Premium
Usability and Potential of Geostatistics for Spatial Discrimination of Multiple Sclerosis Lesion Patterns
Author(s) -
Marschallinger Robert,
Golaszewski Stefan M.,
Kunz Alexander B.,
Kronbichler Martin,
Ladurner Gunther,
Hofmann Peter,
Trinka Eugen,
McCoy Mark,
Kraus Jörg
Publication year - 2013
Publication title -
journal of neuroimaging
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.822
H-Index - 64
eISSN - 1552-6569
pISSN - 1051-2284
DOI - 10.1111/jon.12000
Subject(s) - medicine , usability , geostatistics , multiple sclerosis , lesion , artificial intelligence , pattern recognition (psychology) , pathology , human–computer interaction , statistics , spatial variability , computer science , psychiatry , mathematics
BACKGROUND AND PURPOSE In multiple sclerosis (MS) the individual disease courses are very heterogeneous among patients and biomarkers for setting the diagnosis and the estimation of the prognosis for individual patients would be very helpful. For this purpose, we are developing a multidisciplinary method and workflow for the quantitative, spatial, and spatiotemporal analysis and characterization of MS lesion patterns from MRI with geostatistics. METHODS We worked on a small data set involving three synthetic and three real‐world MS lesion patterns, covering a wide range of possible MS lesion configurations. After brain normalization, MS lesions were extracted and the resulting binary 3‐dimensional models of MS lesion patterns were subject to geostatistical indicator variography in three orthogonal directions. RESULTS By applying geostatistical indicator variography, we were able to describe the 3‐dimensional spatial structure of MS lesion patterns in a standardized manner. Fitting a model function to the empirical variograms, spatial characteristics of the MS lesion patterns could be expressed and quantified by two parameters. An orthogonal plot of these parameters enabled a well‐arranged comparison of the involved MS lesion patterns. CONCLUSIONS This method in development is a promising candidate to complement standard image‐based statistics by incorporating spatial quantification. The work flow is generic and not limited to analyzing MS lesion patterns. It can be completely automated for the screening of radiological archives.