Morphological active contour driven by local and global intensity fitting for spinal cord segmentation from MR images

BACKGROUND Spinal cord (SC) segmentation from magnetic resonance (MR) images can be used to study neurological disorders and facilitates group analysis. Variation of intensity inhomogeneity and small cross section of SC are difficulties that restrict automizing SC segmentation. NEW METHODS In this paper we present a method for accurate SC segmentation from MR images. The proposed morphological local global intensity fitting model (MLGIF) is based on region based morphological active contour model that utilizes local and global information. The local information is obtained using local morphology fitting and has been embedded into region based active contour to deal with images intensity inhomogeneity and variable contrast levels between SC and the cerebrospinal fluid. The contour evolution has been performed using successive application of a set of morphological operators. RESULTS The proposed method has been validated on 28 T1-weighted and 29 T2-weighted MR images and simulated MR images with different noise levels. Assessment of the results shows the accuracy of the proposed method for SC segmentation. COMPARISON TO EXISTING METHOD(S) The proposed MLGIF method was comparable with existing SC segmentation methods. Between segmented images and corresponding ground truth images, the mean DICE similarity coefficient, mean conformity coefficient and mean Hausdorff distance were 0.90 (092), 0.8 (0.83) and 0.85 mm (0.70 mm), respectively, for T1(T2)-weighted images. CONCLUSION The MLGIF model was proposed to achieve a robust method to deal with intensity inhomogeneity and lack of contrast between SC and surrounding tissues. Moreover, accuracy and less sensitivity to initial curve were seen.

[1]  C. Tench,et al.  Measurement of Spinal Cord Atrophy in Multiple Sclerosis , 2004, Journal of neuroimaging : official journal of the American Society of Neuroimaging.

[2]  Karl Rohr,et al.  Robust segmentation of tubular structures in 3-D medical images by parametric object detection and tracking , 2003, IEEE Trans. Syst. Man Cybern. Part B.

[3]  J. Cohen‐Adad,et al.  Segmentation of the human spinal cord , 2016, Magnetic Resonance Materials in Physics, Biology and Medicine.

[4]  Chunming Li,et al.  Implicit Active Contours Driven by Local Binary Fitting Energy , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Peter D. Scott,et al.  An automatic segmentation method of the spinal canal from clinical MR images based on an attention model and an active contour model , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[6]  Ghassan Hamarneh,et al.  Augmenting Auto-context with Global Geometric Features for Spinal Cord Segmentation , 2013, MLMI.

[7]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[8]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[9]  Woei-Chyn Chu,et al.  Performance measure characterization for evaluating neuroimage segmentation algorithms , 2009, NeuroImage.

[10]  Julien Cohen-Adad,et al.  SCT: Spinal Cord Toolbox, an open-source software for processing spinal cord MRI data , 2017, NeuroImage.

[11]  Shuo Li,et al.  Gradient Competition Anisotropy for Centerline Extraction and Segmentation of Spinal Cords , 2013, IPMI.

[12]  Francesca Bagnato,et al.  Semi-automatic segmentation and modeling of the cervical spinal cord for volume quantification in multiple sclerosis patients from magnetic resonance images , 2008, SPIE Medical Imaging.

[13]  Habib Benali,et al.  Fast and Accurate Semi-Automated Segmentation Method of Spinal Cord MR Images at 3T Applied to the Construction of a Cervical Spinal Cord Template , 2015, PloS one.

[14]  Julien Cohen-Adad,et al.  Automatic Labeling of Vertebral Levels Using a Robust Template-Based Approach , 2014, Int. J. Biomed. Imaging.

[15]  M. Helfroush,et al.  Variational level set combined with Markov random field modeling for simultaneous intensity non-uniformity correction and segmentation of MR images , 2012, Journal of Neuroscience Methods.

[16]  Rohit Bakshi,et al.  The Relationships among MRI‐Defined Spinal Cord Involvement, Brain Involvement, and Disability in Multiple Sclerosis , 2012, Journal of neuroimaging : official journal of the American Society of Neuroimaging.

[17]  Ghassan Hamarneh,et al.  Spinal Cord Segmentation for Volume Estimation in Healthy and Multiple Sclerosis Subjects Using Crawlers and Minimal Paths , 2011, 2011 IEEE First International Conference on Healthcare Informatics, Imaging and Systems Biology.

[18]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[19]  Julien Cohen-Adad,et al.  The current state-of-the-art of spinal cord imaging: Methods , 2014, NeuroImage.

[20]  A. Thompson,et al.  Spinal cord atrophy and disability in multiple sclerosis. A new reproducible and sensitive MRI method with potential to monitor disease progression. , 1996, Brain : a journal of neurology.

[21]  D. L. Collins,et al.  Framework for integrated MRI average of the spinal cord white and gray matter: The MNI–Poly–AMU template , 2014, NeuroImage.

[22]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[23]  G J Barker,et al.  Quantification of spinal cord atrophy from magnetic resonance images via a B‐spline active surface model , 2002, Magnetic resonance in medicine.

[24]  Zhen Chen,et al.  Morphological Multiscale Enhancement, Fuzzy Filter and Watershed for Vascular Tree Extraction in Angiogram , 2011, Journal of Medical Systems.

[25]  M. A. Horsfield,et al.  Rapid semi-automatic segmentation of the spinal cord from magnetic resonance images: Application in multiple sclerosis , 2010, NeuroImage.

[26]  Anil K. Jain,et al.  A modified Hausdorff distance for object matching , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[27]  Julien Cohen-Adad,et al.  Automatic Segmentation of the Spinal Cord and Spinal Canal Coupled With Vertebral Labeling , 2015, IEEE Transactions on Medical Imaging.

[28]  Patrick W. Stroman,et al.  Spatial normalization, bulk motion correction and coregistration for functional magnetic resonance imaging of the human cervical spinal cord and brainstem. , 2008, Magnetic resonance imaging.

[29]  Zhen Chen,et al.  Local Morphology Fitting Active Contour for Automatic Vascular Segmentation , 2012, IEEE Transactions on Biomedical Engineering.

[30]  Luis Álvarez,et al.  A Morphological Approach to Curvature-Based Evolution of Curves and Surfaces , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Ludwig Kappos,et al.  Relevance of spinal cord abnormalities to clinical disability in multiple sclerosis: MR imaging findings in a large cohort of patients. , 2013, Radiology.

[32]  P. Lions,et al.  Axioms and fundamental equations of image processing , 1993 .

[33]  F. Biering-Sørensen,et al.  Independent spinal cord atrophy measures correlate to motor and sensory deficits in individuals with spinal cord injury , 2011, Spinal Cord.

[34]  Julien Cohen-Adad,et al.  A reliable spatially normalized template of the human spinal cord — Applications to automated white matter/gray matter segmentation and tensor-based morphometry (TBM) mapping of gray matter alterations occurring with age , 2015, NeuroImage.

[35]  Julien Cohen-Adad,et al.  Robust, accurate and fast automatic segmentation of the spinal cord , 2014, NeuroImage.

[36]  Boying Wu,et al.  Local- and Global-Statistics-Based Active Contour Model for Image Segmentation , 2012 .

[37]  John A. Butman,et al.  Semi-automatic spinal cord segmentation and quantification , 2005 .

[38]  Ghassan Hamarneh,et al.  Spinal Crawlers: Deformable Organisms for Spinal Cord Segmentation and Analysis , 2006, MICCAI.

[39]  P. W. Stroman,et al.  The current state-of-the-art of spinal cord imaging: Applications , 2014, NeuroImage.

[40]  P. Morgan,et al.  Measurement of cervical spinal cord cross‐sectional area by MRI using edge detection and partial volume correction , 2005, Journal of magnetic resonance imaging : JMRI.

[41]  Ghassan Hamarneh,et al.  Globally optimal spinal cord segmentation using a minimal path in high dimensions , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[42]  P. Jaccard.  THE DISTRIBUTION OF THE FLORA IN THE ALPINE ZONE.1 , 1912 .

[43]  Karla L. Miller,et al.  Detecting microstructural properties of white matter based on compartmentalization of magnetic susceptibility , 2013, NeuroImage.

[44]  Hamid Abrishami Moghaddam,et al.  Design and construction of a brain phantom to simulate neonatal MR images , 2011, Comput. Medical Imaging Graph..

[45]  Alyssa H. Zhu,et al.  Gray matter segmentation of the spinal cord with active contours in MR images , 2017, NeuroImage.

[46]  M. Maccarone.  Fuzzy mathematical morphology: Concepts and applications , 1996 .

[47]  D. Louis Collins,et al.  A new improved version of the realistic digital brain phantom , 2006, NeuroImage.

[48]  D. Louis Collins,et al.  Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging , 2013, Medical Image Anal..

[49]  Shuo Li,et al.  Intervertebral disc segmentation in MR images using anisotropic oriented flux , 2013, Medical Image Anal..