A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer’s disease

AbstractAlzheimer’s disease (AD) is the most common type of dementia. Its diagnosis and progression detection have been intensively studied. Nevertheless, research studies often have little effect on clinical practice mainly due to the following reasons: (1) Most studies depend mainly on a single modality, especially neuroimaging; (2) diagnosis and progression detection are usually studied separately as two independent problems; and (3) current studies concentrate mainly on optimizing the performance of complex machine learning models, while disregarding their explainability. As a result, physicians struggle to interpret these models, and feel it is hard to trust them. In this paper, we carefully develop an accurate and interpretable AD diagnosis and progression detection model. This model provides physicians with accurate decisions along with a set of explanations for every decision. Specifically, the model integrates 11 modalities of 1048 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) real-world dataset: 294 cognitively normal, 254 stable mild cognitive impairment (MCI), 232 progressive MCI, and 268 AD. It is actually a two-layer model with random forest (RF) as classifier algorithm. In the first layer, the model carries out a multi-class classification for the early diagnosis of AD patients. In the second layer, the model applies binary classification to detect possible MCI-to-AD progression within three years from a baseline diagnosis. The performance of the model is optimized with key markers selected from a large set of biological and clinical measures. Regarding explainability, we provide, for each layer, global and instance-based explanations of the RF classifier by using the SHapley Additive exPlanations (SHAP) feature attribution framework. In addition, we implement 22 explainers based on decision trees and fuzzy rule-based systems to provide complementary justifications for every RF decision in each layer. Furthermore, these explanations are represented in natural language form to help physicians understand the predictions. The designed model achieves a cross-validation accuracy of 93.95% and an F1-score of 93.94% in the first layer, while it achieves a cross-validation accuracy of 87.08% and an F1-Score of 87.09% in the second layer. The resulting system is not only accurate, but also trustworthy, accountable, and medically applicable, thanks to the provided explanations which are broadly consistent with each other and with the AD medical literature. The proposed system can help to enhance the clinical understanding of AD diagnosis and progression processes by providing detailed insights into the effect of different modalities on the disease risk.

Download Full-text

Automatic Diagnosis of Alzheimer’s Disease Using Deep Learning Techniques

NeuroQuantology ◽

10.14704/nq.2021.19.11.nq21183 ◽

2021 ◽

Vol 19 (11) ◽

pp. 126-140

Author(s):

Zahraa S. Aaraji ◽

Hawraa H. Abbas

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Deep Learning ◽

Data Analysis ◽

Binary Classification ◽

Brain Mri ◽

Three Dimensional ◽

Structural Variations ◽

Automatic Feature Extraction ◽

Multi Class Classification

Neuroimaging data analysis has attracted a great deal of attention with respect to the accurate diagnosis of Alzheimer’s disease (AD). Magnetic Resonance Imaging (MRI) scanners have thus been commonly used to study AD-related brain structural variations, providing images that demonstrate both morphometric and anatomical changes in the human brain. Deep learning algorithms have already been effectively exploited in other medical image processing applications to identify features and recognise patterns for many diseases that affect the brain and other organs; this paper extends on this to describe a novel computer aided software pipeline for the classification and early diagnosis of AD. The proposed method uses two types of three-dimensional Convolutional Neural Networks (3D CNN) to facilitate brain MRI data analysis and automatic feature extraction and classification, so that pre-processing and post-processing are utilised to normalise the MRI data and facilitate pattern recognition. The experimental results show that the proposed approach achieves 97.5%, 82.5%, and 83.75% accuracy in terms of binary classification AD vs. cognitively normal (CN), CN vs. mild cognitive impairment (MCI) and MCI vs. AD, respectively, as well as 85% accuracy for multi class-classification, based on publicly available data sets from the Alzheimer’s disease Neuroimaging Initiative (ADNI).

Download Full-text

Alzheimer’s Disease Classification using Leung-Malik Filtered Bank Features and Weak Classifier

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.c4484.098319 ◽

2019 ◽

Vol 8 (3) ◽

pp. 1956-1961

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Filter Bank ◽

Binary Classification ◽

Brain Mri ◽

Texture Features ◽

Disease Classification ◽

Weak Classifier ◽

Frame Work ◽

Multi Class Classification

We propose a frame work to classify Brain MRI images in to Alzheimer’s Disease (AD), Cognitive Normal (CN) and Mild Cognitive impairments (MCI). We use 114No’s of T2 weighted MRI Volumes. We extracted relative texture features from Leung-Malik Filter bank, k means is used to generate Bag of Dictionary (BoD) from LM Filtered images. We performed binary classification and Multi class Classification using different Classifiers, Adaboost Classifier gives better performance both in binary and multi class classifications in comparison with other classifiers. Performance of proposed system is enhanced than compared to the existing techniques. It has Sensitivity for AD-CN 89.8, AD-MCI 78.82, AD-CN-MCI 77.77, Specificity for AD-CN79.22, AD-MCI 80.00, AD-CN-MCI 58.88, and positive prediction value for AD-CN 79.48, AD-MCI 83.75, AD-CN-MCI 68.47 and Accuracy AD-CN 84.24, AD-MCI 79.33, AD-CN-MCI 72.88.

Download Full-text