Classification of sMRI for AD Diagnosis with Convolutional Neuronal Networks: A Pilot 2-D+ϵ Study on ADNI

• Main Authors: Aderghal, Karim, Manuel, Boissenin, Benois-Pineau, Jenny, Gwenaêlle, Catheline, Afdel, Karim
• Other Authors: Laboratoire Bordelais de Recherche en Informatique (LaBRI), Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB), Toubkal, Laurent Amsaleg, Gylfi Þór Guðmundsson, Cathal Gurrin, Björn Þór Jónsson, Shin’ichi Satoh, TOUBKAL Alclass 2016-2019
• Format: Conference Object
• Language: English
• Published: HAL CCSD 2017
• Subjects: Alzheimer’s disease; AD; Convolutional neural network; CNN; Deep learning; Structural magnetic resonance imaging; sMRI; Hippocampus; Computer-aided diagnosis; CAD; ACM: H.: Information Systems; [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM]; [INFO]Computer Science [cs]; [SPI]Engineering Sciences [physics]; [SDV]Life Sciences [q-bio]; Iceland
• Online Access: https://hal.archives-ouvertes.fr/hal-01436299; https://doi.org/10.1007/978-3-319-51811-4_56

International audience In interactive health care systems, Convolutional Neural Networks (CNN) are starting to have their applications, e.g. the classification of structural Magnetic Resonance Imaging (sMRI) scans for Alzheimer’s disease Computer-Aided Diagnosis (CAD). In this paper we focus on the hippocampus morphology which is known to be affected in relation with the progress of the illness. We use a subset of the ADNI (Alzheimer’s Disease Neuroimaging Initiative) database to classify images belonging to Alzheimer’s disease (AD), mild cognitive impairment (MCI) and normal control (NC) subjects. As the number of images in such studies is rather limited regarding the needs of CNN, we propose a data augmentation strategy adapted to the specificity of sMRI scans. We also propose a 2-D+ϵ approach, where only a very limited amount of consecutive slices are used for training and classification. The tests conducted on only one - saggital - projection show that this approach provides good classification accuracies: AD/NC 82.8% MCI/NC 66% AD/MCI 62.5% that are promising for integration of this 2-D+ϵ strategy in more complex multi-projection and multi-modal schemes.