Research Article Classifying Dementia Using Local Binary Patterns from Different Regions in Magnetic Resonance Images Ketil Oppedal, 1,2 Trygve Eftestøl, 1 Kjersti Engan, 1 Mona K. Beyer, 3,4 and Dag Aarsland 2,5 1 Department of Electrical Engineering and Computer Science, University of Stavanger, 4036 Stavanger, Norway 2 Centre for Age-Related Medicine, Stavanger University Hospital, Stavanger, Norway 3 Department of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway 4 Department of Life Sciences and Health, Faculty of Health Sciences, Oslo and Akershus University College of Applied Sciences, Oslo, Norway 5 Alzheimer’s Disease Research Centre, Karolinska Institutet (KI), Stockholm, Sweden Correspondence should be addressed to Ketil Oppedal; ketil.oppedal@gmail.com Received 18 December 2014; Revised 26 February 2015; Accepted 2 March 2015 Academic Editor: Yantian Zhang Copyright © 2015 Ketil Oppedal et al. his is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Dementia is an evolving challenge in society, and no disease-modifying treatment exists. Diagnosis can be demanding and MR imaging may aid as a noninvasive method to increase prediction accuracy. We explored the use of 2D local binary pattern (LBP) extracted from FLAIR and T1 MR images of the brain combined with a Random Forest classiier in an attempt to discern patients with Alzheimer’s disease (AD), Lewy body dementia (LBD), and normal controls (NC). Analysis was conducted in areas with white matter lesions (WML) and all of white matter (WM). Results from 10-fold nested cross validation are reported as mean accuracy, precision, and recall with standard deviation in brackets. he best result we achieved was in the two-class problem NC versus AD + LBD with total accuracy of 0.98 (0.04). In the three-class problem AD versus LBD versus NC and the two-class problem AD versus LBD, we achieved 0.87 (0.08) and 0.74 (0.16), respectively. he performance using 3DT1 images was notably better than when using FLAIR images. he results from the WM region gave similar results as in the WML region. Our study demonstrates that LBP texture analysis in brain MR images can be successfully used for computer based dementia diagnosis. 1. Introduction Dementia Is an Evolving Challenge. As a result of increasing age, dementia is an evolving challenge in society. he annual health care costs related to dementia were estimated to $604 billion worldwide in 2010 [1]. Alzheimer’s disease (AD) is the most common neurodegenerative dementia and accounts for 50–60% of people with dementia [2]. he classical neuropathological signs of AD are amyloid plaques and neuroibrillary tangles [3]. No eicient disease-modifying treatment for AD exists today. Dementia with Lewy-bodies (DLB) together with dementia associated with Parkinson’s disease (PDD) account for 15–20% of people with dementia [2]. he deining pathological feature for these patients is Lewy-body degeneration in brain stem, forebrain, and limbic and cortical structures, and the DLB and PDD are therefore oten combined into a Lewy-body dementia group (LBD) [4, 5]. However, the relationship between localization and density of Lewy-bodies with clinical dementia symptoms is not strong [6], suggesting that other pathologies contribute as well, such as AD pathology and vascular brain changes seen as white matter hyperintensities (WML) or lacunar infarcts, which may contribute to the clinical presentation of LBD. For example, vascular changes in the basal ganglia are common in the elderly and may cause parkinsonism and cognitive impairment [7]. Early Diagnosis Is Important. AD and LBD are very complex diseases making them diicult to be prevented, delayed, or cured. Current therapy focuses on many approaches, for example, helping patients maintain an acceptable mental functioning, managing typical behavioural changes, and slowing symptom progression. Early intervention is impor- tant, and the ability to identify these types of dementia and healthy controls early in the disease course may be essential for successful patient care. Diferentiating between Hindawi Publishing Corporation International Journal of Biomedical Imaging Volume 2015, Article ID 572567, 14 pages http://dx.doi.org/10.1155/2015/572567