Incorporating Domain Knowledge Into the Fuzzy Connectedness Framework: Application to Brain Lesion Volume Estimation in Multiple Sclerosis

A method for incorporating prior knowledge into the fuzzy connectedness image segmentation framework is presented. This prior knowledge is in the form of probabilistic feature distribution and feature size maps, in a standard anatomical space, and ldquointensity hintsrdquo selected by the user that allow for a skewed distribution of the feature intensity characteristics. The fuzzy affinity between pixels is modified to encapsulate this domain knowledge. The method was tested by using it to segment brain lesions in patients with multiple sclerosis, and the results compared to an established method for lesion outlining based on edge detection and contour following. With the fuzzy connections (FC) method, the user is required to identify each lesion with a mouse click, to provide a set of seed pixels. The algorithm then grows the features from the seeds to define the lesions as a set of objects with fuzzy connectedness above a preset threshold. The FC method gave improved interobserver reproducibility of lesion volumes, and the set of pixels determined to be lesion was more consistent compared to the contouring method. The operator interaction time required to evaluate one subject was reduced from an average of 111 min with contouring to 16 min with the FC method.

[1]  R Kikinis,et al.  Automatic identification of gray matter structures from MRI to improve the segmentation of white matter lesions. , 1995, Journal of image guided surgery.

[2]  M Rovaris,et al.  Brain MRI lesion volume measurement reproducibility is not dependent on the disease burden in patients with multiple sclerosis. , 1998, Magnetic resonance imaging.

[3]  Supun Samarasekera,et al.  Multiple sclerosis lesion quantification using fuzzy-connectedness principles , 1997, IEEE Transactions on Medical Imaging.

[4]  J. Kurtzke,et al.  expanded disability status scale (EDSS) Rating neurologic impairment in multiple sclerosis: An , 1983 .

[5]  M. A. Horsfield,et al.  Whole-brain atrophy in multiple sclerosis measured by two segmentation processes from various MRI sequences , 2003, Journal of the Neurological Sciences.

[6]  F. Barkhof,et al.  Accumulation of hypointense lesions ("black holes") on T1 spin-echo MRI correlates with disease progression in multiple sclerosis , 1996, Neurology.

[7]  R. Ordidge,et al.  High field MRI correlates of myelin content and axonal density in multiple sclerosis , 2003, Journal of Neurology.

[8]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[9]  Paul M Matthews,et al.  Reduced brain functional reserve and altered functional connectivity in patients with multiple sclerosis. , 2006, Brain : a journal of neurology.

[10]  P. Pretorius,et al.  The role of MRI in the diagnosis of MS. , 2003, Clinical radiology.

[11]  J. Udupa,et al.  A new computer-assisted method for the quantification of enhancing lesions in multiple sclerosis. , 1997, Journal of computer assisted tomography.

[12]  M. Horsfield,et al.  Intra- and inter-observer agreement of brain MRI lesion volume measurements in multiple sclerosis. A comparison of techniques. , 1995, Brain : a journal of neurology.

[13]  Marco Rovaris,et al.  The effect of repositioning on brain MRI lesion load assessment in multiple sclerosis: reliability of subjective quality criteria , 1998, Journal of Neurology.

[14]  R. Kikinis,et al.  Quantitative follow‐up of patients with multiple sclerosis using MRI: Technical aspects , 1999, Journal of magnetic resonance imaging : JMRI.

[15]  D. Altman,et al.  STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT , 1986, The Lancet.

[16]  F. Lublin,et al.  Multiple sclerosis trial designs for the 21st century: Building on recent lessons , 2005, Journal of neurology.

[17]  Supun Samarasekera,et al.  Fuzzy Connectedness and Object Definition: Theory, Algorithms, and Applications in Image Segmentation , 1996, CVGIP Graph. Model. Image Process..

[18]  J. Kurtzke.  Rating neurologic impairment in multiple sclerosis , 1983, Neurology.

[19]  D L Hill,et al.  Automated three-dimensional registration of magnetic resonance and positron emission tomography brain images by multiresolution optimization of voxel similarity measures. , 1997, Medical physics.

[20]  Alan C. Evans,et al.  Automatic Quantification of MS Lesions in 3D MRI Brain Data Sets: Validation of INSECT , 1998, MICCAI.

[21]  D. Collins,et al.  Automatic 3D Intersubject Registration of MR Volumetric Data in Standardized Talairach Space , 1994, Journal of computer assisted tomography.

[22]  Jayaram K. Udupa,et al.  Scale-Based Fuzzy Connected Image Segmentation: Theory, Algorithms, and Validation , 2000, Comput. Vis. Image Underst..

[23]  J A Frank,et al.  Guidelines for using quantitative measures of brain magnetic resonance imaging abnormalities in monitoring the treatment of multiple sclerosis , 1998, Annals of neurology.

[24]  B J Bedell,et al.  A dual approach for minimizing false lesion classifications on magnetic resonance images , 1997, Magnetic resonance in medicine.

[25]  Massimo Filippi,et al.  European/Canadian multicenter, double‐blind, randomized, placebo‐controlled study of the effects of glatiramer acetate on magnetic resonance imaging–measured disease activity and burden in patients with relapsing multiple sclerosis , 2001, Annals of neurology.

[26]  G. Barker,et al.  Quantification of MRI lesion load in multiple sclerosis: a comparison of three computer-assisted techniques. , 1996, Magnetic resonance imaging.

[27]  Michael Wall,et al.  Baseline MRI characteristics of patients at high risk for multiple sclerosis: results from the CHAMPS trial , 2002, Multiple sclerosis.

[28]  M Filippi,et al.  Correlation between brain MRI lesion volume and disability in patients with multiple sclerosis , 1996, Acta neurologica Scandinavica.

[29]  Koen L. Vincken,et al.  Probabilistic segmentation of white matter lesions in MR imaging , 2004, NeuroImage.

[30]  C. Granger,et al.  Intramuscular interferon beta‐1a for disease progression in relapsing multiple sclerosis , 1996, Annals of neurology.

[31]  P. Duquette,et al.  Interferon beta-1b is effective in relapsing-remitting multiple sclerosis. I. Clinical results of a multicenter, randomized, double-blind, placebo-controlled trial. The IFNB Multiple Sclerosis Study Group. , 1993 .

[32]  Koenraad Van Leemput,et al.  Automated segmentation of multiple sclerosis lesions by model outlier detection , 2001, IEEE Transactions on Medical Imaging.

[33]  J Grimaud,et al.  Effect of training and different measurement strategies on the reproducibility of brain MRI lesion load measurements in multiple sclerosis , 1998, Neurology.

[34]  J M Bland,et al.  Statistical methods for assessing agreement between two methods of clinical measurement , 1986 .

[35]  S Milani,et al.  Linear models for the analysis of variability in factorial designs: an application to anthropometric indicators. , 1985, Statistics in medicine.

[36]  R. Killiany,et al.  Quantitative follow‐up of patients with multiple sclerosis using MRI: Reproducibility , 1999, Journal of magnetic resonance imaging : JMRI.

[37]  R. Kikinis,et al.  Routine quantitative analysis of brain and cerebrospinal fluid spaces with MR imaging , 1992, Journal of magnetic resonance imaging : JMRI.

[38]  F. Barkhof,et al.  Interscanner variation in brain MRI lesion load measurements in MS: Implications for clinical trials , 1997, Neurology.