Smart ROI Detection for Alzheimer's disease prediction using explainable AI

TL;DR

This paper introduces an explainable AI-based method that automatically detects brain regions of interest for improved Alzheimer's disease prediction, achieving high accuracy and outperforming traditional manual ROI methods.

Contribution

A novel automated ROI detection approach using Grad-Cam and 3D CNN for Alzheimer's prediction, reducing manual effort and improving accuracy.

Findings

Accuracy of 98.6% with 5-fold cross-validation

AUC of 1 indicating perfect discrimination

Significant performance boost over whole brain methods

Abstract

Purpose Predicting the progression of MCI to Alzheimer's disease is an important step in reducing the progression of the disease. Therefore, many methods have been introduced for this task based on deep learning. Among these approaches, the methods based on ROIs are in a good position in terms of accuracy and complexity. In these techniques, some specific parts of the brain are extracted as ROI manually for all of the patients. Extracting ROI manually is time-consuming and its results depend on human expertness and precision. Method To overcome these limitations, we propose a novel smart method for detecting ROIs automatically based on Explainable AI using Grad-Cam and a 3DCNN model that extracts ROIs per patient. After extracting the ROIs automatically, Alzheimer's disease is predicted using extracted ROI-based 3D CNN. Results We implement our method on 176 MCI patients of the famous ADNI dataset and obtain remarkable results compared to the state-of-the-art methods. The accuracy acquired using 5-fold cross-validation is 98.6 and the AUC is 1. We also compare the results of the ROI-based method with the whole brain-based method. The results show that the performance is impressively increased. Conclusion The experimental results show that the proposed smart ROI extraction, which extracts the ROIs automatically, performs well for Alzheimer's disease prediction. The proposed method can also be used for Alzheimer's disease classification and diagnosis.