Multiscale Deep Convolutional Networks for Characterization and Detection of Alzheimer's Disease Using MR images

• Published in: Proceedings - International Conference on Image Processing Vol. 2019-September; pp. 789 - 793
• Main Authors: Ge, Chenjie, Qu, Qixun, Gu, Irene Yu-Hua, Store Jakola, Asgeir
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2019
• Subjects: Alzheimer's disease; Alzheimer's disease detection; Feature extraction; feature fusion and enhancement; Magnetic resonance imaging; Medical Imaging; Medicinsk bildvetenskap; MR images; multiscale CNN; multiscale features; Neurologi; Neurology; Radiologi och bildbehandling; Radiology and Medical Imaging; Testing; Three-dimensional displays; Training
• ISSN: 1522-4880; 2381-8549
• DOI: 10.1109/ICIP.2019.8803731

This paper addresses the issues of Alzheimer's disease (AD) characterization and detection from Magnetic Resonance Images (MRIs). Many existing AD detection methods use single-scale feature learning from brain scans. In this paper, we propose a multiscale deep learning architecture for learning AD features. The main contributions of the paper include: (a) propose a novel 3D multiscale CNN architecture for the dedicated task of AD detection; (b) propose a feature fusion and enhancement strategy for multiscale features; (c) empirical study on the impact of several settings, including two dataset partitioning approaches, and the use of multiscale and feature enhancement. Experiments were conducted on an open ADNI dataset (1198 brain scans from 337 subjects), test results have shown the effectiveness of the proposed method with test accuracy of 93.53%, 87.24% (best, average) on subject-separated dataset, and 99.44%, 98.80% (best, average) on random brain scan-partitioned dataset. Comparison with eight existing methods has provided further support to the proposed method.