Bibo Shi

Nonlinear feature transformation and deep fusion for Alzheimer's Disease staging analysis

Abstract In this study, we develop a novel nonlinear metric learning method to improve biomarker identification for Alzheimers Disease (AD) and Mild Cognitive Impairment (MCI). Formulated under a constrained optimization framework, the proposed method learns a smooth nonlinear feature space transformation that makes the mapped data more linearly separable for SVMs. The thin-plate spline (TPS) is chosen as the geometric model due to its remarkable versatility and representation power in generating sophisticated yet smooth deformations. In addition, a deep network based feature fusion strategy through stacked denoising sparse auto-encoder (DSAE) is adopted to integrate cross-sectional and longitudinal features estimated from MR brain images. Using the ADNI dataset, we evaluate the effectiveness of the proposed feature transformation and feature fusion strategies and demonstrate the improvements over the state-of-the-art solutions within the same category.

Quad-mesh based radial distance biomarkers for Alzheimer's disease

Detailed analysis of brain structures is essential in identifying anatomical biomarkers in Alzheimers disease (AD). In this paper, we develop a new radial distance model to compare different hippocampal shapes and measure their atrophies over time. Using harmonic mappings, we project hippocampal surfaces onto cylinders to obtain evenly-spaced quadrilateral meshes. Surface radial distances estimated via the quad-meshes are invariant to global shifts in the surrounding tissues, leading to a powerful way to detect localized anatomical progressions. The novel quad-meshing method also provides an efficient means to align anatomical surfaces across subjects. Through regions of interest (ROI) analysis, we extract discriminative patches of radial distance and atrophy, and utilize them as anatomical features for patient classification. The effectiveness of the proposed surface modeling and feature extraction strategies in identifying shape biomarkers for AD/MCI is evaluated using the ADNI dataset.

Nonlinear Metric Learning for Alzheimer's Disease Diagnosis with Integration of Longitudinal Neuroimaging Features.

Identifying neuroimaging biomarkers of Alzheimer’s disease (AD) is of great importance for diagnosis and prognosis of the disease. In this study, we develop a novel nonlinear metric learning method to improve biomarker identification for Alzheimer’s disease and its early stage Mild Cognitive Impairment (MCI). Formulated under a constrained optimization framework, the proposed method learns a smooth nonlinear feature space transformation that pulls the samples of the same class closer to each other while pushing different classes further away. The thin-plate spline (TPS) is chosen as the geometric model due to its remarkable versatility and representation power in accounting for sophisticated deformations. In addition, a multi-resolution patch-based feature selection strategy is proposed to extract both cross-sectional and longitudinal features from MR brain images. Using the ADNI dataset, we evaluate the effectiveness of the proposed metric learning and feature extraction strategies and demonstrate the improvements over the state-of-the-art solutions within the same category.

Nonlinear Metric Learning for Semi-Supervised Learning via Coherent Point Drifting

In this paper, we propose a nonlinear metric learning framework to boost the performance of semi-supervised learning (SSL) algorithms. Constructed on top of Laplacian SVM (LapSVM), the proposed method learns a smooth nonlinear feature space transformation that makes the input data points more linearly separable. Coherent point drifting (CPD) is utilized as the geometric model with the consideration of its remarkable expressive power in generating sophisticated yet smooth deformations. Our framework has broad applicability, and it can be integrated with many other SSL classifiers than LapSVM. Experiments performed on synthetic and real world datasets show the effectiveness of our CPD-LapSVM over the state-of-the-art metric learning solutions in SSL.

Nonlinear Feature Transformation and Deep Fusion for Alzheimer's Disease Staging Analysis

In this study, we develop a novel nonlinear metric learning method to improve biomarker identification for Alzheimers Disease AD and Mild Cognitive Impairment MCI. Formulated under a constrained optimization framework, the proposed method learns a smooth nonlinear feature space transformation that makes the input data points more linearly separable in SVMs. The thin-plate spline TPS is chosen as the geometric model due to its remarkable versatility and representation power in accounting for sophisticated deformations. In addition, a deep network based feature fusion strategy through stacked denoising sparse autoencoder DSAE is adopted to integrate cross-sectional and longitudinal features estimated from MR brain images. Using the ADNI dataset, we evaluate the effectiveness of the proposed feature transformation and feature fusion strategies and demonstrate the improvements over the state-of-the-art solutions within the same category.

Hippocampus segmentation through multi-view ensemble ConvNets

Automated segmentation of brain structures from MR images is an important practice in many neuroimage studies. In this paper, we explore the utilization of a multi-view ensemble approach that relies on neural networks (NN) to combine multiple decision maps in achieving accurate hippocampus segmentation. Constructed under a general convolutional NN structure, our Ensemble-Net networks explore different convolution configurations to capture the complementary information residing in the multiple label probabilities produced by our U-Seg-Net (a modified U-Net) segmentation neural network. T1-weighted MRI scans and the associated Hippocampal masks of 110 healthy subjects from the ADNI project were used as the training and testing data. The combined U-Seg-Net + Ensemble-Net framework achieves over 89% Dice ratio on the test dataset.

Distance-informed metric learning for Alzheimer's disease staging

Identifying intermediate biomarkers of Alzheimers disease (AD) is of great importance for diagnosis and prognosis of the disease. In this study, we develop a new AD staging method to classify patients into Normal Controls (NC), Mild Cognitive Impairment (MCI), and AD groups. Our solution employs a novel metric learning technique that improves classification rates through the guidance of some weak supervisory information in AD progression. More specifically, those information are in the form of pairwise constraints that specify the relative Mini Mental State Examination (MMSE) score disparity of two subjects, depending on whether they are in the same group or not. With the imposed constraints, the common knowledge that MCI generally sits in between of NC and AD can be integrated into the classification distance metric. Subjects from the Alzheimers Disease Neuroimaging Initiative cohort (ADNI; 56 AD, 104 MCI, 161 controls) were used to demonstrate the improvements made comparing with two state-of-the-art metric learning solutions: large margin nearest neighbors (LMNN) and relevant component analysis (RCA).

Accurate and Consistent Hippocampus Segmentation Through Convolutional LSTM and View Ensemble

In this work, a novel deep neural network is developed to automatically segment human hippocampi from MR images. To take advantage of the efficiency of 2D convolutional operations, as well the inter-slice dependence within 3D volumes, our model stacks fully convolutional neural networks (CNN) through convolutional long short-term memory (CLSTM) to extract voxel labels. Enhanced slice-wise label consistency is ensured, leading to improved segmentation stability and accuracy. We apply our model on ADNI dataset, and demonstrate that our proposed model outperforms the state-of-the-art solutions.

Can Occult Invasive Disease in Ductal Carcinoma In Situ Be Predicted Using Computer-extracted Mammographic Features?

RATIONALE AND OBJECTIVES This study aimed to determine whether mammographic features assessed by radiologists and using computer algorithms are prognostic of occult invasive disease for patients showing ductal carcinoma in situ (DCIS) only in core biopsy. MATERIALS AND METHODS In this retrospective study, we analyzed data from 99 subjects with DCIS (74 pure DCIS, 25 DCIS with occult invasion). We developed a computer-vision algorithm capable of extracting 113 features from magnification views in mammograms and combining these features to predict whether a DCIS case will be upstaged to invasive cancer at the time of definitive surgery. In comparison, we also built predictive models based on physician-interpreted features, which included histologic features extracted from biopsy reports and Breast Imaging Reporting and Data System-related mammographic features assessed by two radiologists. The generalization performance was assessed using leave-one-out cross validation with the receiver operating characteristic curve analysis. RESULTS Using the computer-extracted mammographic features, the multivariate classifier was able to distinguish DCIS with occult invasion from pure DCIS, with an area under the curve for receiver operating characteristic equal to 0.70 (95% confidence interval: 0.59-0.81). The physician-interpreted features including histologic features and Breast Imaging Reporting and Data System-related mammographic features assessed by two radiologists showed mixed results, and only one radiologists subjective assessment was predictive, with an area under the curve for receiver operating characteristic equal to 0.68 (95% confidence interval: 0.57-0.81). CONCLUSIONS Predicting upstaging for DCIS based upon mammograms is challenging, and there exists significant interobserver variability among radiologists. However, the proposed computer-extracted mammographic features are promising for the prediction of occult invasion in DCIS.

Adaptive multi-scale total variation minimization filter for low dose CT imaging

In this work we revisit TV filter and propose an improved version that is tailored to diagnostic CT purposes. We revise TV cost function, which results in symmetric gradient function that leads to more natural noise texture. We apply a multi-scale approach to resolve noise grain issue in CT images. We examine noise texture, granularity, and loss of low contrast in the test images. We also discuss potential acceleration by Nesterov and Conjugate Gradient methods.