Biceph-Net: A robust and lightweight framework for the diagnosis of Alzheimer's disease using 2D-MRI scans and deep similarity learning

TL;DR

Biceph-Net is a lightweight deep learning framework that effectively diagnoses Alzheimer's disease from 2D MRI slices by modeling intra- and inter-slice information, achieving high accuracy and interpretability.

Contribution

It introduces Biceph-Net, a novel, efficient model that captures both intra- and inter-slice features for AD diagnosis from 2D MRI scans, outperforming standard CNNs.

Findings

Achieves 100% accuracy in CN vs AD classification

Attains 98.16% accuracy in MCI vs AD classification

Provides neighborhood-based interpretation of decisions

Abstract

Alzheimer's Disease (AD) is a neurodegenerative disease that is one of the significant causes of death in the elderly population. Many deep learning techniques have been proposed to diagnose AD using Magnetic Resonance Imaging (MRI) scans. Predicting AD using 2D slices extracted from 3D MRI scans is challenging as the inter-slice information gets lost. To this end, we propose a novel and lightweight framework termed 'Biceph-Net' for AD diagnosis using 2D MRI scans that model both the intra-slice and inter-slice information. Biceph-Net has been experimentally shown to perform similar to other Spatio-temporal neural networks while being computationally more efficient. Biceph-Net is also superior in performance compared to vanilla 2D convolutional neural networks (CNN) for AD diagnosis using 2D MRI slices. Biceph-Net also has an inbuilt neighbourhood-based model interpretation feature that can be exploited to understand the classification decision taken by the network. Biceph-Net experimentally achieves a test accuracy of 100% in the classification of Cognitively Normal (CN) vs AD, 98.16% for Mild Cognitive Impairment (MCI) vs AD, and 97.80% for CN vs MCI vs AD.