertebrae CT volumes of various patients. Quantitative comparisons validate that our proposed AGLSA is more accurate in segmenting lumbar vertebrae CT images with irregular boundaries and more robust to various levels of salt-and-pepper noise.

Artificial Intelligence and Computer Vision in Low Back Pain: A Systematic Review

“…However, recent research has been exploring the use of deep learning-based AI systems which are able to perform multiple tasks at the basic and advanced level in a single model [1]. Vertebrae are by far the most investigated structure, with AI systems reaching > 90% DICE and > 90% accuracy in the majority of studies included in our review, both using DIP [28][29][30][31][32][33][34][35][36][37][38][39][40][41]43,44,[48][49][50]53,61,62] and deep learning models [67,69,77,[80][81][82][83][84]. In particular, a study from Lee et al [40] proposed a model to obtain an automated segmentation of lumbar pedicles from CT images in order to increase accuracy and safety during transpedicular screw placement.…”

“…In addition, in a successive article Haq et al [25] utilized a shape statistical deformable model for the segmentation of IVDs on CT images of 18 subjects from the SpineWeb dataset, achieving DICE scores ranging from 91.7 to 95.4%. Li et al [28] applied a threshold to the results of a Gaussian Mixture Model for segmenting vertebrae on a total of 115 CT images from the SpineWeb and the Microsoft Research datasets, with an average DICE of 92.1%. Ibragimov et al [29] used landmark detection and deformable models for segmenting 30 vertebrae on CT images, with a DICE of 84.7%.…”

Autonomous image segmentation and identification of anatomical landmarks from lumbar spine intraoperative computed tomography scans using machine learning: A validation study

“…[ 2 ] This is concordant with prior work on automatic segmentation that has noted 90%–95% accuracy. [ 3 4 18 19 ] Manually segmented vertebrae on CT scans have been proven to be highly accurate with submillimeter accuracy and precision,[ 20 ] suggesting pedicle screw placement under machine-learned guidance to be well within the margin of safety by Gertzbein and Robbins. [ 21 ]…”

Self-Learning Network-based segmentation for real-time brain M.R. images through HARIS

“…But it is not very efficient for noisy images and high-intensity images. Li et al (2018) have proposed a level set centric technique for the MR image segmentation based on the pre-approximated threshold value. The level set method is a very complex approach, and the approximated threshold value determines the efficiency of the approach’s segmentation.…”