MRI Pattern Recognition in Multiple Sclerosis Normal-Appearing Brain Areas

• Published in: PloS one Vol. 6; no. 6; p. e21138
• Main Authors: Weygandt, Martin, Hackmack, Kerstin, Pfüller, Caspar, Bellmann–Strobl, Judith, Paul, Friedemann, Zipp, Frauke, Haynes, John­–Dylan
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 17.06.2011; Public Library of Science (PLoS)
• Subjects: Adult; Algorithms; Alzheimer's disease; Alzheimers disease; Anatomy; Automation; Brain; Brain - cytology; Brain - pathology; Brain architecture; Brain research; Case-Control Studies; Cerebellum; Classification; Data mining; Deformation; Diagnosis; Diagnostic systems; Eating disorders; Female; Humans; Image Interpretation, Computer-Assisted - methods; Lesions; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Mapping; Mathematics; Medical imaging; Medicine; Methods; Multiple sclerosis; Multiple Sclerosis - diagnosis; Multiple Sclerosis - pathology; Neurosciences; NMR; Nuclear magnetic resonance; Patients; Pattern classification; Pattern recognition; Pattern Recognition, Automated - methods; Questioning; Standardization; Studies; Substantia alba; Substantia grisea; Germany
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0021138

Here, we use pattern-classification to investigate diagnostic information for multiple sclerosis (MS; relapsing-remitting type) in lesioned areas, areas of normal-appearing grey matter (NAGM), and normal-appearing white matter (NAWM) as measured by standard MR techniques. A lesion mapping was carried out by an experienced neurologist for Turbo Inversion Recovery Magnitude (TIRM) images of individual subjects. Combining this mapping with templates from a neuroanatomic atlas, the TIRM images were segmented into three areas of homogenous tissue types (Lesions, NAGM, and NAWM) after spatial standardization. For each area, a linear Support Vector Machine algorithm was used in multiple local classification analyses to determine the diagnostic accuracy in separating MS patients from healthy controls based on voxel tissue intensity patterns extracted from small spherical subregions of these larger areas. To control for covariates, we also excluded group-specific biases in deformation fields as a potential source of information. Among regions containing lesions a posterior parietal WM area was maximally informative about the clinical status (96% accuracy, p<10(-13)). Cerebellar regions were maximally informative among NAGM areas (84% accuracy, p<10(-7)). A posterior brain region was maximally informative among NAWM areas (91% accuracy, p<10(-10)). We identified regions indicating MS in lesioned, but also NAGM, and NAWM areas. This complements the current perception that standard MR techniques mainly capture macroscopic tissue variations due to focal lesion processes. Compared to current diagnostic guidelines for MS that define areas of diagnostic information with moderate spatial specificity, we identified hotspots of MS associated tissue alterations with high specificity defined on a millimeter scale.