# A Dual Stream Deep Learning Framework for Alzheimer’s Disease Detection Using MRI Sonification

## TL;DR

This paper introduces a new method for detecting Alzheimer's disease by combining MRI images with their audio versions, achieving high accuracy in diagnosis.

## Contribution

The novel dual-stream framework integrates MRI images and sonified audio for Alzheimer’s detection, achieving state-of-the-art accuracy.

## Key findings

- The multimodal framework achieved 98.2% accuracy in distinguishing Alzheimer’s from cognitively normal subjects.
- It also showed 94% accuracy for Alzheimer’s vs. mild cognitive impairment and 93.2% for mild cognitive impairment vs. cognitively normal.
- MRI sonification provides complementary diagnostic information when combined with image-based methods.

## Abstract

Alzheimer’s Disease (AD) is an advanced brain illness that affects millions of individuals across the world. It causes gradual damage to the brain cells, leading to memory loss and cognitive dysfunction. Although Magnetic Resonance Imaging (MRI) is widely used in AD diagnosis, the existing studies rely solely on the visual representations, leaving alternative features unexplored. The objective of this study is to explore whether MRI sonification can provide complementary diagnostic information when combined with conventional image-based methods. In this study, we propose a novel dual-stream multimodal framework that integrates 2D MRI slices with their corresponding audio representations. MRI images are transformed into audio signals using a multi-scale, multi-orientation Gabor filtering, followed by a Hilbert space-filling curve to preserve spatial locality. The image and sound modalities are processed using a lightweight CNN and YAMNet, respectively, then fused via logistic regression. The experimental results of the multimodal achieved the highest accuracy in distinguishing AD from Cognitively Normal (CN) subjects at 98.2%, 94% for AD vs. Mild Cognitive Impairment (MCI), and 93.2% for MCI vs. CN. This work provides a new perspective and highlights the potential of audio transformation of imaging data for feature extraction and classification.