Automatic Spine Tissue Segmentation from MRI Data Based on Cascade of Boosted Classifiers and Active Appearance Model

Abstract

The study introduces a novel method for automatic segmentation of vertebral column tissue from MRI images. The paper describes a method that combines multiple stages of Machine Learning techniques to recognize and separate different tissues of the human spine. For the needs of this paper, 50 MRI examinations presenting lumbosacral spine of patients with low back pain were selected. After the initial filtration, automatic vertebrae recognition using Cascade Classifier takes place. Afterwards the main segmentation process using the patch based Active Appearance Model is performed. Obtained results are interpolated using centripetal Catmull–Rom splines. The method was tested on previously unseen vertebrae images segmented manually by 5 physicians. A test validating algorithm convergence per iteration was performed and the Intraclass Correlation Coefficient was calculated. Additionally, the 10-fold cross-validation analysis has been done. Presented method proved to be comparable to the physicians (FF = 90.19 ± 1.01%). Moreover results confirmed a proper algorithm convergence. Automatically segmented area correlated well with manual segmentation for single measurements (falser¯=normal0.8336) and for average measurements (falser¯=normal0.9068) with p = 0.05. The 10-fold cross-validation analysis (FF = 91.37 ± 1.13%) confirmed a good model generalization resulting in practical performance.

Automated assessment of paraspinal muscle fat composition based on the segmentation of chemical shift encoding-based water/fat-separated images

“…Differences in PDFF values between the automatic segmentation and ground truth were relatively small and clinically acceptable (absolute difference range from 0.02% to 0.58%). In the future, machine learning methods may be an alternative approach for the segmentation of the paraspinal muscles in water-fat MR images as previously applied for the segmentation of the vertebral column tissues [ 5 ].…”

“…Gawel et al [ 5 ] introduced a method for automatic segmentation of vertebral column tissue based on machine learning with cascade classifiers, active appearance model and principal component analysis. Further approaches have been reported for automatic localisation and segmentation of vertebral bodies on MRI.…”

Research on multi-path dense networks for MRI spinal segmentation

“…Li et al [ 34 ] presented a novel multi-scale and modality dropout learning framework to locate and segment the spine from four-modality MRI. Dominik GaweB et al [ 35 ] combined multiple stages of deep learning to recognize and separate different tissues of the human spine. Faisal Rehman1 et al [ 36 ] presented a novel combination of the traditional region-based level set with deep learning framework in order to predict shape of vertebral bones accurately.…”

A computational outlook on neurostimulation

“…Similarly, the increase in use and efficacy of artificial intelligence or machine learning will certainly open new possibilities with increased automatization. For example, it will increase our ability to automatically segment personalized patient data from magnetic resonance imaging data (Gaweł et al 2018;Perone et al 2018) and create three-dimensional models that are specific to each patient. This capability will open new realistic perspectives on the possibility to precisely characterize the voltage distribution for each patient, thus allowing a level of precision medicine that was unthinkable just a few years ago (Lempka et al 2019).…”