Morphometric analysis of white matter lesions in MR images: method and validation

The analysis of MR images is evolving from qualitative to quantitative. More and more, the question asked by clinicians is how much and where, rather than a simple statement on the presence or absence of abnormalities. The authors present a study in which the results obtained with a semiautomatic, multispectral segmentation technique are quantitatively compared to manually delineated regions. The core of the semiautomatic image analysis system is a supervised artificial neural network classifier augmented with dedicated preand postprocessing algorithms, including anisotropic noise filtering and a surface-fitting method for the correction of spatial intensity variations. The study was focused on the quantitation of white matter lesions in the human brain. A total of 36 images from six brain volumes was analyzed twice by each of two operators, under supervision of a neuroradiologist. Both the intra- and interrater variability of the methods were studied in terms of the average tissue area detected per slice, the correlation coefficients between area measurements, and a measure of similarity derived from the kappa statistic. The results indicate that, compared to a manual method, the use of the semiautomatic technique not only facilitates the analysis of the images, but also has similar or lower intra- and interrater variabilities.

[1]  V M Haughton,et al.  Multiple sclerosis: specificity of MR for diagnosis. , 1991, Radiology.

[2]  Aaron Fenster,et al.  Automated detection and quantification of multiple sclerosis lesions in MR volumes of the brain , 1992, Medical Imaging.

[3]  P. Scheltens,et al.  A semiquantative rating scale for the assessment of signal hyperintensities on magnetic resonance imaging , 1993, Journal of the Neurological Sciences.

[4]  Benoit M. Dawant,et al.  Correction of intensity variations in MR images for computer-aided tissue classification , 1993, IEEE Trans. Medical Imaging.

[5]  K. Baum,et al.  Periventricular Plaques in Multiple Sclerosis: Irreversible? , 1992 .

[6]  K. Lim,et al.  Segmentation of MR Brain Images into Cerebrospinal Fluid Spaces, White and Gray Matter , 1989, Journal of computer assisted tomography.

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

[8]  B M Dawant,et al.  Automatic detection of intracranial contours in MR images. , 1994, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[9]  P. Narayana,et al.  Accuracy and Reproducibility in Volumetric Analysis of Multiple Sclerosis Lesions , 1993, Journal of computer assisted tomography.

[10]  B C Bowen,et al.  MR signal abnormalities in memory disorder and dementia. , 1990, AJNR. American journal of neuroradiology.

[11]  Kazuo Miyasaka,et al.  MRI findings of multiple sclerosis with acute transverse myelopathy , 1992, Journal of the Neurological Sciences.

[12]  J J Bartko,et al.  ON THE METHODS AND THEORY OF RELIABILITY , 1976, The Journal of nervous and mental disease.

[13]  J. Fleiss Measuring agreement between two judges on the presence or absence of a trait. , 1975, Biometrics.

[14]  D. Louis Collins,et al.  Model-based 3-D segmentation of multiple sclerosis lesions in dual-echo MRI data , 1992, Other Conferences.

[15]  Frederik Barkhof,et al.  Magnetic Resonance Imaging Hyperintensities in Alzheimer's Disease-Reply , 1991 .

[16]  J. Fleiss Measuring nominal scale agreement among many raters. , 1971 .

[17]  Guido Gerig,et al.  Nonlinear anisotropic filtering of MRI data , 1992, IEEE Trans. Medical Imaging.

[18]  J. V. van Swieten,et al.  Periventricular lesions in the white matter on magnetic resonance imaging in the elderly. A morphometric correlation with arteriolosclerosis and dilated perivascular spaces. , 1991, Brain : a journal of neurology.

[19]  B L Miller,et al.  Neuropsychological correlates of white-matter lesions in healthy elderly subjects. A threshold effect. , 1992, Archives of neurology.

[20]  W Schörner,et al.  Periventricular plaques in multiple sclerosis: irreversible? An MRI follow-up study. , 1992, European neurology.

[21]  Douglas L. Rickman,et al.  Validation of magnetic resonance imaging (MRI) multispectral tissue classification , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[22]  Y. Chien,et al.  Pattern classification and scene analysis , 1974 .

[23]  P. Murali Doraiswamy,et al.  Magnetic resonance imaging hyperintensities in Alzheimer's disease. , 1991, Archives of neurology.

[24]  J. Bartko Measurement and reliability: statistical thinking considerations. , 1991, Schizophrenia bulletin.

[25]  G. Press,et al.  Methods for measuring brain morphologic features on magnetic resonance images. Validation and normal aging. , 1990, Archives of neurology.

[26]  Benoit M. Dawant,et al.  Neural-network-based segmentation of multi-modal medical images: a comparative and prospective study , 1993, IEEE Trans. Medical Imaging.

[27]  R. Bornstein,et al.  Magnetic resonance imaging of white matter lesions in HIV infection. , 1992, The Journal of neuropsychiatry and clinical neurosciences.

[28]  P. Scheltens,et al.  White matter lesions on magnetic resonance imaging in clinically diagnosed Alzheimer's disease. Evidence for heterogeneity. , 1992, Brain : a journal of neurology.

[29]  B Horwitz,et al.  White matter hyperintensities in dementia of Alzheimer's type and in healthy subjects without cerebrovascular risk factors. A magnetic resonance imaging study. , 1990, Archives of neurology.

[30]  P. Murali Doraiswamy,et al.  Magnetic resonance findings in patients with early-onset Alzheimer's disease , 1991, Biological Psychiatry.

[31]  Russell M. Mersereau,et al.  Automatic Detection of Brain Contours in MRI Data Sets , 1991, IPMI.

[32]  J. Friedman,et al.  Quantitative MRI studies for assessment of multiple sclerosis , 1992, Magnetic resonance in medicine.

[33]  Reinhold Schmidt,et al.  Magnetic Resonance Imaging Hyperintensities in Alzheimer's Disease , 1991 .

[34]  I Kapouleas Automatic detection of white matter lesions in magnetic resonance brain images. , 1990, Computer methods and programs in biomedicine.