Attention-based Efficient Classification for 3D MRI Image of Alzheimer's Disease

TL;DR

This paper introduces an efficient 3D MRI classification model for Alzheimer's disease that combines a pre-trained ResNet backbone, a post-fusion algorithm, and attention mechanisms to improve accuracy and reduce training costs.

Contribution

It presents a novel combination of 2D fusion and attention mechanisms within a ResNet-based framework for Alzheimer's detection in 3D MRI images.

Findings

Improved diagnostic accuracy with attention mechanisms

Reduced training expense through 2D fusion algorithm

Effective weighting of important brain regions

Abstract

Early diagnosis of Alzheimer Diagnostics (AD) is a challenging task due to its subtle and complex clinical symptoms. Deep learning-assisted medical diagnosis using image recognition techniques has become an important research topic in this field. The features have to accurately capture main variations of anatomical brain structures. However, time-consuming is expensive for feature extraction by deep learning training. This study proposes a novel Alzheimer's disease detection model based on Convolutional Neural Networks. The model utilizes a pre-trained ResNet network as the backbone, incorporating post-fusion algorithm for 3D medical images and attention mechanisms. The experimental results indicate that the employed 2D fusion algorithm effectively improves the model's training expense. And the introduced attention mechanism accurately weights important regions in images, further enhancing the model's diagnostic accuracy.