Automated detection and characterization of multiple sclerosis lesions in brain MR images.

In the present study an automatic algorithm for detection and contouring of multiple sclerosis (MS) lesions in brain magnetic resonance (MR) images is introduced. This algorithm automatically detects MS lesions in axial proton density, T2-weighted, gadolinium enhanced, and fast fluid attenuated inversion recovery (FLAIR) brain MR images. Automated detection consists of three main stages: (1) detection and contouring of all hyperintense signal regions within the image; (2) partial elimination of false positive segments (defined herein as artifacts) by size, shape index, and anatomical location; (3) the use of an artificial neural paradigm (Back-Propagation) for final removal of artifacts by differentiating them from true MS lesions. The algorithm was applied to 45 images acquired from 14 MS patients. The algorithm's sensitivity was 0.87 and the specificity 0.96. In 34 images, 100% of the lesions were detected. The algorithm potentially may serve as a useful preprocessing tool for quantitative MS monitoring via magnetic resonance imaging.

[1]  Alan C. Evans,et al.  The Role of MRI in clinical trials of multiple sclerosis: Comparison of image processing techniques , 1997, Annals of neurology.

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

[3]  A. Thompson,et al.  Magnetic resonance imaging in monitoring the treatment of multiple sclerosis: concerted action guidelines. , 1991, Journal of neurology, neurosurgery, and psychiatry.

[4]  M. Horsfield,et al.  Quantitative assessment of MRI lesion load in monitoring the evolution of multiple sclerosis. , 1995, Brain : a journal of neurology.

[5]  R. Knobler,et al.  Neuropsychological and structural brain lesions in multiple sclerosis , 1992, Neurology.

[6]  Stamatios V. Kartalopoulos,et al.  Understanding neural networks and fuzzy logic , 1995 .

[7]  J K Udupa,et al.  Computer-assisted quantitation of enhancing lesions in multiple sclerosis: correlation with clinical classification. , 1997, AJNR. American journal of neuroradiology.

[8]  Stamatios V. Kartalopoulos,et al.  Understanding neural networks and fuzzy logic - basic concepts and applications , 1997 .

[9]  D G Gibson,et al.  Continuous assessment of left ventricular shape in man. , 1975, British heart journal.

[10]  Alan C. Evans,et al.  Experiments in the automated detection of multiple sclerosis brain lesions in magnetic resonance images , 1993, Proceedings of 9th IEEE Conference on Artificial Intelligence for Applications.

[11]  D. Miller,et al.  Magnetic resonance in monitoring the treatment of multiple sclerosis , 1994, Annals of neurology.

[12]  J. Taveras,et al.  Abnormal corpus callosum: a sensitive and specific indicator of multiple sclerosis. , 1991, Radiology.

[13]  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.

[14]  L S Honig,et al.  Magnetic resonance imaging of spinal cord lesions in multiple sclerosis. , 1989, Journal of neurology, neurosurgery, and psychiatry.

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

[16]  V. Haughton,et al.  Correlation of magnetic resonance imaging with neuropsychological testing in multiple sclerosis , 1989, Neurology.

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

[18]  D. Paty,et al.  Interferon beta‐1b is effective in relapsing‐remitting multiple sclerosis , 1993, Neurology.

[19]  Judith E. Dayhoff,et al.  Neural Network Architectures: An Introduction , 1989 .

[20]  S R Arridge,et al.  Using greyscale voxel databases for improved shading and segmentation. , 1989, Medical informatics = Medecine et informatique.

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

[22]  N. Patronas,et al.  Serial gadolinium‐enhanced magnetic resonance imaging scans in patients with early, relapsing‐remitting multiple sclerosis: Implications for clinical trials and natural history , 1991, Annals of neurology.

[23]  A J Thompson,et al.  Correlations between changes in disability and T2‐weighted brain MRI activity in multiple sclerosis , 1995, Neurology.

[24]  G. Barker,et al.  The MRI measurement of NMR and physiological parameters in tissue to study disease process. , 1991, Progress in clinical and biological research.