Multi-Domain Transfer Learning for Early Diagnosis of Alzheimer's Disease

Predicting conversion from mild cognitive impairment to Alzheimer's disease: a multimodal approach

Successively predicting whether mild cognitive impairment patients will progress to Alzheimer's disease is of significant clinical relevance. This ability may provide information that can be leveraged by emerging intervention approaches and thus mitigate some of the negative effects of the disease. Neuroimaging biomarkers have gained some attention in recent years and may be useful in predicting the conversion of mild cognitive impairment to Alzheimer's disease. We implemented a novel multi-modal approach that allowed us to evaluate the potential of different imaging modalities, both alone and in different degrees of combinations, in predicting the conversion to Alzheimer's disease of mild cognitive impairment patients. We applied this approach to the imaging data from the Alzheimer's Disease Neuroimaging Initiative that is a multi-modal imaging dataset comprised of MRI, Fluorodeoxyglucose PET, Florbetapir PET and diffusion tensor imaging. We included a total of 480 mild cognitive impairment patients that were split into two groups: converted and stable. Imaging data were segmented into atlas-based regions of interest, from which relevant features were extracted for the different imaging modalities and used to construct machine-learning models to classify mild cognitive impairment patients into converted or stable, using each of the different imaging modalities independently. The models were then combined, using a simple weight fusion ensemble strategy, to evaluate the complementarity of different imaging modalities and their contribution to the prediction accuracy of the models. The single-modality findings revealed that the model, utilizing features extracted from Florbetapir PET, demonstrated the highest performance with a balanced accuracy of 83.51%. Concerning multi-modality models, not all combinations enhanced mild cognitive impairment conversion prediction. Notably, the combination of MRI with Fluorodeoxyglucose PET emerged as the most promising, exhibiting an overall improvement in predictive capabilities, achieving a balanced accuracy of 78.43%. This indicates synergy and complementarity between the two imaging modalities in predicting mild cognitive impairment conversion. These findings suggest that β-amyloid accumulation provides robust predictive capabilities, while the combination of multiple imaging modalities has the potential to surpass certain single-modality approaches. Exploring modality-specific biomarkers, we identified the brainstem as a sensitive biomarker for both MRI and Fluorodeoxyglucose PET modalities, implicating its involvement in early Alzheimer's pathology. Notably, the corpus callosum and adjacent cortical regions emerged as potential biomarkers, warranting further study into their role in the early stages of Alzheimer's disease.

Advancements in computer-assisted diagnosis of Alzheimer's disease: A comprehensive survey of neuroimaging methods and AI techniques for early detection

Alzheimer's Disease (AD) is a brain disorder that causes the brain to shrink and eventually causes brain cells to die. This neurological condition progressively hampers cognitive and memory functions, along with the ability to carry out fundamental tasks over time. From the symptoms it is very difficult to detect during its early stage. It has become necessary to develop a computer assisted diagnostic models for the early AD detection. This survey work, discussed about a review of 110 published AD detection methods and techniques from the year 2011 to till-date. This study lies in its comprehensive exploration of AD detection methods using a range of artificial intelligence (AI) techniques and neuroimaging modalities. By collecting and analysing 50 papers related to AD diagnosis datasets, the study provides a comprehensive understanding of the diversity of input types, subjects, and classes used in AD research. Summarizing 60 papers on methodologies gives researchers a succinct overview of various approaches that contribute to enhancing detection accuracy. From the review, data are acquired and pre-processed form multiple modalities of neuroimaging. This paper mainly focused on review of different datasets used, various feature extraction methods, parameters used in neuro images. To diagnosis the Alzheimer's disease, the existing methods utilized three most common artificial intelligence techniques such as machine learning, deep learning, and transfer learning. We conclude this survey work by providing future perspectives for AD diagnosis at early stage.

A transfer learning approach for multiclass classification of Alzheimer's disease using MRI images

Alzheimer's is an acute degenerative disease affecting the elderly population all over the world. The detection of disease at an early stage in the absence of a large-scale annotated dataset is crucial to the clinical treatment for the prevention and early detection of Alzheimer's disease (AD). In this study, we propose a transfer learning base approach to classify various stages of AD. The proposed model can distinguish between normal control (NC), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI), and AD. In this regard, we apply tissue segmentation to extract the gray matter from the MRI scans obtained from the Alzheimer's Disease National Initiative (ADNI) database. We utilize this gray matter to tune the pre-trained VGG architecture while freezing the features of the ImageNet database. It is achieved through the addition of a layer with step-wise freezing of the existing blocks in the network. It not only assists transfer learning but also contributes to learning new features efficiently. Extensive experiments are conducted and results demonstrate the superiority of the proposed approach.

Machine learning for autism spectrum disorder diagnosis using structural magnetic resonance imaging: Promising but challenging

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects approximately 1% of the population and causes significant burdens. ASD's pathogenesis remains elusive; hence, diagnosis is based on a constellation of behaviors. Structural magnetic resonance imaging (sMRI) studies have shown several abnormalities in volumetric and geometric features of the autistic brain. However, inconsistent findings prevented most contributions from being translated into clinical practice. Establishing reliable biomarkers for ASD using sMRI is crucial for the correct diagnosis and treatment. In recent years, machine learning (ML) and specifically deep learning (DL) have quickly extended to almost every sector, notably in disease diagnosis. Thus, this has led to a shift and improvement in ASD diagnostic methods, fulfilling most clinical diagnostic requirements. However, ASD discovery remains difficult. This review examines the ML-based ASD diagnosis literature over the past 5 years. A literature-based taxonomy of the research landscape has been mapped, and the major aspects of this topic have been covered. First, we provide an overview of ML's general classification pipeline and the features of sMRI. Next, representative studies are highlighted and discussed in detail with respect to methods, and biomarkers. Finally, we highlight many common challenges and make recommendations for future directions. In short, the limited sample size was the main obstacle; Thus, comprehensive data sets and rigorous methods are necessary to check the generalizability of the results. ML technologies are expected to advance significantly in the coming years, contributing to the diagnosis of ASD and helping clinicians soon.

Doubly Supervised Transfer Classifier for Computer-Aided Diagnosis With Imbalanced Modalities

Transfer learning (TL) can effectively improve diagnosis accuracy of single-modal-imaging-based computer-aided diagnosis (CAD) by transferring knowledge from other related imaging modalities, which offers a way to alleviate the small-sample-size problem. However, medical imaging data generally have the following characteristics for the TL-based CAD: 1) The source domain generally has limited data, which increases the difficulty to explore transferable information for the target domain; 2) Samples in both domains often have been labeled for training the CAD model, but the existing TL methods cannot make full use of label information to improve knowledge transfer. In this work, we propose a novel doubly supervised transfer classifier (DSTC) algorithm. In particular, DSTC integrates the support vector machine plus (SVM+) classifier and the low-rank representation (LRR) into a unified framework. The former makes full use of the shared labels to guide the knowledge transfer between the paired data, while the latter adopts the block-diagonal low-rank (BLR) to perform supervised TL between the unpaired data. Furthermore, we introduce the Schatten-p norm for BLR to obtain a tighter approximation to the rank function. The proposed DSTC algorithm is evaluated on the Alzheimer's disease neuroimaging initiative (ADNI) dataset and the bimodal breast ultrasound image (BBUI) dataset. The experimental results verify the effectiveness of the proposed DSTC algorithm.

Cross-Modal Transfer Learning Methods for Alzheimer's Disease Diagnosis

In this paper we propose cross-modal transfer learning for Alzheimer's disease detection. We use positron emission tomography (PET) and magnetic resonance imaging (MRI) brain scans from ADNI to train convolutional neural networks (CNNs) on one modality and fine-tune it on the other modality. We start by showing that cross-modal transfer learning approaches outperform CNNs trained from scratch on a single modality. We then show that cross-modal transfer-learning also outperforms multimodal approaches using the same data.

Domain Adaptation for Medical Image Analysis: A Survey

Machine learning techniques used in computer-aided medical image analysis usually suffer from the domain shift problem caused by different distributions between source/reference data and target data. As a promising solution, domain adaptation has attracted considerable attention in recent years. The aim of this paper is to survey the recent advances of domain adaptation methods in medical image analysis. We first present the motivation of introducing domain adaptation techniques to tackle domain heterogeneity issues for medical image analysis. Then we provide a review of recent domain adaptation models in various medical image analysis tasks. We categorize the existing methods into shallow and deep models, and each of them is further divided into supervised, semi-supervised and unsupervised methods. We also provide a brief summary of the benchmark medical image datasets that support current domain adaptation research. This survey will enable researchers to gain a better understanding of the current status, challenges and future directions of this energetic research field.

A systematic analysis of diagnostic performance for Alzheimer's disease using structural MRI

Background

Alzheimer's disease (AD) is one of the most common neurodegenerative disorders in the elderly. Although numerous structural magnetic resonance imaging (sMRI) studies have reported diagnostic models that could distinguish AD from normal controls (NCs) with 80-95% accuracy, limited efforts have been made regarding the clinically practical computer-aided diagnosis (CAD) system for AD.

Objective

To explore the potential factors that hinder the clinical translation of the AD-related diagnostic models based on sMRI.

Methods

To systematically review the diagnostic models for AD based on sMRI, we identified relevant studies published in the past 15 years on PubMed, Web of Science, Scopus, and Ovid. To evaluate the heterogeneity and publication bias among those studies, we performed subgroup analysis, meta-regression, Begg's test, and Egger's test.

Results

According to our screening criterion, 101 studies were included. Our results demonstrated that high diagnostic accuracy for distinguishing AD from NC was obtained in recently published studies, accompanied by significant heterogeneity. Meta-analysis showed that many factors contributed to the heterogeneity of high diagnostic accuracy of AD using sMRI, which included but was not limited to the following aspects: (i) different datasets; (ii) different machine learning models, e.g. traditional machine learning or deep learning model; (iii) different cross-validation methods, e.g. k-fold cross-validation leads to higher accuracies than leave-one-out cross-validation, but both overestimate the accuracy when compared to validation in independent samples; (iv) different sample sizes; and (v) the publication times. We speculate that these complicated variables might be the adverse factor for developing a clinically applicable system for the early diagnosis of AD.

Conclusions

Our findings proved that previous studies reported promising results for classifying AD from NC with different models using sMRI. However, considering the many factors hindering clinical radiology practice, there would still be a long way to go to improve.

Transfer Learning Approaches for Neuroimaging Analysis: A Scoping Review

Deep learning algorithms have been moderately successful in diagnoses of diseases by analyzing medical images especially through neuroimaging that is rich in annotated data. Transfer learning methods have demonstrated strong performance in tackling annotated data. It utilizes and transfers knowledge learned from a source domain to target domain even when the dataset is small. There are multiple approaches to transfer learning that result in a range of performance estimates in diagnosis, detection, and classification of clinical problems. Therefore, in this paper, we reviewed transfer learning approaches, their design attributes, and their applications to neuroimaging problems. We reviewed two main literature databases and included the most relevant studies using predefined inclusion criteria. Among 50 reviewed studies, more than half of them are on transfer learning for Alzheimer's disease. Brain mapping and brain tumor detection were second and third most discussed research problems, respectively. The most common source dataset for transfer learning was ImageNet, which is not a neuroimaging dataset. This suggests that the majority of studies preferred pre-trained models instead of training their own model on a neuroimaging dataset. Although, about one third of studies designed their own architecture, most studies used existing Convolutional Neural Network architectures. Magnetic Resonance Imaging was the most common imaging modality. In almost all studies, transfer learning contributed to better performance in diagnosis, classification, segmentation of different neuroimaging diseases and problems, than methods without transfer learning. Among different transfer learning approaches, fine-tuning all convolutional and fully-connected layers approach and freezing convolutional layers and fine-tuning fully-connected layers approach demonstrated superior performance in terms of accuracy. These recent transfer learning approaches not only show great performance but also require less computational resources and time.

Aortic Dissection Auxiliary Diagnosis Model and Applied Research Based on Ensemble Learning

Aortic dissection (AD), a dangerous disease threatening to human beings, has a hidden onset and rapid progression and has few effective methods in its early diagnosis. At present, although CT angiography acts as the gold standard on AD diagnosis, it is so expensive and time-consuming that it can hardly offer practical help to patients. Meanwhile, the artificial intelligence technology may provide a cheap but effective approach to building an auxiliary diagnosis model for improving the early AD diagnosis rate by taking advantage of the data of the general conditions of AD patients, such as the data about the basic inspection information. Therefore, this study proposes to hybrid five types of machine learning operators into an integrated diagnosis model, as an auxiliary diagnostic approach, to cooperate with the AD-clinical analysis. To improve the diagnose accuracy, the participating rate of each operator in the proposed model may adjust adaptively according to the result of the data learning. After a set of experimental evaluations, the proposed model, acting as the preliminary AD-discriminant, has reached an accuracy of over 80%, which provides a promising instance for medical colleagues.

Assessing clinical progression from subjective cognitive decline to mild cognitive impairment with incomplete multi-modal neuroimages

Accurately assessing clinical progression from subjective cognitive decline (SCD) to mild cognitive impairment (MCI) is crucial for early intervention of pathological cognitive decline. Multi-modal neuroimaging data such as T1-weighted magnetic resonance imaging (MRI) and positron emission tomography (PET), help provide objective and supplementary disease biomarkers for computer-aided diagnosis of MCI. However, there are few studies dedicated to SCD progression prediction since subjects usually lack one or more imaging modalities. Besides, one usually has a limited number (e.g., tens) of SCD subjects, negatively affecting model robustness. To this end, we propose a Joint neuroimage Synthesis and Representation Learning (JSRL) framework for SCD conversion prediction using incomplete multi-modal neuroimages. The JSRL contains two components: 1) a generative adversarial network to synthesize missing images and generate multi-modal features, and 2) a classification network to fuse multi-modal features for SCD conversion prediction. The two components are incorporated into a joint learning framework by sharing the same features, encouraging effective fusion of multi-modal features for accurate prediction. A transfer learning strategy is employed in the proposed framework by leveraging model trained on the Alzheimer's Disease Neuroimaging Initiative (ADNI) with MRI and fluorodeoxyglucose PET from 863 subjects to both the Chinese Longitudinal Aging Study (CLAS) with only MRI from 76 SCD subjects and the Australian Imaging, Biomarkers and Lifestyle (AIBL) with MRI from 235 subjects. Experimental results suggest that the proposed JSRL yields superior performance in SCD and MCI conversion prediction and cross-database neuroimage synthesis, compared with several state-of-the-art methods.

Classification of Initial Stages of Alzheimer’s Disease through Pet Neuroimaging Modality and Deep Learning: Quantifying the Impact of Image Filtering Approaches

Alzheimer’s disease (AD) is a leading health concern affecting the elderly population worldwide. It is defined by amyloid plaques, neurofibrillary tangles, and neuronal loss. Neuroimaging modalities such as positron emission tomography (PET) and magnetic resonance imaging are routinely used in clinical settings to monitor the alterations in the brain during the course of progression of AD. Deep learning techniques such as convolutional neural networks (CNNs) have found numerous applications in healthcare and other technologies. Together with neuroimaging modalities, they can be deployed in clinical settings to learn effective representations of data for different tasks such as classification, segmentation, detection, etc. Image filtering methods are instrumental in making images viable for image processing operations and have found numerous applications in image-processing-related tasks. In this work, we deployed 3D-CNNs to learn effective representations of PET modality data to quantify the impact of different image filtering approaches. We used box filtering, median filtering, Gaussian filtering, and modified Gaussian filtering approaches to preprocess the images and use them for classification using 3D-CNN architecture. Our findings suggest that these approaches are nearly equivalent and have no distinct advantage over one another. For the multiclass classification task between normal control (NC), mild cognitive impairment (MCI), and AD classes, the 3D-CNN architecture trained using Gaussian-filtered data performed the best. For binary classification between NC and MCI classes, the 3D-CNN architecture trained using median-filtered data performed the best, while, for binary classification between AD and MCI classes, the 3D-CNN architecture trained using modified Gaussian-filtered data performed the best. Finally, for binary classification between AD and NC classes, the 3D-CNN architecture trained using box-filtered data performed the best.

Regression and Classification of Alzheimers Disease Diagnosis using NMF-TDNet Features from 3D Brain MR Image

With the development of deep learning and medical imaging technology, many researchers use convolutional neural network(CNN) to obtain deep-level features of medical image in order to better classify Alzheimer's disease (AD) and predict clinical scores. The principal component analysis network (PCANet) is a lightweight deep-learning network that mainly uses principal component analysis (PCA) to generate multilevel filter banks for the centralized learning of samples and then performs binarization and generates blockwise histograms to obtain image features. However, the dimensions of the extracted PCANet features reaching tens of thousands or even hundreds of thousands, and the formation of the multilevel filter banks is sample data dependent, reducing the flexibility of PCANet. In this paper, based on the idea of PCANet, we propose a data-independent network called the nonnegative matrix factorization tensor decomposition network (NMF-TDNet), which improves the computational efficiency and solves the data dependence problem of PCANet. In this network, we use nonnegative matrix factorization (NMF) instead of PCA to create multilevel filter banks for sample learning, then uses the learning results to build a higher-order tensor and perform tensor decomposition (TD) to achieve data dimensionality reduction, producing the final image features. Finally, our method use these features as the input of the support vector machine (SVM) for AD classification diagnosis and clinical score prediction. The performance of our method is extensively evaluated on the ADNI-1, ADNI-2 and OASIS datasets. The experimental results show that NMF-TDNet can achieve data dimensionality reduction (the dimensionality of the extracted features numbers only a few hundred dimensions, far less than the hundreds of thousands required by PCANet) and the NMF-TDNet features as input achieved superior performance than using PCANet features as input.

Multi-auxiliary domain transfer learning for diagnosis of MCI conversion

In the early stage of Alzheimer's disease (AD), mild cognitive impairment (MCI) has a higher risk of progression to AD, so the prediction of whether an MCI subject will progress to AD (known as progressive MCI, PMCI) or not (known as stable MCI, SMCI) within a certain period is particularly important in practice. It is known that such a task could benefit from jointly learning-related auxiliary tasks such as differentiating AD from PMCI or PMCI from normal control (NC) in order to take full advantage of their shared commonality. However, few existing methods along this line fully consider the correlations between the target and auxiliary tasks according to the clinical practice of AD pathology for diagnosis. To deal with this problem, in this paper, treating each task domain as a different one, we borrow the idea from transfer learning and propose a novel multi-auxiliary domain transfer learning (MaDTL) method, which explicitly utilizes the correlations between the target domain (task) and multi-auxiliary domains (tasks) according to the clinical practice. Specifically, the proposed MaDTL method incorporates two key modules. The first one is a multi-auxiliary domain transfer-based feature selection (MaDTFS) model, which can select a discriminative feature subset shared by the target domain and the multi-auxiliary domains. In the MaDTFS model, to combine more training data from multi-auxiliary domains and simultaneously suppress the negative effects resulting from the irrelevant parts of multi-auxiliary domains, we proposed a sparse group correlation Lasso that includes a proposed group correlation Lasso penalty (i.e., [Formula: see text]) and a proposed correlation Lasso penalty (i.e., [Formula: see text]). The second module in MaDTL is a multi-auxiliary domain transfer-based classification (MaDTC) model that improves the voting with linear weighting-based ensemble learning. This model extends the constraints of the linear weighting method so that it can simultaneously combine training data from multi-auxiliary domains and achieve a robust classifier by minimizing negative effects from the irrelevant part of multi-auxiliary domains. Experimental results on 409 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database with the baseline magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) data validate the effectiveness of the proposed method by significantly improving the classification accuracy to 80.37% for the identification of MCI-to-AD conversion, outperforming the state-of-the-art methods.

Disease Modelling of Cognitive Outcomes and Biomarkers in the European Prevention of Alzheimer's Dementia Longitudinal Cohort

A key challenge for the secondary prevention of Alzheimer’s dementia is the need to identify individuals early on in the disease process through sensitive cognitive tests and biomarkers. The European Prevention of Alzheimer’s Dementia (EPAD) consortium recruited participants into a longitudinal cohort study with the aim of building a readiness cohort for a proof-of-concept clinical trial and also to generate a rich longitudinal data-set for disease modelling. Data have been collected on a wide range of measurements including cognitive outcomes, neuroimaging, cerebrospinal fluid biomarkers, genetics and other clinical and environmental risk factors, and are available for 1,828 eligible participants at baseline, 1,567 at 6 months, 1,188 at one-year follow-up, 383 at 2 years, and 89 participants at three-year follow-up visit. We novelly apply state-of-the-art longitudinal modelling and risk stratification approaches to these data in order to characterise disease progression and biological heterogeneity within the cohort. Specifically, we use longitudinal class-specific mixed effects models to characterise the different clinical disease trajectories and a semi-supervised Bayesian clustering approach to explore whether participants can be stratified into homogeneous subgroups that have different patterns of cognitive functioning evolution, while also having subgroup-specific profiles in terms of baseline biomarkers and longitudinal rate of change in biomarkers.

Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review

(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer's diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.

Deep Bayesian Hashing With Center Prior for Multi-Modal Neuroimage Retrieval

Multi-modal neuroimage retrieval has greatly facilitated the efficiency and accuracy of decision making in clinical practice by providing physicians with previous cases (with visually similar neuroimages) and corresponding treatment records. However, existing methods for image retrieval usually fail when applied directly to multi-modal neuroimage databases, since neuroimages generally have smaller inter-class variation and larger inter-modal discrepancy compared to natural images. To this end, we propose a deep Bayesian hash learning framework, called CenterHash, which can map multi-modal data into a shared Hamming space and learn discriminative hash codes from imbalanced multi-modal neuroimages. The key idea to tackle the small inter-class variation and large inter-modal discrepancy is to learn a common center representation for similar neuroimages from different modalities and encourage hash codes to be explicitly close to their corresponding center representations. Specifically, we measure the similarity between hash codes and their corresponding center representations and treat it as a center prior in the proposed Bayesian learning framework. A weighted contrastive likelihood loss function is also developed to facilitate hash learning from imbalanced neuroimage pairs. Comprehensive empirical evidence shows that our method can generate effective hash codes and yield state-of-the-art performance in cross-modal retrieval on three multi-modal neuroimage datasets.

Improving Alzheimer's stage categorization with Convolutional Neural Network using transfer learning and different magnetic resonance imaging modalities

BACKGROUND

Alzheimer's Disease (AD) is a neurodegenerative disease characterized by progressive loss of memory and general decline in cognitive functions. Multi-modal imaging such as structural MRI and DTI provide useful information for the classification of patients on the basis of brain biomarkers. Recently, CNN methods have emerged as powerful tools to improve classification using images.

NEW METHOD

In this paper, we propose a transfer learning scheme using Convolutional Neural Networks (CNNs) to automatically classify brain scans focusing only on a small ROI: e.g. a few slices of the hippocampal region. The network's architecture is similar to a LeNet-like CNN upon which models are built and fused for AD stage classification diagnosis. We evaluated various types of transfer learning through the following mechanisms: (i) cross-modal (sMRI and DTI) and (ii) cross-domain transfer learning (using MNIST) (iii) a hybrid transfer learning of both types.

RESULTS

Our method shows good performances even on small datasets and with a limited number of slices of small brain region. It increases accuracy with more than 5 points for the most difficult classification tasks, i.e., AD/MCI and MCI/NC.

COMPARISON WITH EXISTING METHODS

Our methodology provides good accuracy scores for classification over a shallow convolutional network. Besides, we focused only on a small region; i.e., the hippocampal region, where few slices are selected to feed the network. Also, we used cross-modal transfer learning.

CONCLUSIONS

Our proposed method is suitable for working with a shallow CNN network for low-resolution MRI and DTI scans. It yields to significant results even if the model is trained on small datasets, which is often the case in medical image analysis.

A Survey on Deep Learning for Neuroimaging-Based Brain Disorder Analysis

Deep learning has recently been used for the analysis of neuroimages, such as structural magnetic resonance imaging (MRI), functional MRI, and positron emission tomography (PET), and it has achieved significant performance improvements over traditional machine learning in computer-aided diagnosis of brain disorders. This paper reviews the applications of deep learning methods for neuroimaging-based brain disorder analysis. We first provide a comprehensive overview of deep learning techniques and popular network architectures by introducing various types of deep neural networks and recent developments. We then review deep learning methods for computer-aided analysis of four typical brain disorders, including Alzheimer's disease, Parkinson's disease, Autism spectrum disorder, and Schizophrenia, where the first two diseases are neurodegenerative disorders and the last two are neurodevelopmental and psychiatric disorders, respectively. More importantly, we discuss the limitations of existing studies and present possible future directions.

Deep Disentangled Hashing with Momentum Triplets for Neuroimage Search

Neuroimaging has been widely used in computer-aided clinical diagnosis and treatment, and the rapid increase of neuroimage repositories introduces great challenges for efficient neuroimage search. Existing image search methods often use triplet loss to capture high-order relationships between samples. However, we find that the traditional triplet loss is difficult to pull positive and negative sample pairs to make their Hamming distance discrepancies larger than a small fixed value. This may reduce the discriminative ability of learned hash code and degrade the performance of image search. To address this issue, in this work, we propose a deep disentangled momentum hashing (DDMH) framework for neuroimage search. Specifically, we first investigate the original triplet loss and find that this loss function can be determined by the inner product of hash code pairs. Accordingly, we disentangle hash code norms and hash code directions and analyze the role of each part. By decoupling the loss function from the hash code norm, we propose a unique disentangled triplet loss, which can effectively push positive and negative sample pairs by desired Hamming distance discrepancies for hash codes with different lengths. We further develop a momentum triplet strategy to address the problem of insufficient triplet samples caused by small batch-size for 3D neuroimages. With the proposed disentangled triplet loss and the momentum triplet strategy, we design an end-to-end trainable deep hashing framework for neuroimage search. Comprehensive empirical evidence on three neuroimage datasets shows that DDMH has better performance in neuroimage search compared to several state-of-the-art methods.

Regularized Bagged Canonical Component Analysis for Multiclass Learning in Brain Imaging

A fundamental problem of supervised learning algorithms for brain imaging applications is that the number of features far exceeds the number of subjects. In this paper, we propose a combined feature selection and extraction approach for multiclass problems. This method starts with a bagging procedure which calculates the sign consistency of the multivariate analysis (MVA) projection matrix feature-wise to determine the relevance of each feature. This relevance measure provides a parsimonious matrix, which is combined with a hypothesis test to automatically determine the number of selected features. Then, a novel MVA regularized with the sign and magnitude consistency of the features is used to generate a reduced set of summary components providing a compact data description. We evaluated the proposed method with two multiclass brain imaging problems: 1) the classification of the elderly subjects in four classes (cognitively normal, stable mild cognitive impairment (MCI), MCI converting to AD in 3 years, and Alzheimer's disease) based on structural brain imaging data from the ADNI cohort; 2) the classification of children in 3 classes (typically developing, and 2 types of Attention Deficit/Hyperactivity Disorder (ADHD)) based on functional connectivity. Experimental results confirmed that each brain image (defined by 29.852 features in the ADNI database and 61.425 in the ADHD) could be represented with only 30 - 45% of the original features. Furthermore, this information could be redefined into two or three summary components, providing not only a gain of interpretability but also classification rate improvements when compared to state-of-art reference methods.

Machine Learning Techniques for the Diagnosis of Alzheimer’s Disease

Alzheimer’s disease is an incurable neurodegenerative disease primarily affecting the elderly population. Efficient automated techniques are needed for early diagnosis of Alzheimer’s. Many novel approaches are proposed by researchers for classification of Alzheimer’s disease. However, to develop more efficient learning techniques, better understanding of the work done on Alzheimer’s is needed. Here, we provide a review on 165 papers from 2005 to 2019, using various feature extraction and machine learning techniques. The machine learning techniques are surveyed under three main categories: support vector machine (SVM), artificial neural network (ANN), and deep learning (DL) and ensemble methods. We present a detailed review on these three approaches for Alzheimer’s with possible future directions.

Neuropsychological assessment and cortisol levels in biofluids from early Alzheimer's disease patients

Cortisol dysregulation is proposed as a factor in the development of Alzheimer's disease (AD). AD patients can show high cortisol levels in prodromal phases of AD, early enough that neuropsychological alterations exist but activities of daily living remain unimpaired. Nevertheless, it is unknown if biofluid cortisol levels can have some AD predictive power together with neuropsychological assessment in prodromal stages in comparison with other cognitive disorders. In this work, an analytical method based on ultra-performance liquid chromatography coupled to tandem mass spectrometry (UPLC-MS/MS) was applied to determine the cortisol levels in different biofluids (urine, plasma, saliva, cerebrospinal fluid). Early AD patients and non-AD patients recruited at out-patient neurological unit were classified from the standard cerebrospinal fluid biomarkers levels (β-amyloid, tau, phosphorylated tau), and studied with an extensive neuropsychological assessment including global, neuropsychological, functional and affective scales. We used a logistic regression model to discriminate between the AD and non-AD groups. Higher plasma cortisol levels were found in the AD group than in the non-AD group (p < 0.001). Regarding neuropsychological evaluation, delayed memory was used as representative of the neuropsychological status, and lower scores were obtained in the AD group (p < 0.001). The prediction model, including plasma cortisol levels and delayed memory scores, achieved an AUC of 0.93, as well as a sensitivity of 97% and a specificity of 69.4%. In conclusion, plasma cortisol levels and delayed memory scores were specifically impaired in early AD, allowing the development of a new diagnostic model which could be employed as a very satisfactory screening system.

Robust multi-label transfer feature learning for early diagnosis of Alzheimer's disease

Transfer learning has been successfully used in the early diagnosis of Alzheimer's disease (AD). In these methods, data from one single or multiple related source domain(s) are employed to aid the learning task in the target domain. However, most of the existing methods utilize data from all source domains, ignoring the fact that unrelated source domains may degrade the learning performance. Also, previous studies assume that class labels for all subjects are reliable, without considering the ambiguity of class labels caused by slight differences between early AD patients and normal control subjects. To address these issues, we propose to transform the original binary class label of a particular subject into a multi-bit label coding vector with the aid of multiple source domains. We further develop a robust multi-label transfer feature learning (rMLTFL) model to simultaneously capture a common set of features from different domains (including the target domain and all source domains) and to identify the unrelated source domains. We evaluate our method on 406 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database with baseline magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) data. The experimental results show that the proposed rMLTFL method can effectively improve the performance of AD diagnosis, compared with several state-of-the-art methods.

Transfer learning improves resting-state functional connectivity pattern analysis using convolutional neural networks

Background

Deep learning is gaining importance in the prediction of cognitive states and brain pathology based on neuroimaging data. Including multiple hidden layers in artificial neural networks enables unprecedented predictive power; however, the proper training of deep neural networks requires thousands of exemplars. Collecting this amount of data is not feasible in typical neuroimaging experiments. A handy solution to this problem, which has largely fallen outside the scope of deep learning applications in neuroimaging, is to repurpose deep networks that have already been trained on large datasets by fine-tuning them to target datasets/tasks with fewer exemplars. Here, we investigated how this method, called transfer learning, can aid age category classification and regression based on brain functional connectivity patterns derived from resting-state functional magnetic resonance imaging. We trained a connectome-convolutional neural network on a larger public dataset and then examined how the knowledge learned can be used effectively to perform these tasks on smaller target datasets collected with a different type of scanner and/or imaging protocol and pre-processing pipeline.

Results

Age classification on the target datasets benefitted from transfer learning. Significant improvement (∼9%–13% increase in accuracy) was observed when the convolutional layers’ weights were initialized based on the values learned on the public dataset and then fine-tuned to the target datasets. Transfer learning also appeared promising in improving the otherwise poor prediction of chronological age.

Conclusions

Transfer learning is a plausible solution to adapt convolutional neural networks to neuroimaging data with few exemplars and different data acquisition and pre-processing protocols.

Localized instance fusion of MRI data of Alzheimer's disease for classification based on instance transfer ensemble learning

BACKGROUND

Diagnosis of Alzheimer's disease (AD) is very important, and MRI is an effective imaging mode of Alzheimer's disease. There are many existing studies on the diagnosis of Alzheimer's disease based on MRI data. However, there are no studies on the transfer learning between different datasets (including different subjects), thereby improving the sample size of target dataset indirectly.

METHODS

Therefore, a new framework method is proposed in this paper to solve this problem. First, gravity transfer is used to transfer the source domain data closer to the target data set. Secondly, the best deviation between the transferred source domain samples and the target domain samples is searched by instance transfer learning algorithm (ITL) based on wrapper mode, thereby obtaining optimal transferred domain samples. Finally, the optimal transferred domain samples and the target domain training samples are combined for classification. If the source data and the target data have different features, a feature growing algorithm is proposed to solve this problem.

RESULTS

The experimental results show that the proposed method is effective regardless of different kernel functions, different number of samples and different parameters. Besides, the transferred source domain samples by ITL algorithm can enlarge the target domain training samples and assist to improve the classification accuracy significantly.

CONCLUSIONS

Therefore, the study can enlarge the samples of AD by instance transfer learning, thereby being helpful for the small sample problems of AD. Since the proposed algorithm is a framework algorithm, the study is heuristics to the relevant researchers.