Semi-supervised pattern classification of medical images: application to mild cognitive impairment (MCI)

Artificial intelligence for dementia research methods optimization

Artificial intelligence (AI) and machine learning (ML) approaches are increasingly being used in dementia research. However, several methodological challenges exist that may limit the insights we can obtain from high-dimensional data and our ability to translate these findings into improved patient outcomes. To improve reproducibility and replicability, researchers should make their well-documented code and modeling pipelines openly available. Data should also be shared where appropriate. To enhance the acceptability of models and AI-enabled systems to users, researchers should prioritize interpretable methods that provide insights into how decisions are generated. Models should be developed using multiple, diverse datasets to improve robustness, generalizability, and reduce potentially harmful bias. To improve clarity and reproducibility, researchers should adhere to reporting guidelines that are co-produced with multiple stakeholders. If these methodological challenges are overcome, AI and ML hold enormous promise for changing the landscape of dementia research and care. HIGHLIGHTS: Machine learning (ML) can improve diagnosis, prevention, and management of dementia. Inadequate reporting of ML procedures affects reproduction/replication of results. ML models built on unrepresentative datasets do not generalize to new datasets. Obligatory metrics for certain model structures and use cases have not been defined. Interpretability and trust in ML predictions are barriers to clinical translation.

Artificial Intelligence for Dementia Research Methods Optimization

INTRODUCTION

Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater.

METHODS

We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research.

RESULTS

We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future.

DISCUSSION

ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.

Deep semi-supervised multiple instance learning with self-correction for DME classification from OCT images

Supervised deep learning has achieved prominent success in various diabetic macular edema (DME) recognition tasks from optical coherence tomography (OCT) volumetric images. A common problematic issue that frequently occurs in this field is the shortage of labeled data due to the expensive fine-grained annotations, which increases substantial difficulty in accurate analysis by supervised learning. The morphological changes in the retina caused by DME might be distributed sparsely in B-scan images of the OCT volume, and OCT data is often coarsely labeled at the volume level. Hence, the DME identification task can be formulated as a multiple instance classification problem that could be addressed by multiple instance learning (MIL) techniques. Nevertheless, none of previous studies utilize unlabeled data simultaneously to promote the classification accuracy, which is particularly significant for a high quality of analysis at the minimum annotation cost. To this end, we present a novel deep semi-supervised multiple instance learning framework to explore the feasibility of leveraging a small amount of coarsely labeled data and a large amount of unlabeled data to tackle this problem. Specifically, we come up with several modules to further improve the performance according to the availability and granularity of their labels. To warm up the training, we propagate the bag labels to the corresponding instances as the supervision of training, and propose a self-correction strategy to handle the label noise in the positive bags. This strategy is based on confidence-based pseudo-labeling with consistency regularization. The model uses its prediction to generate the pseudo-label for each weakly augmented input only if it is highly confident about the prediction, which is subsequently used to supervise the same input in a strongly augmented version. This learning scheme is also applicable to unlabeled data. To enhance the discrimination capability of the model, we introduce the Student-Teacher architecture and impose consistency constraints between two models. For demonstration, the proposed approach was evaluated on two large-scale DME OCT image datasets. Extensive results indicate that the proposed method improves DME classification with the incorporation of unlabeled data and outperforms competing MIL methods significantly, which confirm the feasibility of deep semi-supervised multiple instance learning at a low annotation cost.

Transfer learning-based modified inception model for the diagnosis of Alzheimer's disease

Alzheimer's disease (AD) is a neurodegenerative ailment, which gradually deteriorates memory and weakens the cognitive functions and capacities of the body, such as recall and logic. To diagnose this disease, CT, MRI, PET, etc. are used. However, these methods are time-consuming and sometimes yield inaccurate results. Thus, deep learning models are utilized, which are less time-consuming and yield results with better accuracy, and could be used with ease. This article proposes a transfer learning-based modified inception model with pre-processing methods of normalization and data addition. The proposed model achieved an accuracy of 94.92 and a sensitivity of 94.94. It is concluded from the results that the proposed model performs better than other state-of-the-art models. For training purposes, a Kaggle dataset was used comprising 6,200 images, with 896 mild demented (M.D) images, 64 moderate demented (Mod.D) images, and 3,200 non-demented (N.D) images, and 1,966 veritably mild demented (V.M.D) images. These models could be employed for developing clinically useful results that are suitable to descry announcements in MRI images.

Voting Ensemble Approach for Enhancing Alzheimer's Disease Classification

Alzheimer's disease is dementia that impairs one's thinking, behavior, and memory. It starts as a moderate condition affecting areas of the brain that make it challenging to retain recently learned information, causes mood swings, and causes confusion regarding occasions, times, and locations. The most prevalent type of dementia, called Alzheimer's disease (AD), causes memory-related problems in patients. A precise medical diagnosis that correctly classifies AD patients results in better treatment. Currently, the most commonly used classification techniques extract features from longitudinal MRI data before creating a single classifier that performs classification. However, it is difficult to train a reliable classifier to achieve acceptable classification performance due to limited sample size and noise in longitudinal MRI data. Instead of creating a single classifier, we propose an ensemble voting method that generates multiple individual classifier predictions and then combines them to develop a more accurate and reliable classifier. The ensemble voting classifier model performs better in the Open Access Series of Imaging Studies (OASIS) dataset for older adults than existing methods in important assessment criteria such as accuracy, sensitivity, specificity, and AUC. For the binary classification of with dementia and no dementia, an accuracy of 96.4% and an AUC of 97.2% is attained.

HTLML: Hybrid AI Based Model for Detection of Alzheimer’s Disease

Alzheimer’s disease (AD) is a degenerative condition of the brain that affects the memory and reasoning abilities of patients. Memory is steadily wiped out by this condition, which gradually affects the brain’s ability to think, recall, and form intentions. In order to properly identify this disease, a variety of manual imaging modalities including CT, MRI, PET, etc. are being used. These methods, however, are time-consuming and troublesome in the context of early diagnostics. This is why deep learning models have been devised that are less time-intensive, require less high-tech hardware or human interaction, continue to improve in performance, and are useful for the prediction of AD, which can also be verified by experimental results obtained by doctors in medical institutions or health care facilities. In this paper, we propose a hybrid-based AI-based model that includes the combination of both transfer learning (TL) and permutation-based machine learning (ML) voting classifier in terms of two basic phases. In the first phase of implementation, it comprises two TL-based models: namely, DenseNet-121 and Densenet-201 for features extraction, whereas in the second phase of implementation, it carries out three different ML classifiers like SVM, Naïve base and XGBoost for classification purposes. The final classifier outcomes are evaluated by means of permutations of the voting mechanism. The proposed model achieved accuracy of 91.75%, specificity of 96.5%, and an F1-score of 90.25. The dataset used for training was obtained from Kaggle and contains 6200 photos, including 896 images classified as mildly demented, 64 images classified as moderately demented, 3200 images classified as non-demented, and 1966 images classified as extremely mildly demented. The results show that the suggested model outperforms current state-of-the-art models. These models could be used to generate therapeutically viable methods for detecting AD in MRI images based on these results for clinical prospective.

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.

Image Classification and Land Cover Mapping Using Sentinel-2 Imagery: Optimization of SVM Parameters

Land use/cover (LU/LC) classification provides proxies of the natural and social processes related to urban development, providing stakeholders with crucial information. Remotely sensed images combined with supervised classification are common to define land use, but high-performance classifiers remain difficult to achieve, due to the presence of model hyperparameters. Conventional approaches rely on manual adjustment, which is time consuming and often unsatisfying. Therefore, the goal of this study has been to optimize the parameters of the support vector machine (SVM) algorithm for the generation of land use/cover maps from Sentinel-2 satellite imagery in selected humid and arid (three study sites each) climatic regions of Iran. For supervised SVM classification, we optimized two important parameters (gamma in kernel function and penalty parameter) of the LU/LC classification. Using the radial basis function (RBF) of the SVM classification method, we examined seven values for both parameters ranging from 0.001 to 1000. For both climate types, the penalty parameters (PP) showed a direct relationship with overall accuracy (OA). Statistical results confirmed that in humid study regions, LU/LC maps produced with a penalty parameter >100 were more accurate. However, for regions with arid climates, LU/LC maps with a penalty parameter >0.1 were more accurate. Mapping accuracy for both climate types was sensitive to the penalty parameter. In contrast, variations of the gamma values in the kernel function had no effect on the accuracy of the LU/LC maps in either of the climate zones. These new findings on SVM image classification are directly applicable to LU/LC for planning and environmental and natural resource management.

GraphXCOVID: Explainable deep graph diffusion pseudo-Labelling for identifying COVID-19 on chest X-rays

Can one learn to diagnose COVID-19 under extreme minimal supervision? Since the outbreak of the novel COVID-19 there has been a rush for developing automatic techniques for expert-level disease identification on Chest X-ray data. In particular, the use of deep supervised learning has become the go-to paradigm. However, the performance of such models is heavily dependent on the availability of a large and representative labelled dataset. The creation of which is a heavily expensive and time consuming task, and especially imposes a great challenge for a novel disease. Semi-supervised learning has shown the ability to match the incredible performance of supervised models whilst requiring a small fraction of the labelled examples. This makes the semi supervised paradigm an attractive option for identifying COVID-19. In this work, we introduce a graph based deep semi-supervised framework for classifying COVID-19 from chest X-rays. Our framework introduces an optimisation model for graph diffusion that reinforces the natural relation among the tiny labelled set and the vast unlabelled data. We then connect the diffusion prediction output as pseudo-labels that are used in an iterative scheme in a deep net. We demonstrate, through our experiments, that our model is able to outperform the current leading supervised model with a tiny fraction of the labelled examples. Finally, we provide attention maps to accommodate the radiologist's mental model, better fitting their perceptual and cognitive abilities. These visualisation aims to assist the radiologist in judging whether the diagnostic is correct or not, and in consequence to accelerate the decision.

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.

Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer's disease dementia: a systematic review

BACKGROUND

An increase in lifespan in our society is a double-edged sword that entails a growing number of patients with neurocognitive disorders, Alzheimer's disease being the most prevalent. Advances in medical imaging and computational power enable new methods for the early detection of neurocognitive disorders with the goal of preventing or reducing cognitive decline. Computer-aided image analysis and early detection of changes in cognition is a promising approach for patients with mild cognitive impairment, sometimes a prodromal stage of Alzheimer's disease dementia.

METHODS

We conducted a systematic review following PRISMA guidelines of studies where machine learning was applied to neuroimaging data in order to predict whether patients with mild cognitive impairment might develop Alzheimer's disease dementia or remain stable. After removing duplicates, we screened 452 studies and selected 116 for qualitative analysis.

RESULTS

Most studies used magnetic resonance image (MRI) and positron emission tomography (PET) data but also magnetoencephalography. The datasets were mainly extracted from the Alzheimer's disease neuroimaging initiative (ADNI) database with some exceptions. Regarding the algorithms used, the most common was support vector machine with a mean accuracy of 75.4%, but convolutional neural networks achieved a higher mean accuracy of 78.5%. Studies combining MRI and PET achieved overall better classification accuracy than studies that only used one neuroimaging technique. In general, the more complex models such as those based on deep learning, combined with multimodal and multidimensional data (neuroimaging, clinical, cognitive, genetic, and behavioral) achieved the best performance.

CONCLUSIONS

Although the performance of the different methods still has room for improvement, the results are promising and this methodology has a great potential as a support tool for clinicians and healthcare professionals.

Biomarker Extraction Based on Subspace Learning for the Prediction of Mild Cognitive Impairment Conversion

Accurate recognition of progressive mild cognitive impairment (MCI) is helpful to reduce the risk of developing Alzheimer's disease (AD). However, it is still challenging to extract effective biomarkers from multivariate brain structural magnetic resonance imaging (MRI) features to accurately differentiate the progressive MCI from stable MCI. We develop novel biomarkers by combining subspace learning methods with the information of AD as well as normal control (NC) subjects for the prediction of MCI conversion using multivariate structural MRI data. Specifically, we first learn two projection matrices to map multivariate structural MRI data into a common label subspace for AD and NC subjects, where the original data structure and the one-to-one correspondence between multiple variables are kept as much as possible. Afterwards, the multivariate structural MRI features of MCI subjects are mapped into a common subspace according to the projection matrices. We then perform the self-weighted operation and weighted fusion on the features in common subspace to extract the novel biomarkers for MCI subjects. The proposed biomarkers are tested on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Experimental results indicate that our proposed biomarkers outperform the competing biomarkers on the discrimination between progressive MCI and stable MCI. And the improvement from the proposed biomarkers is not limited to a particular classifier. Moreover, the results also confirm that the information of AD and NC subjects is conducive to predicting conversion from MCI to AD. In conclusion, we find a good representation of brain features from high-dimensional MRI data, which exhibits promising performance for predicting conversion from MCI to AD.

Anomaly Analysis of Alzheimer’s Disease in PET Images Using an Unsupervised Adversarial Deep Learning Model

In this study, the anomaly analysis of Alzheimer’s disease using positron emission tomography (PET) images using an unsupervised proposed adversarial model is investigated. The model consists of three parts: a parallel-network encoder, which is comprised of a convolutional pipeline and a dilated convolutional pipeline that extracts global and local features and concatenates them, a decoder that reconstructs the input image from the obtained feature vector, and a discriminator that distinguishes if the input image image is real or fake. The hypothesis is that if the proposed model is trained with only normal brain images, the corresponding construction loss for normal images should be minimal. However, if the input image belongs to a class that is designated as an anomaly that which the model is not trained with, then the construction loss will be high. This will reflect during the anomaly score comparison between the normal and the anomalous image. A multi-case analysis is performed for three major classes using the Alzheimer’s Disease Neuroimaging Initiative dataset, Alzheimer’s disease, mild cognitive impairment, and normal control. The base parallel-encoder network shows better classification accuracy than the benchmark models, and the proposed model that is built on the parallel model outperforms the benchmark anomaly detection models. The proposed model gave out 96.03% and 75.21% in classification and area under the curve score, respectively. Additionally, a qualitative evaluation done by using Fréchet inception distance gave a better score than the state-of-the-art by three points.

Deep virtual adversarial self-training with consistency regularization for semi-supervised medical image classification

Convolutional neural networks have achieved prominent success on a variety of medical imaging tasks when a large amount of labeled training data is available. However, the acquisition of expert annotations for medical data is usually expensive and time-consuming, which poses a great challenge for supervised learning approaches. In this work, we proposed a novel semi-supervised deep learning method, i.e., deep virtual adversarial self-training with consistency regularization, for large-scale medical image classification. To effectively exploit useful information from unlabeled data, we leverage self-training and consistency regularization to harness the underlying knowledge, which helps improve the discrimination capability of training models. More concretely, the model first uses its prediction for pseudo-labeling on the weakly-augmented input image. A pseudo-label is kept only if the corresponding class probability is of high confidence. Then the model prediction is encouraged to be consistent with the strongly-augmented version of the same input image. To improve the robustness of the network against virtual adversarial perturbed input, we incorporate virtual adversarial training (VAT) on both labeled and unlabeled data into the course of training. Hence, the network is trained by minimizing a combination of three types of losses, including a standard supervised loss on labeled data, a consistency regularization loss on unlabeled data, and a VAT loss on both labeled and labeled data. We extensively evaluate the proposed semi-supervised deep learning methods on two challenging medical image classification tasks: breast cancer screening from ultrasound images and multi-class ophthalmic disease classification from optical coherence tomography B-scan images. Experimental results demonstrate that the proposed method outperforms both supervised baseline and other state-of-the-art methods by a large margin on all tasks.

Gradually evaluating of suicidal risk in depression by semi-supervised cluster analysis on resting-state fMRI

A timely and effective evaluation of the suicidal ideation bears practical meaning, particularly for the depressive who tend to disguise the real suicide intent and without obvious symptoms. Measuring individual ideation of the depression with uncertain or transient suicide crisis is the purpose. Resting-state fMRI data were collected from 78 depressed patients with variable clinical suicidal crisis. Thirty subjects were well labeled as extremely serious individuals with suicide attempters or as without suicidal ideation. A feature mask was constructed via the two sample t-test on their regional conncectivities. Then, a semi-supervised machine learning frame using the feature mask was designed to assist in clarifying gradation of suicidal susceptibility for the residual forty-eight vaguely defined subjects, by a way of Iterative Self-Organizing Data analysis techniques (ISODATA). Such semi-supervised model was designed purposely to block out the effect of disease itself on the suicide intendancy evaluation. The vague-labeled patients were divided into another two different stages relating to their suicidal susceptibility. The distance ratio of each subject to the two well-defined extreme groups in the feature space can be utilized as the suicide risk index. The re-evaluation of the Nurses' Global Assessment of Suicide Risk (NGASR) via experts blind to original HAM-D rates was significantly correlated with the model estimation. The constructed model suggested its potential to examine the risk of suicidal in an objective way. The functional connectivity, locating mostly within the frontal-temporal circuit and involving the default mode network (DMN), were well integrated to discriminative the gradual susceptibility of suicidal.

Digital Biomarkers for the Early Detection of Mild Cognitive Impairment: Artificial Intelligence Meets Virtual Reality

Elderly people affected by Mild Cognitive Impairment (MCI) usually report a perceived decline in cognitive functions that deeply impacts their quality of life. This subtle waning, although it cannot be diagnosable as dementia, is noted by caregivers on the basis of their relative’s behaviors. Crucially, if this condition is also not detected in time by clinicians, it can easily turn into dementia. Thus, early detection of MCI is strongly needed. Classical neuropsychological measures – underlying a categorical model of diagnosis - could be integrated with a dimensional assessment approach involving Virtual Reality (VR) and Artificial Intelligence (AI). VR can be used to create highly ecologically controlled simulations resembling the daily life contexts in which patients’ daily instrumental activities (IADL) usually take place. Clinicians can record patients’ kinematics, particularly gait, while performing IADL (Digital Biomarkers). Then, Artificial Intelligence employs Machine Learning (ML) to analyze them in combination with clinical and neuropsychological data. This integrated computational approach would enable the creation of a predictive model to identify specific patterns of cognitive and motor impairment in MCI. Therefore, this new dimensional cognitive-behavioral assessment would reveal elderly people’s neural alterations and impaired cognitive functions, typical of MCI and dementia, even in early stages for more time-sensitive interventions.

Dynamical Role of Pivotal Brain Regions in Parkinson Symptomatology Uncovered with Deep Learning

BACKGROUND

The release of a broad, longitudinal anatomical dataset by the Parkinson's Progression Markers Initiative promoted a surge of machine-learning studies aimed at predicting disease onset and progression. However, the excessive number of features used in these models often conceals their relationship to the Parkinsonian symptomatology.

OBJECTIVES

The aim of this study is two-fold: (i) to predict future motor and cognitive impairments up to four years from brain features acquired at baseline; and (ii) to interpret the role of pivotal brain regions responsible for different symptoms from a neurological viewpoint.

METHODS

We test several deep-learning neural network configurations, and report our best results obtained with an autoencoder deep-learning model, run on a 5-fold cross-validation set. Comparison with Existing Methods: Our approach improves upon results from standard regression and others. It also includes neuroimaging biomarkers as features.

RESULTS

The relative contributions of pivotal brain regions to each impairment change over time, suggesting a dynamical reordering of culprits as the disease progresses. Specifically, the Putamen is initially the most critical region accounting for the overall cognitive state, only being surpassed by the Substantia Nigra in later years. The Pallidum is the first region to influence motor scores, followed by the parahippocampal and ambient gyri, and the anterior orbital gyrus.

CONCLUSIONS

While the causal link between regional brain atrophy and Parkinson symptomatology is poorly understood, our methods demonstrate that the contributions of pivotal regions to cognitive and motor impairments are more dynamical than generally appreciated.

Identification of Alzheimer’s Disease on the Basis of a Voxel-Wise Approach

Robust prediction of Alzheimer’s disease (AD) helps in the early diagnosis of AD and may support the treatment of AD patients. In this study, for early detection of AD and prediction of mild cognitive impairment (MCI) conversion, we develop an automatic computer-aided diagnosis (CAD) framework based on a merit-based feature selection method through a whole-brain voxel-wise analysis using baseline magnetic resonance imaging (MRI) data. We also explore the impact of different MRI spatial resolution on the voxel-wise metric AD classification and MCI conversion prediction. We assessed the proposed CAD framework using the whole-brain voxel-wise MRI features of 507 J-ADNI participants (146 healthy controls [HCs], 102 individuals with stable MCI [sMCI], 112 with progressive MCI [pMCI], and 147 with AD) among four clinically relevant pairs of diagnostic groups at different imaging resolutions (i.e., 2, 4, 8, and 16 mm). Using a support vector machine classifier through a 10-fold cross-validation strategy at a spatial resolution of 2 mm, the proposed CAD framework yielded classification accuracies of 91.13%, 74.77%, 81.12%, and 81.78% in identifying AD/healthy control, sMCI/pMCI, sMCI/AD, and pMCI/HC, respectively. The experimental results show that a lower spatial resolution (i.e., 2 mm) may provide more robust information to trace the neuronal loss-related brain atrophy in AD.

A deep learning model for early prediction of Alzheimer's disease dementia based on hippocampal magnetic resonance imaging data

INTRODUCTION

It is challenging at baseline to predict when and which individuals who meet criteria for mild cognitive impairment (MCI) will ultimately progress to Alzheimer's disease (AD) dementia.

METHODS

A deep learning method is developed and validated based on magnetic resonance imaging scans of 2146 subjects (803 for training and 1343 for validation) to predict MCI subjects' progression to AD dementia in a time-to-event analysis setting.

RESULTS

The deep-learning time-to-event model predicted individual subjects' progression to AD dementia with a concordance index of 0.762 on 439 Alzheimer's Disease Neuroimaging Initiative testing MCI subjects with follow-up duration from 6 to 78 months (quartiles: [24, 42, 54]) and a concordance index of 0.781 on 40 Australian Imaging Biomarkers and Lifestyle Study of Aging testing MCI subjects with follow-up duration from 18 to 54 months (quartiles: [18, 36, 54]). The predicted progression risk also clustered individual subjects into subgroups with significant differences in their progression time to AD dementia (P < .0002). Improved performance for predicting progression to AD dementia (concordance index = 0.864) was obtained when the deep learning-based progression risk was combined with baseline clinical measures.

DISCUSSION

Our method provides a cost effective and accurate means for prognosis and potentially to facilitate enrollment in clinical trials with individuals likely to progress within a specific temporal period.

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods that can learn with less/other types of supervision, have been proposed. We give an overview of semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research. A dataset with the details of the surveyed papers is available via https://figshare.com/articles/Database_of_surveyed_literature_in_Not-so-supervised_a_survey_of_semi-supervised_multi-instance_and_transfer_learning_in_medical_image_analysis_/7479416.

Dynamic Hyper-Graph Inference Framework for Computer-Assisted Diagnosis of Neurodegenerative Diseases

Hyper-graph techniques have been widely investigated in computer vision and medical imaging applications, showing superior performance for modeling complex subject-wise relationships and sufficient flexibility to deal with missing data from multi-modal neuroimaging data. Existing hyper-graph methods, however, are inadequate for two reasons. First, representations are generated only from the observed imaging data, a process that is completely independent of the subsequent data label inference/ classification step. Thus, hyper-graph results constructed in this way may not be consistent with phenotype data such as clinical labels or scores. More critically, it might generate sub-optimal predictions in relation to clinical labels/scores. Second, current hyper-graph inference methods rely on two sequential steps: 1) building the hyper-graph for each individual modality and then predicted latent labels for new subjects upon each constructed hyper-graph and 2) a voting procedure to incorporate inference results across different hyper-graphs. This approach, however, is limited by failing to consider the complex and complementary relationships of multi-modal imaging data with respect to hyper-graph inference procedure. To address these two issues, we propose a novel dynamic hyper-graph inference method supported by a semi-supervised framework. Our method iteratively estimates and adjusts the hyper-graph structures from multi-modal imaging data until consistency between the learned hyper-graph and the observed clinical labels and scores is achieved. This hyper-graph inference framework also eases the integration process of classification (identifying individuals having neurodegenerative disease) and regression (predicting the clinical scores) within the same framework. The experimental results on identifying mild cognition impairment (MCI) subjects and the fine grained recognition of MCI progression stages show improved performance using our proposed hyper-graph inference method compared with conventional methods.

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.

A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer's disease

Some forms of mild cognitive impairment (MCI) are the clinical precursors of Alzheimer's disease (AD), while other MCI types tend to remain stable over-time and do not progress to AD. To identify and choose effective and personalized strategies to prevent or slow the progression of AD, we need to develop objective measures that are able to discriminate the MCI patients who are at risk of AD from those MCI patients who have less risk to develop AD. Here, we present a novel deep learning architecture, based on dual learning and an ad hoc layer for 3D separable convolutions, which aims at identifying MCI patients who have a high likelihood of developing AD within 3 years. Our deep learning procedures combine structural magnetic resonance imaging (MRI), demographic, neuropsychological, and APOe4 genetic data as input measures. The most novel characteristics of our machine learning model compared to previous ones are the following: 1) our deep learning model is multi-tasking, in the sense that it jointly learns to simultaneously predict both MCI to AD conversion as well as AD vs. healthy controls classification, which facilitates relevant feature extraction for AD prognostication; 2) the neural network classifier employs fewer parameters than other deep learning architectures which significantly limits data-overfitting (we use ∼550,000 network parameters, which is orders of magnitude lower than other network designs); 3) both structural MRI images and their warp field characteristics, which quantify local volumetric changes in relation to the MRI template, were used as separate input streams to extract as much information as possible from the MRI data. All analyses were performed on a subset of the database made publicly available via the Alzheimer's Disease Neuroimaging Initiative (ADNI), (n = 785 participants, n = 192 AD patients, n = 409 MCI patients (including both MCI patients who convert to AD and MCI patients who do not covert to AD), and n = 184 healthy controls). The most predictive combination of inputs were the structural MRI images and the demographic, neuropsychological, and APOe4 data. In contrast, the warp field metrics were of little added predictive value. The algorithm was able to distinguish the MCI patients developing AD within 3 years from those patients with stable MCI over the same time-period with an area under the curve (AUC) of 0.925 and a 10-fold cross-validated accuracy of 86%, a sensitivity of 87.5%, and specificity of 85%. To our knowledge, this is the highest performance achieved so far using similar datasets. The same network provided an AUC of 1 and 100% accuracy, sensitivity, and specificity when classifying patients with AD from healthy controls. Our classification framework was also robust to the use of different co-registration templates and potentially irrelevant features/image portions. Our approach is flexible and can in principle integrate other imaging modalities, such as PET, and diverse other sets of clinical data. The convolutional framework is potentially applicable to any 3D image dataset and gives the flexibility to design a computer-aided diagnosis system targeting the prediction of several medical conditions and neuropsychiatric disorders via multi-modal imaging and tabular clinical data.

Brain MR Radiomics to Differentiate Cognitive Disorders

OBJECTIVE

Subtle and gradual changes occur in the brain years before cognitive impairment due to age-related neurodegenerative disorders. The authors examined the utility of hippocampal texture analysis and volumetric features extracted from brain magnetic resonance (MR) data to differentiate between three cognitive groups (cognitively normal individuals, individuals with mild cognitive impairment, and individuals with Alzheimer's disease) and neuropsychological scores on the Clinical Dementia Rating (CDR) scale.

METHODS

Data from 173 unique patients with 3-T T₁-weighted MR images from the Alzheimer's Disease Neuroimaging Initiative database were analyzed. A variety of texture and volumetric features were extracted from bilateral hippocampal regions and were used to perform binary classification of cognitive groups and CDR scores. The authors used diagonal quadratic discriminant analysis in a leave-one-out cross-validation scheme. Sensitivity, specificity, and area under the receiver operating characteristic curve were used to assess the performance of models.

RESULTS

The results show promise for hippocampal texture analysis to distinguish between no impairment and early stages of impairment. Volumetric features were more successful at differentiating between no impairment and advanced stages of impairment.

CONCLUSIONS

MR radiomics may be a promising tool to classify various cognitive groups.

Callosal thickness profiles for prognosticating conversion from mild cognitive impairment to Alzheimer's disease: A classification approach

INTRODUCTION

Alzheimer's disease (AD) is the most common form of dementia. Finding biomarkers to prognosticate transition from mild cognitive impairment (MCI) to AD is important to clinical medicine. Promising imaging biomarkers of AD conversion identified so far include atrophy of the cerebral cortex and subcortical gray matter nuclei.

METHODS

This study introduces thickness and bending angle of the corpus callosum as a putative white matter marker of MCI to AD conversion. The corpus callosum is computationally less demanding to segment automatically compared to more complicated structures and a subject can be processed in a few minutes. We aimed to demonstrate that callosal shape and thickness measures provide a simple, effective, and accurate prognostication tool in ADNI dataset. Using longitudinal datasets, we classified MCI subjects based on conversion to AD assessed via cognitive testing. We evaluated the classification accuracy of callosal shape features in comparison with the existing "gold standard" cortical thickness and subcortical gray matter volume measures.

RESULTS

The callosal thickness measures were less accurate in classifying conversion status by cognitive scores compared to gray matter measures for AD.

CONCLUSIONS

While this paper presented a negative result, this method may be more suitable for a disease of the white matter.

Brain MRI analysis for Alzheimer's disease diagnosis using an ensemble system of deep convolutional neural networks

Alzheimer's disease is an incurable, progressive neurological brain disorder. Earlier detection of Alzheimer's disease can help with proper treatment and prevent brain tissue damage. Several statistical and machine learning models have been exploited by researchers for Alzheimer's disease diagnosis. Analyzing magnetic resonance imaging (MRI) is a common practice for Alzheimer's disease diagnosis in clinical research. Detection of Alzheimer's disease is exacting due to the similarity in Alzheimer's disease MRI data and standard healthy MRI data of older people. Recently, advanced deep learning techniques have successfully demonstrated human-level performance in numerous fields including medical image analysis. We propose a deep convolutional neural network for Alzheimer's disease diagnosis using brain MRI data analysis. While most of the existing approaches perform binary classification, our model can identify different stages of Alzheimer's disease and obtains superior performance for early-stage diagnosis. We conducted ample experiments to demonstrate that our proposed model outperformed comparative baselines on the Open Access Series of Imaging Studies dataset.

Identifying Degenerative Brain Disease Using Rough Set Classifier Based on Wavelet Packet Method

Population aging has become a worldwide phenomenon, which causes many serious problems. The medical issues related to degenerative brain disease have gradually become a concern. Magnetic Resonance Imaging is one of the most advanced methods for medical imaging and is especially suitable for brain scans. From the literature, although the automatic segmentation method is less laborious and time-consuming, it is restricted in several specific types of images. In addition, hybrid techniques segmentation improves the shortcomings of the single segmentation method. Therefore, this study proposed a hybrid segmentation combined with rough set classifier and wavelet packet method to identify degenerative brain disease. The proposed method is a three-stage image process method to enhance accuracy of brain disease classification. In the first stage, this study used the proposed hybrid segmentation algorithms to segment the brain ROI (region of interest). In the second stage, wavelet packet was used to conduct the image decomposition and calculate the feature values. In the final stage, the rough set classifier was utilized to identify the degenerative brain disease. In verification and comparison, two experiments were employed to verify the effectiveness of the proposed method and compare with the TV-seg (total variation segmentation) algorithm, Discrete Cosine Transform, and the listing classifiers. Overall, the results indicated that the proposed method outperforms the listing methods.

Classification of Alzheimer's Disease and Prediction of Mild Cognitive Impairment Conversion Using Histogram-Based Analysis of Patient-Specific Anatomical Brain Connectivity Networks

In this study, we investigated the early detection of Alzheimer's disease (AD) and mild cognitive impairment (MCI) conversion to AD through individual structural connectivity networks using structural magnetic resonance imaging (sMRI) data. In the proposed method, the cortical morphometry of individual gray matter images were used to construct structural connectivity networks. A statistical feature generation approach based on histogram-based feature generation procedure was proposed to represent a statistical-pattern of connectivity networks from a high-dimensional space into low-dimensional feature vectors. The proposed method was evaluated on numerous samples including 61 healthy controls (HC), 42 stable-MCI (sMCI), 45 progressive-MCI (pMCI), and 83 AD subjects at the baseline from the J-ADNI data-set using support vector machine classifier. The proposed method yielded a classification accuracy of 84.17%, 70.38%, and 61.05% in identifying AD/HC, MCIs/HCs, and sMCI/pMCI, respectively. The experimental results show that the proposed method performed in a comparable way to alternative methods using MRI data.

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.

Landmark-based deep multi-instance learning for brain disease diagnosis

In conventional Magnetic Resonance (MR) image based methods, two stages are often involved to capture brain structural information for disease diagnosis, i.e., 1) manually partitioning each MR image into a number of regions-of-interest (ROIs), and 2) extracting pre-defined features from each ROI for diagnosis with a certain classifier. However, these pre-defined features often limit the performance of the diagnosis, due to challenges in 1) defining the ROIs and 2) extracting effective disease-related features. In this paper, we propose a landmark-based deep multi-instance learning (LDMIL) framework for brain disease diagnosis. Specifically, we first adopt a data-driven learning approach to discover disease-related anatomical landmarks in the brain MR images, along with their nearby image patches. Then, our LDMIL framework learns an end-to-end MR image classifier for capturing both the local structural information conveyed by image patches located by landmarks and the global structural information derived from all detected landmarks. We have evaluated our proposed framework on 1526 subjects from three public datasets (i.e., ADNI-1, ADNI-2, and MIRIAD), and the experimental results show that our framework can achieve superior performance over state-of-the-art approaches.

Generative diffeomorphic modelling of large MRI data sets for probabilistic template construction

In this paper we present a hierarchical generative model of medical image data, which can capture simultaneously the variability of both signal intensity and anatomical shapes across large populations. Such a model has a direct application for learning average-shaped probabilistic tissue templates in a fully automated manner. While in principle the generality of the proposed Bayesian approach makes it suitable to address a wide range of medical image computing problems, our work focuses primarily on neuroimaging applications. In particular we validate the proposed method on both real and synthetic brain MR scans including the cervical cord and demonstrate that it yields accurate alignment of brain and spinal cord structures, as compared to state-of-the-art tools for medical image registration. At the same time we illustrate how the resulting tissue probability maps can readily be used to segment, bias correct and spatially normalise unseen data, which are all crucial pre-processing steps for MR imaging studies.

•

We present a generative modelling framework to process large MRI data sets.

•

The proposed framework can serve to learn average-shaped tissue probability maps and empirical intensity priors.

•

We explore semi-supervised learning and variational inference schemes.

•

The method is validated against state-of-the-art tools using publicly available data.

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

Recently, transfer learning has been successfully applied in early diagnosis of Alzheimer's Disease (AD) based on multi-domain data. However, most of existing methods only use data from a single auxiliary domain, and thus cannot utilize the intrinsic useful correlation information from multiple domains. Accordingly, in this paper, we consider the joint learning of tasks in multi-auxiliary domains and the target domain, and propose a novel Multi-Domain Transfer Learning (MDTL) framework for early diagnosis of AD. Specifically, the proposed MDTL framework consists of two key components: 1) a multi-domain transfer feature selection (MDTFS) model that selects the most informative feature subset from multi-domain data, and 2) a multi-domain transfer classification (MDTC) model that can identify disease status for early AD detection. We evaluate our method on 807 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database using baseline magnetic resonance imaging (MRI) data. The experimental results show that the proposed MDTL method can effectively utilize multi-auxiliary domain data for improving the learning performance in the target domain, compared with several state-of-the-art methods.

Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls

Neuroimaging-based single subject prediction of brain disorders has gained increasing attention in recent years. Using a variety of neuroimaging modalities such as structural, functional and diffusion MRI, along with machine learning techniques, hundreds of studies have been carried out for accurate classification of patients with heterogeneous mental and neurodegenerative disorders such as schizophrenia and Alzheimer's disease. More than 500 studies have been published during the past quarter century on single subject prediction focused on a multiple brain disorders. In the first part of this study, we provide a survey of more than 200 reports in this field with a focus on schizophrenia, mild cognitive impairment (MCI), Alzheimer's disease (AD), depressive disorders, autism spectrum disease (ASD) and attention-deficit hyperactivity disorder (ADHD). Detailed information about those studies such as sample size, type and number of extracted features and reported accuracy are summarized and discussed. To our knowledge, this is by far the most comprehensive review of neuroimaging-based single subject prediction of brain disorders. In the second part, we present our opinion on major pitfalls of those studies from a machine learning point of view. Common biases are discussed and suggestions are provided. Moreover, emerging trends such as decentralized data sharing, multimodal brain imaging, differential diagnosis, disease subtype classification and deep learning are also discussed. Based on this survey, there is extensive evidence showing the great potential of neuroimaging data for single subject prediction of various disorders. However, the main bottleneck of this exciting field is still the limited sample size, which could be potentially addressed by modern data sharing models such as the ones discussed in this paper. Emerging big data technologies and advanced data-intensive machine learning methodologies such as deep learning have coincided with an increasing need for accurate, robust and generalizable single subject prediction of brain disorders during an exciting time. In this report, we survey the past and offer some opinions regarding the road ahead.

Semi-supervised learning for genomic prediction of novel traits with small reference populations: an application to residual feed intake in dairy cattle

Background

Genomic prediction for novel traits, which can be costly and labor-intensive to measure, is often hampered by low accuracy due to the limited size of the reference population. As an option to improve prediction accuracy, we introduced a semi-supervised learning strategy known as the self-training model, and applied this method to genomic prediction of residual feed intake (RFI) in dairy cattle.

Methods

We describe a self-training model that is wrapped around a support vector machine (SVM) algorithm, which enables it to use data from animals with and without measured phenotypes. Initially, a SVM model was trained using data from 792 animals with measured RFI phenotypes. Then, the resulting SVM was used to generate self-trained phenotypes for 3000 animals for which RFI measurements were not available. Finally, the SVM model was re-trained using data from up to 3792 animals, including those with measured and self-trained RFI phenotypes.

Results

Incorporation of additional animals with self-trained phenotypes enhanced the accuracy of genomic predictions compared to that of predictions that were derived from the subset of animals with measured phenotypes. The optimal ratio of animals with self-trained phenotypes to animals with measured phenotypes (2.5, 2.0, and 1.8) and the maximum increase achieved in prediction accuracy measured as the correlation between predicted and actual RFI phenotypes (5.9, 4.1, and 2.4%) decreased as the size of the initial training set (300, 400, and 500 animals with measured phenotypes) increased. The optimal number of animals with self-trained phenotypes may be smaller when prediction accuracy is measured as the mean squared error rather than the correlation between predicted and actual RFI phenotypes.

Conclusions

Our results demonstrate that semi-supervised learning models that incorporate self-trained phenotypes can achieve genomic prediction accuracies that are comparable to those obtained with models using larger training sets that include only animals with measured phenotypes. Semi-supervised learning can be helpful for genomic prediction of novel traits, such as RFI, for which the size of reference population is limited, in particular, when the animals to be predicted and the animals in the reference population originate from the same herd-environment.

Multimodal manifold-regularized transfer learning for MCI conversion prediction

As the early stage of Alzheimer's disease (AD), mild cognitive impairment (MCI) has high chance to convert to AD. Effective prediction of such conversion from MCI to AD is of great importance for early diagnosis of AD and also for evaluating AD risk pre-symptomatically. Unlike most previous methods that used only the samples from a target domain to train a classifier, in this paper, we propose a novel multimodal manifold-regularized transfer learning (M2TL) method that jointly utilizes samples from another domain (e.g., AD vs. normal controls (NC)) as well as unlabeled samples to boost the performance of the MCI conversion prediction. Specifically, the proposed M2TL method includes two key components. The first one is a kernel-based maximum mean discrepancy criterion, which helps eliminate the potential negative effect induced by the distributional difference between the auxiliary domain (i.e., AD and NC) and the target domain (i.e., MCI converters (MCI-C) and MCI non-converters (MCI-NC)). The second one is a semi-supervised multimodal manifold-regularized least squares classification method, where the target-domain samples, the auxiliary-domain samples, and the unlabeled samples can be jointly used for training our classifier. Furthermore, with the integration of a group sparsity constraint into our objective function, the proposed M2TL has a capability of selecting the informative samples to build a robust classifier. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database validate the effectiveness of the proposed method by significantly improving the classification accuracy of 80.1 % for MCI conversion prediction, and also outperforming the state-of-the-art methods.

Beyond Lumping and Splitting: A Review of Computational Approaches for Stratifying Psychiatric Disorders

Heterogeneity is a key feature of all psychiatric disorders that manifests on many levels, including symptoms, disease course, and biological underpinnings. These form a substantial barrier to understanding disease mechanisms and developing effective, personalized treatments. In response, many studies have aimed to stratify psychiatric disorders, aiming to find more consistent subgroups on the basis of many types of data. Such approaches have received renewed interest after recent research initiatives, such as the National Institute of Mental Health Research Domain Criteria and the European Roadmap for Mental Health Research, both of which emphasize finding stratifications that are based on biological systems and that cut across current classifications. We first introduce the basic concepts for stratifying psychiatric disorders and then provide a methodologically oriented and critical review of the existing literature. This shows that the predominant clustering approach that aims to subdivide clinical populations into more coherent subgroups has made a useful contribution but is heavily dependent on the type of data used; it has produced many different ways to subgroup the disorders we review, but for most disorders it has not converged on a consistent set of subgroups. We highlight problems with current approaches that are not widely recognized and discuss the importance of validation to ensure that the derived subgroups index clinically relevant variation. Finally, we review emerging techniques-such as those that estimate normative models for mappings between biology and behavior-that provide new ways to parse the heterogeneity underlying psychiatric disorders and evaluate all methods to meeting the objectives of such as the National Institute of Mental Health Research Domain Criteria and Roadmap for Mental Health Research.

Independent Component Analysis-Support Vector Machine-Based Computer-Aided Diagnosis System for Alzheimer's with Visual Support

Computer-aided diagnosis (CAD) systems constitute a powerful tool for early diagnosis of Alzheimer's disease (AD), but limitations on interpretability and performance exist. In this work, a fully automatic CAD system based on supervised learning methods is proposed to be applied on segmented brain magnetic resonance imaging (MRI) from Alzheimer's disease neuroimaging initiative (ADNI) participants for automatic classification. The proposed CAD system possesses two relevant characteristics: optimal performance and visual support for decision making. The CAD is built in two stages: a first feature extraction based on independent component analysis (ICA) on class mean images and, secondly, a support vector machine (SVM) training and classification. The obtained features for classification offer a full graphical representation of the images, giving an understandable logic in the CAD output, that can increase confidence in the CAD support. The proposed method yields classification results up to 89% of accuracy (with 92% of sensitivity and 86% of specificity) for normal controls (NC) and AD patients, 79% of accuracy (with 82% of sensitivity and 76% of specificity) for NC and mild cognitive impairment (MCI), and 85% of accuracy (with 85% of sensitivity and 86% of specificity) for MCI and AD patients.

A Novel Grading Biomarker for the Prediction of Conversion From Mild Cognitive Impairment to Alzheimer's Disease

OBJECTIVE

Identifying mild cognitive impairment (MCI) subjects who will progress to Alzheimer's disease (AD) is not only crucial in clinical practice, but also has a significant potential to enrich clinical trials. The purpose of this study is to develop an effective biomarker for an accurate prediction of MCI-to-AD conversion from magnetic resonance images.

METHODS

We propose a novel grading biomarker for the prediction of MCI-to-AD conversion. First, we comprehensively study the effects of several important factors on the performance in the prediction task including registration accuracy, age correction, feature selection, and the selection of training data. Based on the studies of these factors, a grading biomarker is then calculated for each MCI subject using sparse representation techniques. Finally, the grading biomarker is combined with age and cognitive measures to provide a more accurate prediction of MCI-to-AD conversion.

RESULTS

Using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, the proposed global grading biomarker achieved an area under the receiver operating characteristic curve (AUC) in the range of 79-81% for the prediction of MCI-to-AD conversion within three years in tenfold cross validations. The classification AUC further increases to 84-92% when age and cognitive measures are combined with the proposed grading biomarker.

CONCLUSION

The obtained accuracy of the proposed biomarker benefits from the contributions of different factors: a tradeoff registration level to align images to the template space, the removal of the normal aging effect, selection of discriminative voxels, the calculation of the grading biomarker using AD and normal control groups, and the integration of sparse representation technique and the combination of cognitive measures.

SIGNIFICANCE

The evaluation on the ADNI dataset shows the efficacy of the proposed biomarker and demonstrates a significant contribution in accurate prediction of MCI-to-AD conversion.