Türkan, YaseminTek, Faik Boray2022-05-232022-05-232021-09-17Türkan, Y. & Tek, F. B. (2021). Convolutional attention network for MRI-based Alzheimer's disease classification and its interpretability analysis. Paper presented at the 2021 6th International Conference on Computer Science and Engineering (UBMK), 151-156. doi:10.1109/UBMK52708.2021.95588829781665429085978166542907897816654290922521-16412768-0592https://hdl.handle.net/11729/4351http://dx.doi.org/10.1109/UBMK52708.2021.9558882Neuroimaging techniques, such as Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET), help to identify Alzheimer's disease (AD). These techniques generate large-scale, high-dimensional, multimodal neuroimaging data, which is time-consuming and difficult to interpret and classify. Therefore, interest in deep learning approaches for the classification of 3D structural MRI brain scans has grown rapidly. In this research study, we improved the 3D VGG model proposed by Korolev et al. [2]. We increased the filters in the 3D convolutional layers and then added an attention mechanism for better classification. We compared the performance of the proposed approaches for the classification of Alzheimer's disease versus mild cognitive impairments and normal cohorts on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. We observed that both the accuracy and area under curve results improved with the proposed models. However, deep neural networks are black boxes that produce predictions that require further explanation for medical usage. We compared the 3D-data interpretation capabilities of the proposed models using four different interpretability methods: Occlusion, 3D Ultrametric Contour Map, 3D Gradient-Weighted Class Activation Mapping, and SHapley Additive explanations (SHAP). We observed that explanation results differed in different network models and data classes.eninfo:eu-repo/semantics/closedAccess3D Modeling3D Structural MRI brain scans3D Ultrametric contour map3D VGG model3D-Data interpretation capabilitiesActivation analysisActivation mappingAlzheimer’s diseaseAlzheimers diseaseAttentionAttention mechanismBiomedical MRIBrainChemical activationClassification (of information)CognitionContour mapConvolutionConvolutional attention networkConvolutional networksConvolutional neural networksDeep learningDeep learning approachesDeep neural networksDifferent interpretability methodsDifferent network modelsDiseasesHeating systemsHigh-dimensional neuroimaging dataImage classificationInterpretabilityInterpretability analysisLearning (artificial intelligence)Magnetic resonance imagingMappingMedical image processingMild cognitive impairmentsMRIMRI-based AlzheimerMultimodal neuroimaging dataNeural netsNeurodegenerative diseasesNeuroimagingNeuroimaging techniquesNeurophysiologyOcclusionPositron emission tomographySHAPShapleyShapley additive explanationSolid modelingThree-dimensional displaysUltrametricsVisualizationConference Object1511562-s2.0-8512587511610.1109/UBMK52708.2021.9558882N/A