Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI

A Deep Learning-Based Model for Classification of Different Subtypes of Subcortical Vascular Cognitive Impairment With FLAIR

Deep learning methods have shown their great capability of extracting high-level features from image and have been used for effective medical imaging classification recently. However, training samples of medical images are restricted by the amount of patients as well as medical ethics issues, making it hard to train the neural networks. In this paper, we propose a novel end-to-end three-dimensional (3D) attention-based residual neural network (ResNet) architecture to classify different subtypes of subcortical vascular cognitive impairment (SVCI) with single-shot T2-weighted fluid-attenuated inversion recovery (FLAIR) sequence. Our aim is to develop a convolutional neural network to provide a convenient and effective way to assist doctors in the diagnosis and early treatment of the different subtypes of SVCI. The experiment data in this paper are collected from 242 patients from the Neurology Department of Renji Hospital, including 78 amnestic mild cognitive impairment (a-MCI), 70 nonamnestic MCI (na-MCI), and 94 no cognitive impairment (NCI). The accuracy of our proposed model has reached 98.6% on a training set and 97.3% on a validation set. The test accuracy on an untrained testing set reaches 93.8% with robustness. Our proposed method can provide a convenient and effective way to assist doctors in the diagnosis and early treatment.

Generalizable, Reproducible, and Neuroscientifically Interpretable Imaging Biomarkers for Alzheimer's Disease

Precision medicine for Alzheimer's disease (AD) necessitates the development of personalized, reproducible, and neuroscientifically interpretable biomarkers, yet despite remarkable advances, few such biomarkers are available. Also, a comprehensive evaluation of the neurobiological basis and generalizability of the end-to-end machine learning system should be given the highest priority. For this reason, a deep learning model (3D attention network, 3DAN) that can simultaneously capture candidate imaging biomarkers with an attention mechanism module and advance the diagnosis of AD based on structural magnetic resonance imaging is proposed. The generalizability and reproducibility are evaluated using cross-validation on in-house, multicenter (n = 716), and public (n = 1116) databases with an accuracy up to 92%. Significant associations between the classification output and clinical characteristics of AD and mild cognitive impairment (MCI, a middle stage of dementia) groups provide solid neurobiological support for the 3DAN model. The effectiveness of the 3DAN model is further validated by its good performance in predicting the MCI subjects who progress to AD with an accuracy of 72%. Collectively, the findings highlight the potential for structural brain imaging to provide a generalizable, and neuroscientifically interpretable imaging biomarker that can support clinicians in the early diagnosis of AD.

Weakly Supervised Deep Learning for Brain Disease Prognosis Using MRI and Incomplete Clinical Scores

As a hot topic in brain disease prognosis, predicting clinical measures of subjects based on brain magnetic resonance imaging (MRI) data helps to assess the stage of pathology and predict future development of the disease. Due to incomplete clinical labels/scores, previous learning-based studies often simply discard subjects without ground-truth scores. This would result in limited training data for learning reliable and robust models. Also, existing methods focus only on using hand-crafted features (e.g., image intensity or tissue volume) of MRI data, and these features may not be well coordinated with prediction models. In this paper, we propose a weakly supervised densely connected neural network (wiseDNN) for brain disease prognosis using baseline MRI data and incomplete clinical scores. Specifically, we first extract multiscale image patches (located by anatomical landmarks) from MRI to capture local-to-global structural information of images, and then develop a weakly supervised densely connected network for task-oriented extraction of imaging features and joint prediction of multiple clinical measures. A weighted loss function is further employed to make full use of all available subjects (even those without ground-truth scores at certain time-points) for network training. The experimental results on 1469 subjects from both ADNI-1 and ADNI-2 datasets demonstrate that our proposed method can efficiently predict future clinical measures of subjects.

MRI Segmentation and Classification of Human Brain Using Deep Learning for Diagnosis of Alzheimer's Disease: A Survey

Many neurological diseases and delineating pathological regions have been analyzed, and the anatomical structure of the brain researched with the aid of magnetic resonance imaging (MRI). It is important to identify patients with Alzheimer's disease (AD) early so that preventative measures can be taken. A detailed analysis of the tissue structures from segmented MRI leads to a more accurate classification of specific brain disorders. Several segmentation methods to diagnose AD have been proposed with varying complexity. Segmentation of the brain structure and classification of AD using deep learning approaches has gained attention as it can provide effective results over a large set of data. Hence, deep learning methods are now preferred over state-of-the-art machine learning methods. We aim to provide an outline of current deep learning-based segmentation approaches for the quantitative analysis of brain MRI for the diagnosis of AD. Here, we report how convolutional neural network architectures are used to analyze the anatomical brain structure and diagnose AD, discuss how brain MRI segmentation improves AD classification, describe the state-of-the-art approaches, and summarize their results using publicly available datasets. Finally, we provide insight into current issues and discuss possible future research directions in building a computer-aided diagnostic system for AD.

Characterizing white matter connectivity in Alzheimer's disease and mild cognitive impairment: An automated fiber quantification analysis with two independent datasets

Alzheimer's disease (AD) is a chronic neurodegenerative disease characterized by progressive dementia. Diffusion tensor imaging (DTI) has been widely used to show structural integrity and delineate white matter (WM) degeneration in AD. The automated fiber quantification (AFQ) method is a fully automated approach that can rapidly and reliably identify major WM fiber tracts and evaluate WM properties. The main aim of this study was to assess WM integrity and abnormities in a cohort of patients with amnestic mild cognitive impairment (aMCI) and AD as well as normal controls (NCs). For this purpose, we first used AFQ to identify 20 major WM tracts and assessed WM integrity and abnormalities in a cohort of 120 subjects (39 NCs, 34 aMCI patients and 47 AD patients) in a discovery dataset and 122 subjects (43 NCs, 37 aMCI patients and 42 AD patients) in a replicated dataset. Pointwise differences along WM tracts were identified in the discovery dataset and simultaneously confirmed in the replicated dataset. Next, we investigated the utility of DTI measures along WM tracts as features to distinguish patients with AD from NCs via multilevel cross validation using a support vector machine. Correlation analysis revealed the identified microstructural WM alterations and classification output to be highly associated with cognitive ability in the patient groups, suggesting that they may be a robust biomarker of AD. This systematic study provides a pipeline to examine WM integrity and its potential clinical application in AD and may be useful for studying other neurological and psychiatric disorders.

[Coupled convolutional and graph network-based diagnosis of Alzheimer's disease using MRI]

OBJECTIVE

To propose a coupled convolutional and graph convolutional network (CCGCN) model for diagnosis of Alzheimer's disease (AD) and its prodromal stage.

METHODS

The disease-related brain regions generated by group-wise comparison were used as the input. The convolutional neural networks (CNNs) were used to extract disease-related features from different locations on brain magnetic resonance (MR) images. The generated features via the graph convolutional network (GCN) were processed, and graph pooling was performed to analyze the inherent relationship between the brain topology and the diagnosis task adaptively. Through ADNI dataset, we acquired the accuracy, sensitivity and specificity of the diagnosis tasks for AD and its prodromal stages, followed by an ablation study on the model structure.

RESULTS

The CCGCN model outperformed the current state-of-the-art methods and showed a classification accuracy of 92.5% for AD with a sensitivity of 88.1% and a specificity of 96.0%.

CONCLUSIONS

Based on the structural and topological features of the brain MR images, the proposed CCGCN model shows excellent performance in AD diagnosis and is expected to provide important assistance to physicians in disease diagnosis.

Imaging biomarkers in neurodegeneration: current and future practices

There is an increasing role for biological markers (biomarkers) in the understanding and diagnosis of neurodegenerative disorders. The application of imaging biomarkers specifically for the in vivo investigation of neurodegenerative disorders has increased substantially over the past decades and continues to provide further benefits both to the diagnosis and understanding of these diseases. This review forms part of a series of articles which stem from the University College London/University of Gothenburg course "Biomarkers in neurodegenerative diseases". In this review, we focus on neuroimaging, specifically positron emission tomography (PET) and magnetic resonance imaging (MRI), giving an overview of the current established practices clinically and in research as well as new techniques being developed. We will also discuss the use of machine learning (ML) techniques within these fields to provide additional insights to early diagnosis and multimodal analysis.

One-Shot Generative Adversarial Learning for MRI Segmentation of Craniomaxillofacial Bony Structures

Compared to computed tomography (CT), magnetic resonance imaging (MRI) delineation of craniomaxillofacial (CMF) bony structures can avoid harmful radiation exposure. However, bony boundaries are blurry in MRI, and structural information needs to be borrowed from CT during the training. This is challenging since paired MRI-CT data are typically scarce. In this paper, we propose to make full use of unpaired data, which are typically abundant, along with a single paired MRI-CT data to construct a one-shot generative adversarial model for automated MRI segmentation of CMF bony structures. Our model consists of a cross-modality image synthesis sub-network, which learns the mapping between CT and MRI, and an MRI segmentation sub-network. These two sub-networks are trained jointly in an end-to-end manner. Moreover, in the training phase, a neighbor-based anchoring method is proposed to reduce the ambiguity problem inherent in cross-modality synthesis, and a feature-matching-based semantic consistency constraint is proposed to encourage segmentation-oriented MRI synthesis. Experimental results demonstrate the superiority of our method both qualitatively and quantitatively in comparison with the state-of-the-art MRI segmentation methods.

Emphasis Learning, Features Repetition in Width Instead of Length to Improve Classification Performance: Case Study-Alzheimer's Disease Diagnosis

In the past decade, many studies have been conducted to advance computer-aided systems for Alzheimer's disease (AD) diagnosis. Most of them have recently developed systems concentrated on extracting and combining features from MRI, PET, and CSF. For the most part, they have obtained very high performance. However, improving the performance of a classification problem is complicated, specifically when the model's accuracy or other performance measurements are higher than 90%. In this study, a novel methodology is proposed to address this problem, specifically in Alzheimer's disease diagnosis classification. This methodology is the first of its kind in the literature, based on the notion of replication on the feature space instead of the traditional sample space. Briefly, the main steps of the proposed method include extracting, embedding, and exploring the best subset of features. For feature extraction, we adopt VBM-SPM; for embedding features, a concatenation strategy is used on the features to ultimately create one feature vector for each subject. Principal component analysis is applied to extract new features, forming a low-dimensional compact space. A novel process is applied by replicating selected components, assessing the classification model, and repeating the replication until performance divergence or convergence. The proposed method aims to explore most significant features and highest-preforming model at the same time, to classify normal subjects from AD and mild cognitive impairment (MCI) patients. In each epoch, a small subset of candidate features is assessed by support vector machine (SVM) classifier. This repeating procedure is continued until the highest performance is achieved. Experimental results reveal the highest performance reported in the literature for this specific classification problem. We obtained a model with accuracies of 98.81%, 81.61%, and 81.40% for AD vs. normal control (NC), MCI vs. NC, and AD vs. MCI classification, respectively.

Multi-modal latent space inducing ensemble SVM classifier for early dementia diagnosis with neuroimaging data

Fusing multi-modality data is crucial for accurate identification of brain disorder as different modalities can provide complementary perspectives of complex neurodegenerative disease. However, there are at least four common issues associated with the existing fusion methods. First, many existing fusion methods simply concatenate features from each modality without considering the correlations among different modalities. Second, most existing methods often make prediction based on a single classifier, which might not be able to address the heterogeneity of the Alzheimer's disease (AD) progression. Third, many existing methods often employ feature selection (or reduction) and classifier training in two independent steps, without considering the fact that the two pipelined steps are highly related to each other. Forth, there are missing neuroimaging data for some of the participants (e.g., missing PET data), due to the participants' "no-show" or dropout. In this paper, to address the above issues, we propose an early AD diagnosis framework via novel multi-modality latent space inducing ensemble SVM classifier. Specifically, we first project the neuroimaging data from different modalities into a latent space, and then map the learned latent representations into the label space to learn multiple diversified classifiers. Finally, we obtain the more reliable classification results by using an ensemble strategy. More importantly, we present a Complete Multi-modality Latent Space (CMLS) learning model for complete multi-modality data and also an Incomplete Multi-modality Latent Space (IMLS) learning model for incomplete multi-modality data. Extensive experiments using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset have demonstrated that our proposed models outperform other state-of-the-art methods.

Context-guided fully convolutional networks for joint craniomaxillofacial bone segmentation and landmark digitization

Cone-beam computed tomography (CBCT) scans are commonly used in diagnosing and planning surgical or orthodontic treatment to correct craniomaxillofacial (CMF) deformities. Based on CBCT images, it is clinically essential to generate an accurate 3D model of CMF structures (e.g., midface, and mandible) and digitize anatomical landmarks. This process often involves two tasks, i.e., bone segmentation and anatomical landmark digitization. Because landmarks usually lie on the boundaries of segmented bone regions, the tasks of bone segmentation and landmark digitization could be highly associated. Also, the spatial context information (e.g., displacements from voxels to landmarks) in CBCT images is intuitively important for accurately indicating the spatial association between voxels and landmarks. However, most of the existing studies simply treat bone segmentation and landmark digitization as two standalone tasks without considering their inherent relationship, and rarely take advantage of the spatial context information contained in CBCT images. To address these issues, we propose a Joint bone Segmentation and landmark Digitization (JSD) framework via context-guided fully convolutional networks (FCNs). Specifically, we first utilize displacement maps to model the spatial context information in CBCT images, where each element in the displacement map denotes the displacement from a voxel to a particular landmark. An FCN is learned to construct the mapping from the input image to its corresponding displacement maps. Using the learned displacement maps as guidance, we further develop a multi-task FCN model to perform bone segmentation and landmark digitization jointly. We validate the proposed JSD method on 107 subjects, and the experimental results demonstrate that our method is superior to the state-of-the-art approaches in both tasks of bone segmentation and landmark digitization.

End-to-End Dementia Status Prediction from Brain MRI Using Multi-task Weakly-Supervised Attention Network

Computer-aided prediction of dementia status (e.g., clinical scores of cognitive tests) from brain MRI is of great clinical value, as it can help assess pathological stage and predict disease progression. Existing learning-based approaches typically preselect dementia-sensitive regions from the whole-brain MRI for feature extraction and prediction model construction, which might be sub-optimal due to potential heterogeneities between different steps. Also, based on anatomical prior knowledge (e.g., brain atlas) and time-consuming nonlinear registration, these preselected brain regions are usually the same across all subjects, ignoring their individual specificities in dementia progression. In this paper, we propose a multi-task weakly-supervised attention network (MWAN) to jointly predict multiple clinical scores from the baseline MRI data, by explicitly considering individual specificities of different subjects. Leveraging a fully-trainable dementia attention block, our MWAN method can automatically identify subject-specific discriminative locations from the whole-brain MRI for end-to-end feature learning and multi-task regression. We evaluated our MWAN method by cross-validation on two public datasets (i.e., ADNI-1 and ADNI-2). Experimental results demonstrate that the proposed method performs well in both the tasks of clinical score prediction and weakly-supervised discriminative localization in brain MR images.

Deep Learning for Fast and Spatially Constrained Tissue Quantification From Highly Accelerated Data in Magnetic Resonance Fingerprinting

Magnetic resonance fingerprinting (MRF) is a quantitative imaging technique that can simultaneously measure multiple important tissue properties of human body. Although MRF has demonstrated improved scan efficiency as compared to conventional techniques, further acceleration is still desired for translation into routine clinical practice. The purpose of this paper is to accelerate MRF acquisition by developing a new tissue quantification method for MRF that allows accurate quantification with fewer sampling data. Most of the existing approaches use the MRF signal evolution at each individual pixel to estimate tissue properties, without considering the spatial association among neighboring pixels. In this paper, we propose a spatially constrained quantification method that uses the signals at multiple neighboring pixels to better estimate tissue properties at the central pixel. Specifically, we design a unique two-step deep learning model that learns the mapping from the observed signals to the desired properties for tissue quantification, i.e.: 1) with a feature extraction module for reducing the dimension of signals by extracting a low-dimensional feature vector from the high-dimensional signal evolution and 2) a spatially constrained quantification module for exploiting the spatial information from the extracted feature maps to generate the final tissue property map. A corresponding two-step training strategy is developed for network training. The proposed method is tested on highly undersampled MRF data acquired from human brains. Experimental results demonstrate that our method can achieve accurate quantification for T1 and T2 relaxation times by using only 1/4 time points of the original sequence (i.e., four times of acceleration for MRF acquisition).

Multi-task exclusive relationship learning for alzheimer's disease progression prediction with longitudinal data

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by progressive impairment of memory and other cognitive functions. Currently, many multi-task learning approaches have been proposed to predict the disease progression at the early stage using longitudinal data, with each task corresponding to a particular time point. However, the underlying association among different time points in disease progression is still under-explored in previous studies. To this end, we propose a multi-task exclusive relationship learning model to automatically capture the intrinsic relationship among tasks at different time points for estimating clinical measures based on longitudinal imaging data. The proposed method can select the most discriminative features for different tasks and also model the intrinsic relatedness among different time points, by utilizing an exclusive lasso regularization and a relationship induced regularization. Specifically, the exclusive lasso regularization enables partial group structure feature selection among the longitudinal data, while the relationship induced regularization efficiently introduces the relationship information from data to guide knowledge transfer. We further develop an efficient optimization algorithm to solve the proposed objective function. Extensive experiments on both synthetic and real datasets demonstrate the effectiveness of our proposed method. In comparison with several state-of-the-art methods, our proposed method can achieve promising performance for cognitive status prediction and also can help discover disease-related biomarkers.