Automatic Early Diagnosis of Alzheimer’s Disease Using 3D Deep Ensemble Approach

Abstract

Alzheimer's disease (AD) is considered the 6 th leading cause of death worldwide. Early diagnosis of AD is not an easy task, and no preventive cures have been discovered yet. Having an accurate computer-aided system for the early detection of AD is important to help patients with AD. This study proposes a new approach for classifying disease stages. First, we worked on the MRI images and split them into an appropriate format to avoid data leakage. Subsequently, a simple and fast registration-free preprocessing pipeline was applied to the dataset. Numerous experiments were conducted to analyze the performances of different 3D classification architectures. Finally, an ensemble learning approach is applied to the top-performing models. The outstanding performance of the proposed method was demonstrated using augmentation of the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Our proposed ensemble approach outperforms studies in literature for distinguishing between people with AD and mild cognitive impairment (MCI), and MCI and cognitive normal (CN) with an AUC score of 91.28% and 88.42%, respectively. We also targeted the multiclass task, which was marginalized in previous work, by differentiating between the three stages of the disease.

Certain Studies on Alzheimer's disease: A Comprehensive Review

“…An augmentation of the ADNI dataset was used to show how effective this process is. With AUC values of 91.28% and 88.42%, respectively, the ensemble technique [28] outperformed previous research in the literature regarding better identification between people with AD and MCI and between MCI and cognitive normal (CN). Additionally, the technique showed that it was possible to differentiate between the three stages of the illness.…”

Adversarial Network-Based Classification for Alzheimer’s Disease Using Multimodal Brain Images: A Critical Analysis

“…The overall detection accuracy for AD is 94.08%, 96.39%, and 97.51%, respectively. A. Gamal et al [31] discussed the Ensemble Learning (EL) approach for diagnosing AD. The authors used the ADNI dataset consisting of 789 3D MRI images.…”

Alzheimer’s Disease Detection from Fused PET and MRI Modalities Using an Ensemble Classifier

“…To attain a more accurate and reliable model, researchers propose an ensemble voting approach that combines multiple classifier predictions, yielding impressive results for older individuals in the OASIS data set [43]. This investigation introduces a unique computer-assisted method for early Alzheimer's diagnosis, leveraging MRI images and various 3D classification architectures for image processing and analysis, further enhancing the EL technique's outcomes [44].…”