Chaves, RosaRamírez, JavierGórriz, Juan MIllán, Ignacio AGómez-Río, ManuelCarnero, Cristobal2013-11-252013-11-252012-07-31Chaves R, Ramírez J, Górriz JM, Illán IA, Gómez-Río M, Carnero C. Effective diagnosis of Alzheimer's disease by means of large margin-based methodology. BMC Med Inform Decis Mak; 12:79http://hdl.handle.net/10668/1395Comparative Study; Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't;BACKGROUND Functional brain images such as Single-Photon Emission Computed Tomography (SPECT) and Positron Emission Tomography (PET) have been widely used to guide the clinicians in the Alzheimer's Disease (AD) diagnosis. However, the subjectivity involved in their evaluation has favoured the development of Computer Aided Diagnosis (CAD) Systems. METHODS It is proposed a novel combination of feature extraction techniques to improve the diagnosis of AD. Firstly, Regions of Interest (ROIs) are selected by means of a t-test carried out on 3D Normalised Mean Square Error (NMSE) features restricted to be located within a predefined brain activation mask. In order to address the small sample-size problem, the dimension of the feature space was further reduced by: Large Margin Nearest Neighbours using a rectangular matrix (LMNN-RECT), Principal Component Analysis (PCA) or Partial Least Squares (PLS) (the two latter also analysed with a LMNN transformation). Regarding the classifiers, kernel Support Vector Machines (SVMs) and LMNN using Euclidean, Mahalanobis and Energy-based metrics were compared. RESULTS Several experiments were conducted in order to evaluate the proposed LMNN-based feature extraction algorithms and its benefits as: i) linear transformation of the PLS or PCA reduced data, ii) feature reduction technique, and iii) classifier (with Euclidean, Mahalanobis or Energy-based methodology). The system was evaluated by means of k-fold cross-validation yielding accuracy, sensitivity and specificity values of 92.78%, 91.07% and 95.12% (for SPECT) and 90.67%, 88% and 93.33% (for PET), respectively, when a NMSE-PLS-LMNN feature extraction method was used in combination with a SVM classifier, thus outperforming recently reported baseline methods. CONCLUSIONS All the proposed methods turned out to be a valid solution for the presented problem. One of the advances is the robustness of the LMNN algorithm that not only provides higher separation rate between the classes but it also makes (in combination with NMSE and PLS) this rate variation more stable. In addition, their generalization ability is another advance since several experiments were performed on two image modalities (SPECT and PET).enAncianoAlgoritmosEnfermedad de AlzheimerInteligencia ArtificialInterpretación Estadística de DatosDiagnóstico PrecozFemeninoNeuroimagen FuncionalInterpretación de Imagen Asistida por ComputadorTomografía de Emisión de PositronesAnálisis de Componente PrincipalRadiofármacosSensibilidad y EspecificidadEspañaTomografía Computarizada de Emisión de Fotón ÚnicoMedical Subject Headings::Named Groups::Persons::Age Groups::Adult::AgedMedical Subject Headings::Named Groups::Persons::Age Groups::Adult::Aged::Aged, 80 and overMedical Subject Headings::Phenomena and Processes::Mathematical Concepts::AlgorithmsMedical Subject Headings::Diseases::Nervous System Diseases::Central Nervous System Diseases::Brain Diseases::Dementia::Alzheimer DiseaseMedical Subject Headings::Information Science::Information Science::Computing Methodologies::Artificial IntelligenceMedical Subject Headings::Analytical, Diagnostic and Therapeutic Techniques and Equipment::Investigative Techniques::Decision Support Techniques::Data Interpretation, StatisticalMedical Subject Headings::Analytical, Diagnostic and Therapeutic Techniques and Equipment::Diagnosis::Early DiagnosisMedical Subject Headings::Check Tags::FemaleMedical Subject Headings::Analytical, Diagnostic and Therapeutic Techniques and Equipment::Diagnosis::Diagnostic Techniques and Procedures::Diagnostic Imaging::Neuroimaging::Functional NeuroimagingMedical Subject Headings::Organisms::Eukaryota::Animals::Chordata::Vertebrates::Mammals::Primates::Haplorhini::Catarrhini::Hominidae::HumansMedical Subject Headings::Analytical, Diagnostic and Therapeutic Techniques and Equipment::Diagnosis::Diagnosis, Computer-Assisted::Image Interpretation, Computer-AssistedMedical Subject Headings::Check Tags::FemaleMedical Subject Headings::Named Groups::Persons::Age Groups::Adult::Middle AgedMedical Subject Headings::Analytical, Diagnostic and Therapeutic Techniques and Equipment::Diagnosis::Diagnostic Techniques and Procedures::Diagnostic Imaging::Image Interpretation, Computer-Assisted::Tomography, Emission-Computed::Positron-Emission TomographyMedical Subject Headings::Analytical, Diagnostic and Therapeutic Techniques and Equipment::Investigative Techniques::Epidemiologic Methods::Statistics as Topic::Principal Component AnalysisMedical Subject Headings::Chemicals and Drugs::Chemical Actions and Uses::Specialty Uses of Chemicals::Laboratory Chemicals::Indicators and Reagents::RadiopharmaceuticalsMedical Subject Headings::Analytical, Diagnostic and Therapeutic Techniques and Equipment::Investigative Techniques::Epidemiologic Methods::Statistics as Topic::Sensitivity and SpecificityMedical Subject Headings::Geographicals::Geographic Locations::Europe::SpainMedical Subject Headings::Analytical, Diagnostic and Therapeutic Techniques and Equipment::Diagnosis::Diagnostic Techniques and Procedures::Diagnostic Imaging::Image Interpretation, Computer-Assisted::Tomography, Emission-Computed::Tomography, Emission-Computed, Single-PhotonMedical Subject Headings::Named Groups::Persons::Age Groups::Adultresearch article22849649open access10.1186/1472-6947-12-791472-6947PMC3512495