3D Inception-based CNN with sMRI and MD-DTI data fusion for Alzheimer's Disease diagnostics

Abstract

In the last decade, computer-aided early diagnostics of Alzheimers Disease (AD) and its prodromal form, Mild Cognitive Impairment (MCI), has been the subject of extensive research. Some recent studies have shown promising results in the AD and MCI determination using structural and functional Magnetic Resonance Imaging (sMRI, fMRI), Positron Emission Tomography (PET) and Diffusion Tensor Imaging (DTI) modalities. Furthermore, fusion of imaging modalities in a supervised machine learning framework has shown promising direction of research.In this paper we first review major trends in automatic classification methods such as feature extraction based methods as well as deep learning approaches in medical image analysis applied to the field of Alzheimer's Disease diagnostics. Then we propose our own design of a 3D Inception-based Convolutional Neural Network (CNN) for Alzheimer's Disease diagnostics. The network is designed with an emphasis on the interior resource utilization and uses sMRI and DTI modalities fusion on hippocampal ROI. The comparison with the conventional AlexNet-based network using data from the Alzheimers Disease Neuroimaging Initiative (ADNI) dataset (http://adni.loni.usc.edu) demonstrates significantly better performance of the proposed 3D Inception-based CNN.

Alzheimer’s Disease MRI Identification, Recognition, & Evaluation - Deep Learning

“…Beyond that, some studies have investigated other types of CNN architectures, such as Inception networks in [31] and GoogleNets in [32]. There is a massive number of existing architectures that could be explored that aren't necessarily included in Keras applications, that could be explored using the tools that we have created.…”

FastSurfer -- A fast and accurate deep learning based neuroimaging pipeline

“…The task of whole-brain segmentation in particular is challenging due to the complex 3D architecture and spatial dependency between slices, the large number of labels, the size of the scanning volumes (memory requirements), and variability across scanners and subjects. While several deep learning based approaches have been proposed for specific tasks, such as tumor segmentation [22,23,24,25,26,27], brain lesion segmentation [28,29,30,31,32], MR image reconstruction [33,34,35,36,37,38] or prediction of brain related diseases and their progression [39,40,41,42,43] full brain segmentation into more than 25 classes has -so far -only been achieved by a few groups [44,45,46,47,48].…”