Katherine R. Gray

Random forest-based similarity measures for multi-modal classification of Alzheimer's disease

Neurodegenerative disorders, such as Alzheimers disease, are associated with changes in multiple neuroimaging and biological measures. These may provide complementary information for diagnosis and prognosis. We present a multi-modality classification framework in which manifolds are constructed based on pairwise similarity measures derived from random forest classifiers. Similarities from multiple modalities are combined to generate an embedding that simultaneously encodes information about all the available features. Multi-modality classification is then performed using coordinates from this joint embedding. We evaluate the proposed framework by application to neuroimaging and biological data from the Alzheimers Disease Neuroimaging Initiative (ADNI). Features include regional MRI volumes, voxel-based FDG-PET signal intensities, CSF biomarker measures, and categorical genetic information. Classification based on the joint embedding constructed using information from all four modalities out-performs the classification based on any individual modality for comparisons between Alzheimers disease patients and healthy controls, as well as between mild cognitive impairment patients and healthy controls. Based on the joint embedding, we achieve classification accuracies of 89% between Alzheimers disease patients and healthy controls, and 75% between mild cognitive impairment patients and healthy controls. These results are comparable with those reported in other recent studies using multi-kernel learning. Random forests provide consistent pairwise similarity measures for multiple modalities, thus facilitating the combination of different types of feature data. We demonstrate this by application to data in which the number of features differs by several orders of magnitude between modalities. Random forest classifiers extend naturally to multi-class problems, and the framework described here could be applied to distinguish between multiple patient groups in the future.

Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge

Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi-center data set. Using clinical practice as the starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimers disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with a total of 29 algorithms. The algorithms were trained on a small training set (n=30) and optionally on data from other sources (e.g., the Alzheimers Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.

Multi-region analysis of longitudinal FDG-PET for the classification of Alzheimer's disease.

Imaging biomarkers for Alzheimers disease are desirable for improved diagnosis and monitoring, as well as drug discovery. Automated image-based classification of individual patients could provide valuable diagnostic support for clinicians, when considered alongside cognitive assessment scores. We investigate the value of combining cross-sectional and longitudinal multi-region FDG-PET information for classification, using clinical and imaging data from the Alzheimers Disease Neuroimaging Initiative. Whole-brain segmentations into 83 anatomically defined regions were automatically generated for baseline and 12-month FDG-PET images. Regional signal intensities were extracted at each timepoint, as well as changes in signal intensity over the follow-up period. Features were provided to a support vector machine classifier. By combining 12-month signal intensities and changes over 12 months, we achieve significantly increased classification performance compared with using any of the three feature sets independently. Based on this combined feature set, we report classification accuracies of 88% between patients with Alzheimers disease and elderly healthy controls, and 65% between patients with stable mild cognitive impairment and those who subsequently progressed to Alzheimers disease. We demonstrate that information extracted from serial FDG-PET through regional analysis can be used to achieve state-of-the-art classification of diagnostic groups in a realistic multi-centre setting. This finding may be usefully applied in the diagnosis of Alzheimers disease, predicting disease course in individuals with mild cognitive impairment, and in the selection of participants for clinical trials.

Limited agreement between biomarkers of neuronal injury at different stages of Alzheimer's disease

New diagnostic criteria for Alzheimers disease (AD) treat different biomarkers of neuronal injury as equivalent. Here, we quantified the degree of agreement between hippocampal volume on structural magnetic resonance imaging, regional glucose metabolism on positron emission tomography, and levels of phosphorylated tau in cerebrospinal fluid (CSF) in 585 subjects from all phases of the AD Neuroimaging Initiative. The overall chance‐corrected agreement was poor (Cohen κ, 0.24–0.34), in accord with a high rate of conflicting findings (26%–41%). Neither diagnosis nor APOE ε4 status significantly influenced the distribution of agreement between the biomarkers. The degree of agreement tended to be higher in individuals with abnormal versus normal CSF β‐amyloid (Aβ1‐42) levels. Prospective diagnostic criteria for AD should address the relative importance of markers of neuronal injury and elaborate a way of dealing with conflicting biomarker findings.

Random forest-based manifold learning for classification of imaging data in dementia

Neurodegenerative disorders are characterized by changes in multiple biomarkers, which may provide complementary information for diagnosis and prognosis. We present a framework in which proximities derived from random forests are used to learn a low-dimensional manifold from labelled training data and then to infer the clinical labels of test data mapped to this space. The proposed method facilitates the combination of embeddings from multiple datasets, resulting in the generation of a joint embedding that simultaneously encodes information about all the available features. It is possible to combine different types of data without additional processing, and we demonstrate this key feature by application to voxel-based FDG-PET and region-based MR imaging data from the ADNI study. Classification based on the joint embedding coordinates out-performs classification based on either modality alone. Results are impressive compared with other state-of-the-art machine learning techniques applied to multi-modality imaging data.

Multi-modal classification of Alzheimer's disease using nonlinear graph fusion

Abstract Accurate diagnosis of Alzheimers disease (AD) and its prodromal stage mild cognitive impairment (MCI) is of great interest to patients and clinicians. Recent studies have demonstrated that multiple neuroimaging and biological measures contain complementary information for diagnosis and prognosis. Classification methods are needed to combine these multiple biomarkers to provide an accurate diagnosis. State-of-the-art approaches calculate a mixed kernel or a similarity matrix by linearly combining kernels or similarities from multiple modalities. However, the complementary information from multi-modal data are not necessarily linearly related. In addition, this linear combination is also sensitive to the weights assigned to each modality. In this paper, we present a multi-modality classification framework to efficiently exploit the complementarity in the multi-modal data. First, pairwise similarity is calculated for each modality individually using the features including regional MRI volumes, voxel-based FDG-PET signal intensities, CSF biomarker measures, and categorical genetic information. Similarities from multiple modalities are then combined in a nonlinear graph fusion process, which generates a unified graph for final classification. Based on the unified graphs, we achieved classification area under curve (AUC) of receiver-operator characteristic of 98.1% between AD subjects and normal controls (NC), 82.4% between MCI subjects and NC and 77.9% in a three-way classification, which are significantly better than those using single-modality biomarkers and those based on state-of-the-art linear combination approaches.

Regional analysis of FDG-PET for use in the classification of Alzheimer'S Disease

We present the first use of multi-region FDG-PET data for classification of subjects from the Alzheimers Disease Neuroimaging Initiative. Image data were obtained from 69 healthy controls, 71 AD patients, and 147 patients with a baseline diagnosis of MCI. Anatomical segmentations were automatically generated in the native MRI-space of each subject, and the mean signal intensity per cubic millimetre in each region was extracted from the FDG-PET images. Using a support vector machine classifier, we achieve excellent discrimination between AD patients and HC (accuracy 82%), and good discrimination between MCI patients and HC (accuracy 70%). Using FDG-PET, a technique which is often used clinically in the workup of dementia patients, we achieve results which are comparable with those obtained using data from research-quality MRI, or biomarkers obtained invasively from the cerebrospinal fluid.

Enrichment of clinical trials in MCI due to AD using markers of amyloid and neurodegeneration

Objective: To investigate the effect of enriching mild cognitive impairment (MCI) clinical trials using combined markers of amyloid pathology and neurodegeneration. Methods: We evaluate an implementation of the recent National Institute for Aging–Alzheimers Association (NIA-AA) diagnostic criteria for MCI due to Alzheimer disease (AD) as inclusion criteria in clinical trials and assess the effect of enrichment with amyloid (A+), neurodegeneration (N+), and their combination (A+N+) on the rate of clinical progression, required sample sizes, and estimates of trial time and cost. Results: Enrichment based on an individual marker (A+ or N+) substantially improves all assessed trial characteristics. Combined enrichment (A+N+) further improves these results with a reduction in required sample sizes by 45% to 60%, depending on the endpoint. Conclusions: Operationalizing the NIA-AA diagnostic criteria for clinical trial screening has the potential to substantially improve the statistical power of trials in MCI due to AD by identifying a more rapidly progressing patient population.

Nonlinear Graph Fusion for Multi-modal Classification of Alzheimer's Disease

Recent studies have demonstrated that biomarkers from multiple modalities contain complementary information for the diagnosis of Alzheimers disease AD and its prodromal stage mild cognitive impairment MCI. In order to fuse data from multiple modalities, most previous approaches calculate a mixed kernel or a similarity matrix by linearly combining kernels or similarities from multiple modalities. However, the complementary information from multi-modal data are not necessarily linearly related. In addition, this linear combination is also sensitive to the weights assigned to each modality. In this paper, we propose a nonlinear graph fusion method to efficiently exploit the complementarity in the multi-modal data for the classification of AD. Specifically, a graph is first constructed for each modality individually. Afterwards, a single unified graph is obtained via a nonlinear combination of the graphs in an iterative cross diffusion process. Using the unified graphs, we achieved classification accuracies of 91.8% between AD subjects and normal controls NC, 79.5% between MCI subjects and NC and 60.2% in a three-way classification, which are competitive with state-of-the-art results.

INTEGRATION OF EADC-ADNI HARMONISED HIPPOCAMPUS LABELS INTO THE LEAP AUTOMATED SEGMENTATION TECHNIQUE

IC-P-221 INTEGRATION OF EADC-ADNI HARMONISED HIPPOCAMPUS LABELS INTO THE LEAP AUTOMATED SEGMENTATION TECHNIQUE Katherine Rachel Gray, Mark Austin, Robin Wolz, Kate McLeish, Marina Boccardi, Giovanni Frisoni, Derek Hill, IXICO plc, London, United Kingdom; IXICO plc, London, United Kingdom; IRCCS Centro San Giovanni di Dio Fatebenefratelli, Brescia, Italy. Contact e-mail: katherine.gray03@imperial.ac.uk