Sidong Liu

Multimodal Neuroimaging Feature Learning for Multiclass Diagnosis of Alzheimer's Disease

The accurate diagnosis of Alzheimers disease (AD) is essential for patient care and will be increasingly important as disease modifying agents become available, early in the course of the disease. Although studies have applied machine learning methods for the computer-aided diagnosis of AD, a bottleneck in the diagnostic performance was shown in previous methods, due to the lacking of efficient strategies for representing neuroimaging biomarkers. In this study, we designed a novel diagnostic framework with deep learning architecture to aid the diagnosis of AD. This framework uses a zero-masking strategy for data fusion to extract complementary information from multiple data modalities. Compared to the previous state-of-the-art workflows, our method is capable of fusing multimodal neuroimaging features in one setting and has the potential to require less labeled data. A performance gain was achieved in both binary classification and multiclass classification of AD. The advantages and limitations of the proposed framework are discussed.

Early diagnosis of Alzheimer's disease with deep learning

The accurate diagnosis of Alzheimers disease (AD) plays a significant role in patient care, especially at the early stage, because the consciousness of the severity and the progression risks allows the patients to take prevention measures before irreversible brain damages are shaped. Although many studies have applied machine learning methods for computer-aided-diagnosis (CAD) of AD recently, a bottleneck of the diagnosis performance was shown in most of the existing researches, mainly due to the congenital limitations of the chosen learning models. In this study, we design a deep learning architecture, which contains stacked auto-encoders and a softmax output layer, to overcome the bottleneck and aid the diagnosis of AD and its prodromal stage, Mild Cognitive Impairment (MCI). Compared to the previous workflows, our method is capable of analyzing multiple classes in one setting, and requires less labeled training samples and minimal domain prior knowledge. A significant performance gain on classification of all diagnosis groups was achieved in our experiments.

3D neurological image retrieval with localized pathology-centric CMRGlc patterns

Functional neuroimaging has an important role in non-invasive diagnosis of neurodegenerative disorders. There are now large volumes of imaging data generated by functional imaging technologies and so there is a need to efficiently manage and retrieve these data. In this paper, we propose a new scheme for efficient 3D content-based neurological image retrieval. 3D pathology-centric masks were adaptively designed and applied for extracting CMRGlc (cerebral metabolic rate of glucose consumption) texture features with volumetric co-occurrence matrices from neurological FDG PET images. Our results, using 93 clinical dementia studies, show that our approach offers a robust and efficient retrieval mechanism for relevant clinical cases and provides advantages in image data analysis and management.

Multimodal neuroimaging computing: a review of the applications in neuropsychiatric disorders

Multimodal neuroimaging is increasingly used in neuroscience research, as it overcomes the limitations of individual modalities. One of the most important applications of multimodal neuroimaging is the provision of vital diagnostic data for neuropsychiatric disorders. Multimodal neuroimaging computing enables the visualization and quantitative analysis of the alterations in brain structure and function, and has reshaped how neuroscience research is carried out. Research in this area is growing exponentially, and so it is an appropriate time to review the current and future development of this emerging area. Hence, in this paper, we review the recent advances in multimodal neuroimaging (MRI, PET) and electrophysiological (EEG, MEG) technologies, and their applications to the neuropsychiatric disorders. We also outline some future directions for multimodal neuroimaging where researchers will design more advanced methods and models for neuropsychiatric research.

Localized functional neuroimaging retrieval using 3D discrete curvelet transform

Neuroimaging is a fundamental component of the neurological diagnosis. The greatly increased volume and complexity of neuroimaging datasets has created a need for efficient image management and retrieval. In this paper, we advance a content-based retrieval framework for 3D functional neuroimaging data based on 3D curvelet transforms. The localized volumetric texture feature was extracted by a 3D digital curvelet transform from parametric image of cerebral metabolic rate of glucose consumption with a set of adaptive disorder-oriented masks for each type of neurological disorder. The results, using 142 clinical dementia studies, show that our proposed approach supports efficient and high performance neuroimaging data retrieval.

Multi-Channel neurodegenerative pattern analysis and its application in Alzheimer's disease characterization.

Neuroimaging has played an important role in non-invasive diagnosis and differentiation of neurodegenerative disorders, such as Alzheimers disease and Mild Cognitive Impairment. Various features have been extracted from the neuroimaging data to characterize the disorders, and these features can be roughly divided into global and local features. Recent studies show a tendency of using local features in disease characterization, since they are capable of identifying the subtle disease-specific patterns associated with the effects of the disease on human brain. However, problems arise if the neuroimaging database involved multiple disorders or progressive disorders, as disorders of different types or at different progressive stages might exhibit different degenerative patterns. It is difficult for the researchers to reach consensus on what brain regions could effectively distinguish multiple disorders or multiple progression stages. In this study we proposed a Multi-Channel pattern analysis approach to identify the most discriminative local brain metabolism features for neurodegenerative disorder characterization. We compared our method to global methods and other pattern analysis methods based on clinical expertise or statistics tests. The preliminary results suggested that the proposed Multi-Channel pattern analysis method outperformed other approaches in Alzheimers disease characterization, and meanwhile provided important insights into the underlying pathology of Alzheimers disease and Mild Cognitive Impairment.

A supervised multiview spectral embedding method for neuroimaging classification

The multi-view/multi-modal features are commonly used in neuroimaging classification because they could provide complementary information to each other and thus result in better classification performance than single-view features. However, it is very challenging to effectively integrate such rich features, since straightforward concatenation or singleview spectral embedding methods rarely leads to physically meaningful integration. In this paper, we present a supervised multi-view/multi-modal spectral embedding method (SMSE) for neuroimaging classification. This method embeds the high dimensional multi-view features derived from multi-modal neuroimaging data into a low dimensional feature space and preserves the optimal local embeddings among different views. The proposed SMSE algorithm, validated using three groups of neuroimaging data, is able to achieve significant classification improvement over the state-of-the-art multi-view spectral embedding methods.

Multi-Channel brain atrophy pattern analysis in neuroimaging retrieval

The high throughput 3D neuroimaging datasets have posed great challenges for neuroimaging data retrieval. To achieve more accurate neuroimaging retrieval, various content-based retrieval approaches have been proposed. Recent studies showed a tendency of using the localized features extracted from a subset of the brain structures, instead of the global features extracted from whole brain. However, these studies relied heavily on specific pattern analysis techniques or clinical expertise. In this study we proposed a Multi-Channel pattern analysis approach to identify the most discriminative disease-sensitive brain structures for neurodegenerative disorders and thus to enhance neuroimaging retrieval. The preliminary results suggested that the proposed Multi-Channel pattern analysis approach could confidently identify the brain structures with atrophy and further improve the neuroimaging retrieval performance.

Multifold Bayesian Kernelization in Alzheimer’s Diagnosis

The accurate diagnosis of Alzheimers Disease (AD) and Mild Cognitive Impairment (MCI) is important in early dementia detection and treatment planning. Most of current studies formulate the AD diagnosis scenario as a classification problem and solve it using various machine learners trained with multi-modal biomarkers. However, the diagnosis accuracy is usually constrained by the performance of the machine learners as well as the methods of integrating the multi-modal data. In this study, we propose a novel diagnosis algorithm, the Multifold Bayesian Kernelization (MBK), which models the diagnosis process as a synthesis analysis of multi-modal biomarkers. MBK constructs a kernel for each biomarker that maximizes the local neighborhood affinity, and further evaluates the contribution of each biomarker based on a Bayesian framework. MBK adopts a novel diagnosis scheme that could infer the subjects diagnosis by synthesizing the output diagnosis probabilities of individual biomarkers. The proposed algorithm, validated using multimodal neuroimaging data from the ADNI baseline cohort with 85 AD, 169 MCI and 77 cognitive normal subjects, achieves significant improvements on all diagnosis groups compared to the state-of-the-art methods.

Generalized regional disorder-sensitive-weighting scheme for 3D neuroimaging retrieval

3D functional neuroimaging is used in the diagnosis and management of neurological disorders. The efficient management and analysis of these large imaging datasets has prompted research in the field of content-based image retrieval. In this context, our generalized regional disorder-sensitive-weighting (DSW) scheme gives greater weight to brain regions affected by the diseases than regions that are relatively spared. We used two DSW matrices; one matrix is based on the occurrence maps that highlight abnormal functional regions; the other is based on the regional Fisher discriminant ratio. Our results suggest that our DSW matrices enhance neuroimaging data retrieval and provide a flexible weighting solution for the clinical analysis of different types of neurological disorders.