ADNI Dataset Research Articles

A hypergraph transformer method for brain disease diagnosis

ObjectiveTo address the high-order correlation modeling and fusion challenges between functional and structural brain networks.MethodThis paper proposes a hypergraph transformer method for modeling high-order correlations between functional and structural brain networks. By utilizing hypergraphs, we can effectively capture the high-order correlations within brain networks. The Transformer model provides robust feature extraction and integration capabilities that are capable of handling complex multimodal brain imaging.ResultsThe proposed method is evaluated on the ABIDE and ADNI datasets. It outperforms all the comparison methods, including traditional and graph-based methods, in diagnosing different types of brain diseases. The experimental results demonstrate its potential and application prospects in clinical practice.ConclusionThe proposed method provides new tools and insights for brain disease diagnosis, improving accuracy and aiding in understanding complex brain network relationships, thus laying a foundation for future brain science research.

Adaptive Weighted Multiview Kernel Matrix Factorization and Its Application in Alzheimer’s Disease Analysis

Recent technology and equipment advancements have provided us with opportunities to better analyze Alzheimer’s disease (AD), where we could collect and employ the data from different image and genetic modalities that may potentially enhance the predictive performance. To perform better clustering in AD analysis, in this paper, we propose a novel model to leverage data from all different modalities/views, which can learn the weights of each view adaptively. Different from previous vanilla Non-negative matrix factorization which assumes data is linearly separable, we propose a simple yet efficient method based on kernel matrix factorization, which is not only able to deal with non-linear data structure but also can achieve better prediction accuracy. Experimental results on the ADNI dataset demonstrate the effectiveness of our proposed method, which indicates promising prospects for kernel application in AD analysis.

UNVEILING THE DECISION MAKING PROCESS IN ALZHEIMER’S DISEASE DIAGNOSIS: A CASE-BASED COUNTERFACTUAL METHODOLOGY FOR EXPLAINABLE DEEP LEARNING

BackgroundThe field of Alzheimer's disease (AD) diagnosis is undergoing significant transformation due to the application of deep learning (DL) models. While DL surpasses traditional machine learning in disease prediction from structural magnetic resonance imaging (sMRI), the lack of explainability limits clinical adoption. Counterfactual inference offers a way to integrate causal explanations into these models, enhancing their robustness and transparency. New methodThis study develops a novel methodology combining U-Net and generative adversarial network (GAN) models to create comprehensive counterfactual diagnostic maps for AD. The proposed methodology uses case-based counterfactual reasoning for robust decision classification for counterfactual maps to understand how changes in specific features affect the model's predictions. Comparison with existing methodsThe proposed methodology is compared with state-of-the-art visual explanation techniques across the ADNI dataset. The proposed methodology is also benchmarked against other gradient-based and generative models for its ability to generate comprehensive counterfactual maps. ResultsThe results demonstrate that the proposed methodology significantly outperforms existing methods in accuracy, sensitivity, and specificity while providing detailed counterfactual maps that visualize how slight changes in brain morphology could lead to different diagnostic outcomes. The proposed methodology achieves an accuracy of 95% and an AUC of 0.97, illustrating its superiority in capturing subtle yet crucial anatomical features. ConclusionsBy generating intuitive visual explanations, the proposed methodology improves the interpretability and robustness of AD diagnostic models, making them more reliable and accountable. The use of counterfactual inference enhances clinicians' understanding of disease progression and the impact of different interventions, fostering precision medicine in AD care.

BrainSim: AI-Driven Brain MRI Simulation for Alzheimer’s Disease Diagnosis

Alzheimer's Disease, a progressive neurodegenerative disorder with no cure, presents a formidable challenge to global healthcare. The simulation of brain states, encompassing both rejuvenation and aging, aids clinicians in understanding disease progression and early detection. Recent advances in deep adversarial neural networks, effective in generating age-varied facial images, are now applied to brain MRI simulations across different time states. However, existing methods for brain MRI synthesis predominantly focus on aging simulation, lacking rejuvenation capabilities, and relying heavily on longitudinal data. Access to rejuvenated brain scans is essential as it can help researchers track the structural changes and biomarkers in the early stage of AD, facilitating AD research and personalized treatments. Additionally, previous methods are often 2D-based, failing to capture complex 3D spatial information obtained by 3D scans. To overcome these limitations, I propose BrainSim, a novel longitudinal brain MRI synthesis framework. Specifically, BrainSim leverages a bidirectional cycle-consistent generative neural network to generate rejuvenated and aged MRI scans simultaneously using cross-sectional scans only. BrainSim incorporates a 3D conditional U-Net as its fundamental model, facilitating the direct generation of 3D MRI scans conditioned on the subject's health state and sex. BrainSim was evaluated against benchmark models using longitudinal data and a pre-trained age predictor to assess the quality of generated images. Experiments using the ADNI dataset show BrainSim's state-of-the-art performance in brain aging and rejuvenation tasks, marking significant advancements in MRI synthesis for Alzheimer's research and drug development.

Ensemble of vision transformer architectures for efficient Alzheimer’s Disease classification

Transformers have dominated the landscape of Natural Language Processing (NLP) and revolutionalized generative AI applications. Vision Transformers (VT) have recently become a new state-of-the-art for computer vision applications. Motivated by the success of VTs in capturing short and long-range dependencies and their ability to handle class imbalance, this paper proposes an ensemble framework of VTs for the efficient classification of Alzheimer’s Disease (AD). The framework consists of four vanilla VTs, and ensembles formed using hard and soft-voting approaches. The proposed model was tested using two popular AD datasets: OASIS and ADNI. The ADNI dataset was employed to assess the models’ efficacy under imbalanced and data-scarce conditions. The ensemble of VT saw an improvement of around 2% compared to individual models. Furthermore, the results are compared with state-of-the-art and custom-built Convolutional Neural Network (CNN) architectures and Machine Learning (ML) models under varying data conditions. The experimental results demonstrated an overall performance gain of 4.14% and 4.72% accuracy over the ML and CNN algorithms, respectively. The study has also identified specific limitations and proposes avenues for future research. The codes used in the study are made publicly available.

Fractional gradient optimized explainable convolutional neural network for Alzheimer's disease diagnosis

Alzheimer's is one of the brain syndromes that steadily affects the brain memory. The early stage of Alzheimer's disease (AD) is referred to as mild cognitive impairment (MCI), and the growth of Alzheimer's is not certain in patients with MCI. The premature detection of Alzheimer's is crucial for maintaining healthy brain function and avoiding memory loss. Different multi-neural network architectures have been proposed by researchers for efficient and accurate AD detection. The absence of improved feature extraction mechanisms and unexplored efficient optimizers in complex benchmark architectures lead to an inefficient and inaccurate AD classification. Moreover, the standard convolutional neural network (CNN)-based architectures for Alzheimer's diagnosis lack interpretability in their predictions. An interpretable, simplified, yet effective deep learning model is required for the accurate classification of AD. In this study, a generalized fractional order-based CNN classifier with explainable artificial intelligence (XAI) capabilities is proposed for accurate, efficient, and interpretable classification of AD diagnosis. The proposed study (a) classifies AD accurately by incorporating unexplored pooling technique with enhanced feature extraction mechanism, (b) provides fractional order-based optimization approach for adaptive learning and fast convergence speed, and (c) suggests an interpretable method for proving the transparency of the model. The proposed model outperforms complex benchmark architectures with regard to accuracy using standard ADNI dataset. The proposed fractional order-based CNN classifier achieves an improved accuracy of 99 % as compared to the state-of-the-art models.

Local molecular and connectomic contributions of tau-related neurodegeneration.

Neurodegeneration in Alzheimer's disease (AD) is known to be mostly driven by tau neurofibrillary tangles. However, both tau and neurodegeneration exhibit variability in their distribution across the brain and among individuals, and the relationship between tau and neurodegeneration might be influenced by several factors. I aimed to map local molecular and connectivity characteristics that affect the association between tau pathology and neurodegeneration. The current study was conducted on the cross-sectional tau-PET and longitudinal T1-weighted MRI scan data of 186 participants from the ADNI dataset including 71 cognitively unimpaired (CU) and 115 mild cognitive impairment (MCI) individuals. Furthermore, the normative molecular profile of a region was defined using neurotransmitter receptor densities, gene expression, T1w/T2w ratio (myelination), FDG-PET (glycolytic index, glucose metabolism, and oxygen metabolism), and synaptic density. I found that the excitatory-inhibitory (E:I) ratio, myelination, synaptic density, glycolytic index, and functional connectivity are linked with deviation in the relationship between tau and neurodegeneration. Furthermore, there was spatial similarity between tau pathology and glycolytic index, synaptic density, and functional connectivity across brain regions. The current study demonstrates that the regional susceptibility to tau-related neurodegeneration is associated with specific molecular and connectomic characteristics of the affected neural systems. I found that the molecular and connectivity architecture of the human brain is linked to the different effects of tau pathology on downstream neurodegeneration.

CvFormer: Cross-view transFormers with pre-training for fMRI analysis of human brain

In recent years, functional magnetic resonance imaging (fMRI) has been widely utilized to diagnose neurological disease, by exploiting the region of interest (RoI) nodes as well as their connectivities in human brain. However, most of existing works only rely on either RoIs or connectivities, neglecting the potential for complementary information between them. To address this issue, we study how to discover the rich cross-view information in fMRI data of human brain. This paper presents a novel method for cross-view analysis of fMRI data of the human brain, called Cross-view transFormers (CvFormer). CvFormer employs RoI and connectivity encoder modules to generate two separate views of the human brain, represented as RoI and sub-connectivity tokens. Then, basic transformer modules can be used to process the RoI and sub-connectivity tokens, and cross-view modules integrate the complement information across two views. Furthermore, CvFormer uses a global token for each branch as a query to exchange information with other branches in cross-view modules, which only requires linear time for both computational and memory complexity instead of quadratic time. To enhance the robustness of the proposed CvFormer, we propose a two-stage strategy to train its parameters. To be specific, RoI and connectivity views can be firstly utilized as self-supervised information to pre-train the CvFormer by combining it with contrastive learning and then fused to finetune the CvFormer using label information. Experiment results on two public ABIDE and ADNI datasets can show clear improvements by the proposed CvFormer, which can validate its effectiveness and superiority.

Automated medical diagnosis of dementia through fine-tuned EfficientNet

Automated models using deep learning are more extensively used in medical imaging in the last decade. The present study contributes to the diagnosis of dementia using MRI. Dementia is a syndrome that deteriorates the cognitive function of the brain. The disease has no cure, till now, except for the prior diagnosis. The present study aims for classifying the MRI scans of two datasets OASIS and ADNI into 2 categories: binary and multi-classification. To achieve the objective, the EfficientNetB0 architecture of deep learning is fine-tuned by adding three dense layers on the top of the network. The swish activation function is used in the inner dense layers added. The dropout and batch normalization layers are also added for dealing with the problem of overfitting. This architecture offers high accuracy and high efficiency compared to other pre-trained networks. The model is assessed on various performance measures and outperformed the state of art techniques. For the OASIS dataset, the best testing accuracy for binary classification is 93.10% with a 0.01 learning rate. The sensitivity is 95.93%, specificity is 90.08%, false-negative rate is 4.07, the false-positive rate is 9.92 and the F1-score is 93.48%. The best testing accuracy of multi-classification is 84.50% with a 0.001 learning rate. For the ADNI dataset, the best testing accuracy is 96.08% with a learning rate of 0.001. The sensitivity is 94.74%, specificity is 99.32%, false-negative rate is 5.26, the false-positive rate is 0.68 and the f1-score is 97.16%. The best testing accuracy of multi-classification is 98.10 with a 0.01 learning rate. The proposed model can be utilized for developing an automated framework to help medical services to improve decision-making.

Sex-Specific Effects of Anxiety on Cognition and Activity-Dependent Neural Networks: Insights from (Female) Mice and (Wo)Men

Neuropsychiatric symptoms (NPS), such as depression and anxiety, are observed in 90% of Alzheimer's disease (AD) patients, two-thirds of whom are women. NPS usually manifest long before AD onset creating a therapeutic opportunity. Here, we examined the impact of anxiety on AD progression and the underlying brain-wide neuronal mechanisms. To gain mechanistic insight into how anxiety impacts AD progression, we performed a cross-sectional analysis on mood, cognition, and neural activity utilizing the ArcCreERT2 x enhanced yellow fluorescent protein (eYFP) x APP/PS1 (AD) mice. The ADNI dataset was used to determine the impact of anxiety on AD progression in human subjects. Female APP/PS1 mice exhibited anxiety-like behavior and cognitive decline at an earlier age than control (Ctrl) mice and male mice. Brain-wide analysis of c-Fos+ revealed changes in regional correlations and overall network connectivity in APP/PS1 mice. Sex-specific eYFP+/c-Fos+ changes were observed; female APP/PS1 mice exhibited less eYFP+/c-Fos+ cells in dorsal CA3 (dCA3), while male APP/PS1 mice exhibited less eYFP+/c-Fos+ cells in the dorsal dentate gyrus (dDG). In the ADNI dataset, anxiety predicted transition to dementia. Female subjects positive for anxiety and amyloid transitioned more quickly to dementia than male subjects. While future studies are needed to understand whether anxiety is a predictor, a neuropsychiatric biomarker, or a comorbid symptom that occurs during disease onset, these results suggest that there are sex differences in AD network dysfunction, and that personalized medicine may benefit male and female AD patients rather than a one size fits all approach.

MHNFSP: Design of an Efficient Model for Advanced MRI Image Classification Using Hybrid Neural Networks and Optimized Feature Selection Process

In the field of medical imaging, particularly regarding magnetic resonance imaging (MRI) and the analysis of feature extraction in the MRI, there exists an immediate and pressing need for precision and clarity in the accuracy of such. Current methods, though useful, have inherent weaknesses with respect to dealing with noise, specific feature identification, and an ability to effectively merge different types of data. The explained developments show the need of innovation in MRI image classification, especially for distinguishing slight but critical variations in brain images and samples. These gaps underline the urgency for innovation in MRI image classification, especially for differentiating delicate nuances of brain images and samples. The proposed model has addressed these gaps through an innovative workflow for MRI image classification, identified by a novel, synergistic approach process. The workflow begins with the scrupulous acquisition of MRI and fMRI images, capturing the intricate structural and functional nuances of the brain. Image segmentation is employed for innovative execution using Fuzzy C-Means (FCM), picked for its excellent noise resistance and the advantage of soft clustering that is important for a more exact definition of the boundaries of the regions of interest in the image set. The feature extraction phase involves three phases with Fourier, Entropy, and Convolution features from an elevated perspective. This trio is very carefully picked to encapsulate a comprehensive image representation, harmonizing the shape, texture, and local structure. The workflow of this model is streamlined from the feature set with the employment of Whale Optimization, which quite efficaciously sieves the feature set, retaining the most informative while curtailing redundancy and overfitting issues within the process. Eventually, a Hybrid Convolutional Neural Network (CNN) emerges at the top of this model, incorporating Naive Bayes, k-Nearest Neighbors (kNN), Support Vector Machine (SVM), Logistic Regression (LR), and Multi-Layer Perceptron (MLP) methods. This selective multi-classifier classification provides a robust and heterogeneous set of functions for the classification. Tested on different OASIS and ADNI datasets and samples, this model has outperformed current methods with a 4.9% increase in precision, a 4.5% enhancement in accuracy, a 3.5% rise in recall, a 4.3% augmentation in AUC (Area Under the Curve), a 3.4% improvement in specificity, and a 2.9% cutdown in delay. Such advancements not only signify a great leap in MRI image classification but also carry very much significance for medical diagnosis and research, and that could see its way into the clinical field. In this model, the amalgamation of disparate methods sets a new benchmark in medical imaging, opening doors to better accuracy, higher efficiency, and greater reliability of diagnostic tools.

Transparent Insights into Alzheimer’s Progression: A Time-Aware Approach with Explainable AI

Alzheimer’s disease, acknowledged for its intricate and degenerative characteristics, presents considerable challenges, particularly among the elderly population. The relentless nature of Alzheimer’s, marked by the gradual deterioration of cognitive function, underscores the urgency to develop effective strategies for early diagnosis and intervention. Artificial intelligence has played a significant role in terms of disease diagnosis and treatments. However, it has got limited acceptance in the medical community due to its lack of transparency. This study aims to advance the understanding and prediction of Alzheimer’s disease progression through the integration of time-aware modeling and Explainable AI techniques. It makes significant contributions by addressing two key objectives in the context of Alzheimer’s disease. First, by including temporal aspects, it accurately depicts the pace at which relevant predictors change over time, thereby capturing the dynamic nature of Alzheimer’s disease. Second, by giving interpretable insights into the algorithm’s decision-making process, the study hopes to empower researchers and physicians. This approach not only enhances transparency but also builds trust in the model’s outcomes. The ADNI dataset, comprising 2980 observations, was employed for developing a prediction model using various machine learning classifiers. Among these classifiers, the Random Forest model emerged as the top performer, exhibiting superior accuracy, a high Coefficient of Determination (R2), and an impressive F1 score. To enhance interpretability, subsequent analyses utilized LIME and SHAP techniques. By combining time-aware modeling with Explainable AI methods, we seek to unravel the dynamic relationships within the dataset, providing transparent insights into the temporal evolution of Alzheimer’s disease. Thus, this paper contributes to the creation of a clinically relevant and practical model for monitoring Alzheimer’s disease progression that holds the potential for a deeper understanding of the evolving nature of the disease and paving the way for personalized and timely interventions.

A sparse transformer generation network for brain imaging genetic association

Brain imaging and genetic data are commonly utilized to investigate brain aging and diseases, particularly Alzheimer’s Disease (AD). Imaging genetics analyze the associations between neuroimaging and genetic data to reveal potential pathological mechanisms for more accurate diagnosis. Many existing methods have limitations in performing fine-grained association analysis between genetic data and phenotypic features extracted from predefined regions of interest in imaging data. To address this issue, this paper proposes a sparse transformer association analysis (STAA) framework that integrates phenotype and genotype feature extraction, identification, and association analysis into a unified model. A key component of the framework is a cross-modal generation network that connects genetic variants with imaging data, enhancing the understanding of the genetic associations underlying imaging patterns in AD and brain aging. Validated using the simulated data and real ADNI dataset, STAA shows superior performance in age regression and AD diagnosis, identifying key genetic and imaging biomarkers and providing association analysis of genetic imaging expression patterns at the voxel level.

Joint diffusion: mutual consistency-driven diffusion model for PET-MRI co-reconstruction

Objective. Positron Emission Tomography and Magnetic Resonance Imaging (PET-MRI) systems can obtain functional and anatomical scans. But PET suffers from a low signal-to-noise ratio, while MRI are time-consuming. To address time-consuming, an effective strategy involves reducing k-space data collection, albeit at the cost of lowering image quality. This study aims to leverage the inherent complementarity within PET-MRI data to enhance the image quality of PET-MRI. Approach. A novel PET-MRI joint reconstruction model, termed MC-Diffusion, is proposed in the Bayesian framework. The joint reconstruction problem is transformed into a joint regularization problem, where data fidelity terms of PET and MRI are expressed independently. The regular term, the derivative of the logarithm of the joint probability distribution of PET and MRI, employs a joint score-based diffusion model for learning. The diffusion model involves the forward diffusion process and the reverse diffusion process. The forward diffusion process adds noise to transform a complex joint data distribution into a known joint prior distribution for PET and MRI simultaneously, resembling a denoiser. The reverse diffusion process removes noise using a denoiser to revert the joint prior distribution to the original joint data distribution, effectively utilizing joint probability distribution to describe the correlations of PET and MRI for improved quality of joint reconstruction. Main results. Qualitative and quantitative improvements are observed with the MC-Diffusion model. Comparative analysis against LPLS and Joint ISAT-net on the ADNI dataset demonstrates superior performance by exploiting complementary information between PET and MRI. The MC-Diffusion model effectively enhances the quality of PET and MRI images. Significance. This study employs the MC-Diffusion model to enhance the quality of PET-MRI images by integrating the fundamental principles of PET and MRI modalities and leveraging their inherent complementarity. Furthermore, utilizing the diffusion model to learn the joint probability distribution of PET and MRI, thereby elucidating their latent correlation, facilitates a more profound comprehension of the priors obtained through deep learning, contrasting with black-box prior or artificially constructed structural similarities.

Borderline-DEMNET: A Workflow for Detecting Alzheimer’s and Dementia Stage by Solving Class Imbalance Problem

Alzheimer’s Disease (AD) is the leading cause of dementia, a broad term encompassing memory loss and other cognitive impairments. Although there is no known cure for dementia, managing specific symptoms associated with it can be effective. Mild dementia stages, including AD, can be treated, and computer-based techniques have been developed to aid in early diagnosis. This paper presents a new workflow called Borderline-DEMNET, designed to classify various stages of Alzheimer’s/dementia with more than three classes. Borderline-SMOTE is employed to address the issue of imbalanced datasets. A comparison is made between the proposed Borderline-DEMNET workflow and the existing DEMNET model, which focuses on classifying different dementia and AD stages. The evaluation metrics specified in the paper are used to assess the results. The framework is trained, tested, and validated using the Kaggle dataset, while the robustness of the work is checked using the ADNI dataset. The proposed workflow achieves an accuracy of 99.17% for the Kaggle dataset and 99.14% for the ADNI dataset. In conclusion, the proposed workflow outperforms previously identified models, particularly in terms of accuracy. It also proves that selecting a proper class balancing technique will increase accuracy.

Borderline-DEMNET: A Workflow for Detecting Alzheimer’s and Dementia Stage by Solving Class Imbalance Problem

Alzheimer’s Disease (AD) is the leading cause of dementia, a broad term encompassing memory loss and other cognitive impairments. Although there is no known cure for dementia, managing specific symptoms associated with it can be effective. Mild dementia stages, including AD, can be treated, and computer-based techniques have been developed to aid in early diagnosis. This paper presents a new workflow called Borderline-DEMNET, designed to classify various stages of Alzheimer’s/dementia with more than three classes. Borderline-SMOTE is employed to address the issue of imbalanced datasets. A comparison is made between the proposed Borderline-DEMNET workflow and the existing DEMNET model, which focuses on classifying different dementia and AD stages. The evaluation metrics specified in the paper are used to assess the results. The framework is trained, tested, and validated using the Kaggle dataset, while the robustness of the work is checked using the ADNI dataset. The proposed workflow achieves an accuracy of 99.17% for the Kaggle dataset and 99.14% for the ADNI dataset. In conclusion, the proposed workflow outperforms previously identified models, particularly in terms of accuracy. It also proves that selecting a proper class balancing technique will increase accuracy.

Ensemble approach of transfer learning and vision transformer leveraging explainable AI for disease diagnosis: An advancement towards smart healthcare 5.0

Smart healthcare has advanced the medical industry with the integration of data-driven approaches. Artificial intelligence and machine learning provided remarkable progress, but there is a lack of transparency and interpretability in such applications. To overcome such limitations, explainable AI (EXAI) provided a promising result. This paper applied the EXAI for disease diagnosis in the advancement of smart healthcare. The paper combined the approach of transfer learning, vision transformer, and explainable AI and designed an ensemble approach for prediction of disease and its severity. The result is evaluated on a dataset of Alzheimer's disease. The result analysis compared the performance of transfer learning models with the ensemble model of transfer learning and vision transformer. For training, InceptionV3, VGG19, Resnet50, and Densenet121 transfer learning models were selected for ensembling with vision transformer. The result compares the performance of two models: a transfer learning (TL) model and an ensemble transfer learning (Ensemble TL) model combined with vision transformer (ViT) on ADNI dataset. For the TL model, the accuracy is 58 %, precision is 52 %, recall is 42 %, and the F1-score is 44 %. Whereas, the Ensemble TL model with ViT shows significantly improved performance i.e., 96 % of accuracy, 94 % of precision, 90 % of recall and 92 % of F1-score on ADNI dataset. This shows the efficacy of the ensemble model over transfer learning models.

Achieving multi-modal brain disease diagnosis performance using only single-modal images through generative AI

Brain disease diagnosis using multiple imaging modalities has shown superior performance compared to using single modality, yet multi-modal data is not easily available in clinical routine due to cost or radiation risk. Here we propose a synthesis-empowered uncertainty-aware classification framework for brain disease diagnosis. To synthesize disease-relevant features effectively, a two-stage framework is proposed including multi-modal feature representation learning and representation transfer based on hierarchical similarity matching. Besides, the synthesized and acquired modality features are integrated based on evidential learning, which provides diagnosis decision and also diagnosis uncertainty. Our framework is extensively evaluated on five datasets containing 3758 subjects for three brain diseases including Alzheimer’s disease (AD), subcortical vascular mild cognitive impairment (MCI), and O[6]-methylguanine-DNA methyltransferase promoter methylation status for glioblastoma, achieving 0.950 and 0.806 in area under the ROC curve on ADNI dataset for discriminating AD patients from normal controls and progressive MCI from static MCI, respectively. Our framework not only achieves quasi-multimodal performance although using single-modal input, but also provides reliable diagnosis uncertainty.

Contrastive Self-supervised Learning for Neurodegenerative Disorder Classification.

Neurodegenerative diseases such as Alzheimer's disease (AD) or frontotemporal lobar degeneration (FTLD) involve specific loss of brain volume, detectable in vivo using T1-weighted MRI scans. Supervised machine learning approaches classifying neurodegenerative diseases require diagnostic-labels for each sample. However, it can be difficult to obtain expert labels for a large amount of data. Self-supervised learning (SSL) offers an alternative for training machine learning models without data-labels. We investigated if the SSL models can applied to distinguish between different neurodegenerative disorders in an interpretable manner. Our method comprises a feature extractor and a downstream classification head. A deep convolutional neural network trained in a contrastive self-supervised way serves as the feature extractor, learning latent representation, while the classifier head is a single-layer perceptron. We used N=2694 T1-weighted MRI scans from four data cohorts: two ADNI datasets, AIBL and FTLDNI, including cognitively normal controls (CN), cases with prodromal and clinical AD, as well as FTLD cases differentiated into its sub-types. Our results showed that the feature extractor trained in a self-supervised way provides generalizable and robust representations for the downstream classification. For AD vs. CN, our model achieves 82% balanced accuracy on the test subset and 80% on an independent holdout dataset. Similarly, the Behavioral variant of frontotemporal dementia (BV) vs. CN model attains an 88% balanced accuracy on the test subset. The average feature attribution heatmaps obtained by the Integrated Gradient method highlighted hallmark regions, i.e., temporal gray matter atrophy for AD, and insular atrophy for BV. In conclusion, our models perform comparably to state-of-the-art supervised deep learning approaches. This suggests that the SSL methodology can successfully make use of unannotated neuroimaging datasets as training data while remaining robust and interpretable.

Enhancing Feature Selection in MCI Diagnosis using FDG-PET Images: Leveraging Multiple Simple Autoencoder Architectures

Alzheimer’s Disease (AD) is the most common type of neurodegenerative brain disease in elderly people. Early diagnosis of AD is crucial for providing suitable care. Positron Emission Tomography (PET) images and machine learning can be used to support this purpose. In this paper, we present a method for ranking the effectiveness of brain regions of interest (ROIs) to distinguish between stable mild cognitive impairment (sMCI) from progressive mild cognitive impairment (pMCI) in brain PET images based on AutoEncoder (AE). Experiments on the ADNI dataset show that our proposed method significantly improves classifier performance when compared to other popular feature ranking methods such as Fisher score, t-score, and LASSO. Our results suggest that instead of focusing on designing a complex AE structure, we can also use simple-but-multiple AEs for feature ranking. The proposed method could be easily applied to any image dataset where a feature selection is needed.