The random Fourier features (RFFs) method is a powerful and popular technique in kernel approximation for scalability of kernel methods. The theoretical foundation of RFFs is based on the Bochner theorem (Bochner, 200...
详细信息
Non-rigid registration is essential for a wide range of clinical applications, such as intraoperative image-guidance and postoperative follow-up assessment, and longitudinal image analysis for disease diagnosis and mo...
详细信息
ISBN:
(数字)9781728141640
ISBN:
(纸本)9781728141657
Non-rigid registration is essential for a wide range of clinical applications, such as intraoperative image-guidance and postoperative follow-up assessment, and longitudinal image analysis for disease diagnosis and monitoring. Vascular structures are a rich descriptor of the organ deformation, since it permeates through all organs within body. As vasculature differs in size, shape and topology, following surgical intervention/treatment or due to disease progression, non-rigid vessel matching remains a challenging task. Recently, hybrid mixture models (HdMM) have been applied to tackle this challenge, and demonstrate significant improvements in terms of accuracy and robustness relative to the state-of-the-art. However, the smoothness constraint enforced on the deformation field with this approach only accounts for the global topology of the vasculature, resulting in a reduced capacity to accurately match localized changes to vascular structures, and preserve local topology. In this work, we proposed a modified version of HdMM by formulating an adaptive kernel, to enforce a local smoothness constraint on the deformation field, henceforth referred to as HdMMad. The proposed HdMMad framework is evaluated with cerebral and pulmonary vasculature, acquired retrospectively. The registration results for both data sets demonstrate that the proposed approach outperforms registration algorithms also designed to preserve local topology. Using HdMMad, around 80% of the initial registration error was reduced, for both data sets.
—In clinical practice, electroencephalography (EEG) plays an important role in the diagnosis of epilepsy. EEG-based computer-aided diagnosis of epilepsy can greatly improve the accuracy of epilepsy detection while re...
详细信息
An efficient image denoising algorithm is introduced. Firstly, image pixels are classified into noisy pixels and noise-free pixels by four directional operators. Then an adaptive weighted median filter is designed to ...
详细信息
An efficient image denoising algorithm is introduced. Firstly, image pixels are classified into noisy pixels and noise-free pixels by four directional operators. Then an adaptive weighted median filter is designed to remove and restore the detected noisy pixels and keep the noise-free ones unchanged. Experimental results indicate that the proposed algorithm preserves image details well while removing impulsive noise efficiently, and its filtering performance is significantly superior to the classical median filter and some other typical and recently developed improved median filters.
Cardiovascular diseases are the most common cause of mortality worldwide. Detection of atrial fibrillation (AF) in the asymptomatic stage can help prevent strokes. It also improves clinical decision making through the...
详细信息
In this paper, we develop a quadrature framework for large-scale kernel machines via a numerical integration representation. Considering that the integration domain and measure of typical kernels, e.g., Gaussian kerne...
详细信息
The blind source separation (BSS) is an important task for numerous applications in signal processing, communications and array processing. But for many complex sources blind separation algorithms are not efficient be...
详细信息
The blind source separation (BSS) is an important task for numerous applications in signal processing, communications and array processing. But for many complex sources blind separation algorithms are not efficient because the probability distribution of the sources cannot be estimated accurately. So in this paper, to justify the ME(maximum enteropy) approach, the relation between the ME and the MMI(minimum mutual information) is elucidated first. Then a novel algorithm that uses Gaussian mixture density to approximate the probability distribution of the sources is presented based on the ME approach. The experiment of the BSS of ship-radiated noise demonstrates that the proposed algorithm is valid and efficient.
Different modalities in biomedical images, like CT, MRI and PET scanners, provide detailed cross-sectional views of human anatomy. This paper introduces three-dimensional brain reconstruction based on CT slices. It co...
详细信息
Different modalities in biomedical images, like CT, MRI and PET scanners, provide detailed cross-sectional views of human anatomy. This paper introduces three-dimensional brain reconstruction based on CT slices. It contains filtering, fuzzy segmentation, matching method of contours, cell array structure and image animation. Experimental results have shown its validity. The innovation is matching method of contours and fuzzy segmentation algorithm of CT slices.
A semantics-based pre-fetching model is presented. This model predicts future requests based on latent intention that the user's current access path implies in semantics, rather than on temporal relationships, whi...
详细信息
A semantics-based pre-fetching model is presented. This model predicts future requests based on latent intention that the user's current access path implies in semantics, rather than on temporal relationships, which oversomes the limitation of previous pre-fetching approaches. The hidden Markov model (HMM) was employed for mining actual intention from access patterns. Experimental results show that the proposed pre-fetching model has better general performance.
Nowadays, with the high-speed iteration of convolution neural network, the efficient object detector emerges one after another. As an important branch of computer vision, object detection aims to detect where and what...
详细信息
Nowadays, with the high-speed iteration of convolution neural network, the efficient object detector emerges one after another. As an important branch of computer vision, object detection aims to detect where and what the object is. However, nowadays, many detector cannot extract abundant semantic information to discriminate the location and size of the objects, resulting in poor performance of the network. In this paper, a new module is proposed, named Abundant Semantic Information Module (ASIM), to enrich and expand the semantic information of the object with more and larger receptive fields. In ASIM, we blend the extracted feature maps to different degrees with different blending factors and fuse them so that all object information is given full attention. Compared to the baseline method, a wealth of experiments show that our module has achieved a significant performance improvement.
暂无评论