DeepCurvMRI: Deep Convolutional Curvelet Transform-Based MRI Approach for Early Detection of Alzheimer’s Disease

Abstract

Alzheimer's Disease (AD) is the most common form of dementia. It usually manifests through progressive loss of cognitive function and memory, subsequently impairing the person's ability to live without assistance and causing a tremendous impact on the affected individuals and society. Currently, AD diagnosis relies on cognitive tests, blood tests, behavior assessments, brain imaging, and medical history analysis. However, these procedures are subjective and inconsistent, making an accurate prediction for the early stages of AD difficult. This paper introduces a curvelet transform (CT) based-convolutional neural network (CNN) (DeepCurvMRI) model for improving the accuracy of early-stage AD disease detection using from Magnetic resonance imaging (MRI) images. The MRI images were first pre-processed using CT, and then a CNN model was trained using the new image representation. In this study, we used Alzheimer's MRI images dataset hosted on the Kaggle platform to train DeepCurvMRI for multi and binary classification tasks. DeepCurvMRI achieved an accuracy, sensitivity, specificity, and F1 score of 98.62% ± 0.10%, 99.05% ± 0.10%, 98.50% ± 0.03%, and 99.21 ± 0.08, respectively, using the leave-one-group-out (LOGO) cross-validation approach in multi-classification task. The highest accuracy obtained in binary classification is 98.71% ± 0.05%. In addition to LOGO, DeepCurvMRI was tested using randomly stratified 10-fold and 5-fold cross validation. These encouraging results are superior to the ones reported in related methods, showcasing the potentiality of DeepCurvMRI in capturing the key anatomical changes in MRI images that can be differentiated between various staged of Alzheimer's disease classes.INDEX TERMS Alzheimer's disease, curvelet transform, deep learning, CNN, MRI images.

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

“…In the result analysis, the model achieved 83%, 81%, and 85% precision for healthy, mild, and severe AD. C. M. Chabib et al [22] suggested a DeepCurvMRI model that combined a CNN and the Curvelet Transform (CT) to improve the accuracy of early-stage AD identification using MRI scans. After pre-processing the MRI images with CT, these modified images were used to train the CNN model.…”

“…Meanwhile, ADNI [1], [45], [47], and the Open Access Series of Imaging Studies (OASIS) [36], [37] stand out as significant contributors to advancing research in this domain. Structural MRI [2], [18], [27], [32], [33], [36], [39] OASIS MRI MRI images with a focus on brain tumor detection Structural MRI [5], [8], [14], [15], [17], [19], [21], [22], [24], [25], [36], [37], [38], [42], [43] MRI ADNI Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset Functional and Structural MRI, PET [1], [4], [4], [7], [16], [23], [28], [29], [30], [40], [41], [44], [45] ADNI GARD Gwangju Alzheimer's and Related Dementia (GARD) dataset…”

Certain Studies on Alzheimer's disease: A Comprehensive Review

“…First, the MRI pictures were preprocessed using CT, and then the CNN model was trained using this new representation of the data. DeepCurvMRI [38] was trained on the Alzheimer's MRI images dataset that is accessible on the Kaggle platform for both binary and multi-class classification tasks.…”

Residual-Based Multi-Stage Deep Learning Framework for Computer-Aided Alzheimer’s Disease Detection

“…Recently, researchers have focused on two main approaches for training and classifying models, conventional learning and deep learning, as they proved excellent in other domains [ 28 , 29 , 30 ]. Recent studies like [ 24 , 31 , 32 , 33 , 34 ] used conventional learning for AD classification, while studies like [ 5 , 35 , 36 , 37 , 38 ] employed deep learning techniques.…”

“…The Kaggle ADNI version dataset was used by Chabib et al [ 38 ] to employ curvelet transform (CT) based on the CNN model to determine early-stage AD detection. They first used CT for pre-processing, then a CNN model was trained to utilize it for new image representation.…”