A Multi-modal Convolutional Neural Network Framework for the Prediction of Alzheimer's Disease

This paper presents a multi-modal Alzheimer's disease (AD) classification framework based on a convolutional neural network (CNN) architecture. The devised model takes structural MRI, and clinical assessment and genetic (APOe4) measures as inputs. Our CNN structure is designed to be efficient in its use of parameters which reduces overfitting, computational complexity, memory requirements and speed of prototyping. This is achieved by factorising the convolutional layers in parallel streams which also enables the simultaneous extraction of high and low level feature representations. Our method consistently achieves high classification results in discriminating between AD and control subjects with an average of 99% accuracy, 98% sensitivity, 100% specificity and an AUC of 1 across all test folds. Our study confirms that careful tuning of CNN characteristics can result in a framework which delivers extremely accurate predictions in a clinical problem despite data paucity, opening new avenues for application to prediction tasks which regard patient stratification, prediction of clinical evolution and eventually personalised medicine applications.