Search

Single-modal neuroimaging-based diagnosis for brain diseases is a main routine due to the lack of advanced imaging devices, especially in rural hospitals. Transfer learning (TL) has demonstrate edits effectiveness in improving the performance of a computer-aided diagnosis (CAD) system, which transfers knowledge from the model of a related imaging modality (source domain (SD)) to that of the diagnosis modality (target domain (TD)). Multiple empirical kernel learning machine (MEKLM) is a newly proposed classifier with superior performance to the conventional classifiers with implicit kernel mapping. In this work, we propose a novel projective model(PM) based sparse MEKLM(PM-SMEKLM) algorithm to learn a cross-domain transformation by PM in way of the parameter-based TL, and then apply it to the neuroimaging-based CAD for brain diseases. Sparse learning is integrated into MEKLM to further select effective information in SD for knowledge transfer and enhance the generalization ability of the classifier in TD. The projection matrix in PM and sparse representations in MEKLM are jointly learned, which effectively improves the performance of PM-SMEKLM. Three experiments are conducted on two neuroimaging datasets for the diagnosis of Alzheimer’s disease and Parkinson’s disease, respectively. Experimental results show that the proposed PM-SMEKLM algorithm outperforms all the compared algorithms.

Histopathological image analysis works as ‘gold standard’ for cancer diagnosis. Its computer-aided approach has attracted considerable attention in the field of digital pathology, which highly depends on the feature representation for histopathological images. The principal component analysis network (PCANet) is a novel unsupervised deep learning framework that has shown its effectiveness for feature representation learning. However, PCA is susceptible to noise and outliers to affect the performance of PCANet. The Grassmann average (GA) is superior to PCA on robustness. In this work, a GA network (GANet) algorithm is proposed by embedding GA algorithm into the PCANet framework. Moreover, since quaternion algebra is an excellent tool to represent color images, a quaternion-based GANet (QGANet) algorithm is further developed to learn effective feature representations containing color information for histopathological images. The experimental results based on three histopathological image datasets indicate that the proposed QGANet achieves the best performance on the classification of color histopathological images among all the compared algorithms.

Neuroimaging has shown its effectiveness for diagnosis of Parkinson's disease (PD), and the neuroimaging-based computer-aided diagnosis (CAD) then attracts considerable attention. In a CAD system, the classifier module is one of the key components, which directly decides the classification performance. As a newly proposed classifier, the large margin distribution machine (LDM) has excellent generalization by maximizing the margin mean and minimizing the margin variance simultaneously. However, LDM still suffers from the problem of kernel selection. In this work, we propose a deep neural mapping large margin distribution machine (DNMLDM) algorithm by adopting the deep neural network (DNN) to perform a kernel mapping instead of the implicit kernel function in LDM. A two-stage joint training strategy is then developed, including the unsupervised layer-wise pre-training for DNN and then the supervised fine-tuning for all parameters in the whole networks. Two real-world PD datasets, namely the transcranial sonography (TCS) dataset and the magnetic resonance imaging (MRI) dataset, are used to evaluate the performance of DNMLDM algorithm. The experimental results show that the proposed DNMLDM outperforms all the compared algorithms on both datasets.

In this paper, we propose a sparse quadratic kernel-free least squares semi-supervised support vector machine model by adding an L1 norm regularization term to the objective function and using the least squares method, which results in a nonconvex and nonsmooth quadratic programming problem. For computational considerations, we use the smoothing technique and consensus technique. Then we adopt the proximal alternating direction method of multipliers (P-ADMM) to solve it, as well as propose a strategy of parameter selection. Then we not only derive the convergence analysis of algorithm, but also estimate the convergence rate as o ( 1 / k ) , where k is the number of iteration. This gives the best bound of P-ADMM known so far for nonconvex consensus problem. To demonstrate the efficiency of our model, we compare the proposed method with several state-of-the-art methods. The numerical results show that our model can achieve both better accuracy and sparsity.

The bimodal ultrasound, namely B-mode ultrasound (BUS) and elastography ultrasound (EUS), provide complementary information to improve the diagnostic accuracy of breast cancers. However, in clinical practice, it is easier to acquire the labeled BUS images than the paired bimodal ultrasound data with shared labels due to the lack of EUS devices, especially in many rural hospitals. Thus, the single-modal BUS-based computer-aided diagnosis (CAD) generally has wide applications. Transfer learning (TL) can promote a BUS-based CAD model by transferring additional knowledge from EUS modality. To make full use of labeled paired bimodal data and the additional single-modal BUS images for knowledge transfer, a novel doubly supervised parameter transfer classifier (DSPTC) is proposed to well handle the TL between imbalanced modalities with the guidance of label information. Specifically, the proposed DSPTC consists of two loss functions corresponding to the paired bimodal ultrasound data with shared labels and the unpaired images with different labels, respectively. The former uses the loss function in the specially designed TL paradigm of support vector machine plus, while the latter adopts the Hilbert-Schmidt Independence Criterion (HSIC) for knowledge transfer between the unpaired images, which consist of the single-modal BUS images and the EUS images from the paired bimodal data. Consequently, the doubly supervised knowledge transfer is implemented by way of parameter transfer in a unified optimization framework. Two experiments are designed to evaluate the proposed DSPTC for the ultrasound-based diagnosis of breast cancers. The experimental results indicate that DSPTC outperforms all the compared algorithms, suggesting its wide potential applications.

Deep learning has been successfully applied to the single-image super-resolution (SISR) task with superior performance in recent years. However, most convolutional neural network (CNN) based SR models have a large number of parameters to be optimized, which requires heavy computation and thereby limits their real-world applications. In this work, a novel lightweight SR network, named Adaptive Weighted Super-Resolution Network (LW-AWSRN), is proposed to address this issue. A novel local fusion block (LFB) is developed in LW-AWSRN for efficient residual learning, which consists of several stacked adaptive weighted residual units (AWRU) and a local residual fusion unit (LRFU). Moreover, an adaptive weighted multi-scale (AWMS) module is proposed to make full use of features for the reconstruction of HR images. The AWMS module includes several convolutions with multiple scales, and the redundancy scale branch can be removed according to the contribution of adaptive weights for the lightweight network. The experimental results on the commonly used datasets show that the proposed LW-AWSRN achieves superior performance on × 2, × 3, × 4, and × 8 scale factors compared to state-of-the-art methods with similar parameters and computational overhead. It suggests that LW-AWSRN has a better trade-off between reconstruction quality and model size.

In this paper, numerical methods to compute the Karcher means on the n-order rotation group SO(n) are considered. First, after recalling Karcher means as solutions of a kind of minimization problems on SO(n), a super-linearly convergent numerical method, namely conjugate gradient method, has been used to deal with them. By the geometric structure of SO(n), the proposed algorithm is structure preserving. Then, a variety of numerical experiments are presented to demonstrate the performance and efficiency of the proposed algorithm by comparing with a recent structure preserving method.

Multi-scale PCA framework is proposed for filtering the virus images.A multi-scale CLBP descriptor is developed to extract the features.Images are classified by the SVM with polynomial kernel and the MPMC features.Experiments show that the proposed method is better than the conventional methods. Virus image classification is an important issue in clinical virology, highly accurate algorithm of automatic virus image classification is very helpful. In this paper, instead of extracting virus feature from the original image, we propose a novel method that extracts the virus feature from the filtered images by multi-scale principal component analysis (PCA). Firstly, multi-scale PCA filters are learned from all original images in the data set. Secondly, the original images are convolved with the learned filters. Therefore, the filtered images can capture the principal texture information from different perspectives. Then, the completed local binary pattern (CLBP) descriptor is firstly utilized to depict the features of all filtered virus images. The multi-scale CLBP features extracted from filtered images by multi-scale PCA are combined as the feature MPMC (Multi-scale PCA and Multi-scale CLBP), which is proposed in this paper. Finally, support vector machine (SVM) with polynomial kernel is used for classification. Experiments show that the classification accuracy based on MPMC outperforms the previous methods in the literature for the same virus image data set.

Thin-plate spline for robust point matching (TPS-RPM) algorithm is a famous and widely used approach in nonlinear shape registration. In this paper, we improve this approach by adopting an alternatively iterative strategy of globally affine and locally nonlinear registration. Concretely, in the affine registration step, we apply the Lie group parameterization method to globally align two shapes to assume the global similarity. In which, some suitable constraints are introduced to improve the robustness of algorithm. Then, in the locally nonlinear deformation step, we apply the thin-plate spline approach. By alternatively iterating these two steps, the proposed method not only preserves the advantages of spline methods, but also overcomes an overmatching phenomenon in shape registration. Finally, we test the proposed method on several conventional data sets with comparison of TPS-RPM. The experimental results validate that our method is really effective for nonlinear shape registration as well as more robust.

Normalizing all images in a large data set into a common space is a key step in many clinical and research studies, e.g., for brain development, maturation, and aging. Recently, groupwise registration has been developed for simultaneous alignment of all images without selecting a particular image as template, thus potentially avoiding bias in the registration. However, most conventional groupwise registration methods do not explore the data distribution during the image registration. Thus, their performance could be affected by large inter-subject variations in the data set under registration. To solve this potential issue, we propose to use a graph to model the distribution of all image data sitting on the image manifold, with each node representing an image and each edge representing the geodesic pathway between two nodes (or images). Then, the procedure of warping all images to their population center turns to the dynamic shrinking of the graph nodes along their graph edges until all graph nodes become close to each other. Thus, the topology of image distribution on the image manifold is always preserved during the groupwise registration. More importantly, by modeling the distribution of all images via a graph, we can potentially reduce registration error since every time each image is warped only according to its nearby images with similar structures in the graph. We have evaluated our proposed groupwise registration method on both infant and adult data sets, by also comparing with the conventional group-mean based registration and the ABSORB methods. All experimental results show that our proposed method can achieve better performance in terms of registration accuracy and robustness.

Point set registration is important for calibration of multiple cameras, 3D reconstruction and recognition, etc. The iterative closest point (ICP) algorithm is accurate and fast for point set registration in a same scale, but it does not handle the case with different scales. This paper instead introduces a novel approach named the scaling iterative closest point (SICP) algorithm which integrates a scale matrix with boundaries into the original ICP algorithm for scaling registration. At each iterative step of this algorithm, we set up correspondence between two m-D point sets, and then use a simple and fast iterative algorithm with the singular value decomposition (SVD) method and the properties of parabola incorporated to compute scale, rotation and translation transformations. The SICP algorithm has been proved to converge monotonically to a local minimum from any given parameters. Hence, to reach desired global minimum, good initial parameters are required which are successfully estimated in this paper by analyzing covariance matrices of point sets. The SICP algorithm is independent of shape representation and feature extraction, and thereby it is general for scaling registration of m-D point sets. Experimental results demonstrate its efficiency and accuracy compared with the standard ICP algorithm.

The traditional iterative closest point (ICP) algorithm is accurate and fast for rigid point set registration but it is unable to handle affine case. This paper instead introduces a novel generalized ICP algorithm based on lie group for affine registration of m-D point sets. First, with singular value decomposition technique applied, this paper decomposes affine transformation into three special matrices which are then constrained. Then, these matrices are expressed by exponential mappings of lie group and their Taylor approximations at each iterative step of affine ICP algorithm. In this way, affine registration problem is ultimately simplified to a quadratic programming problem. By solving this quadratic problem, the new algorithm converges monotonically to a local minimum from any given initial parameters. Hence, to reach desired minimum, good initial parameters and constraints are required which are successfully estimated by independent component analysis. This new algorithm is independent of shape representation and feature extraction, and thereby it is a general framework for affine registration of m-D point sets. Experimental results demonstrate its robustness and efficiency compared with the traditional ICP algorithm and the state-of-the-art methods.