Speckle Variance Photoacoustic Microscopy for Microhemodynamic Imaging.

Relying on the strong optical absorption of hemoglobin to pulsed laser energy, photoacoustic microscopy provides morphological and functional information on microvasculature label-freely. Here, we propose speckle variance photoacoustic microscopy (SV-PAM), which harnesses intrinsic imaging contrast from temporal-varied photoacoustic signals of moving red blood cells in blood vessels, for recovering three-dimension hemodynamic images down to capillary-level resolution within the microcirculatory tissue beds in vivo. Calculating the speckle variance of consecutive photoacoustic B-scan frames acquired at the same lateral position enables accurate identification of blood perfusion and occlusion, which provides interpretations of dynamic blood flow in the microvasculature, in addition to the microvascular anatomic structures. We demonstrate high-resolution hemodynamic imaging of vascular occlusion and reperfusion in the microvasculature of mice ears in vivo. The results suggest that our SV-PAM is potentially invaluable for biomedical hemodynamic investigations, for example, imaging ischemic stroke and hemorrhagic stroke.

Enhanced tensor low-rank representation learning for multi-view clustering.

Multi-view subspace clustering (MSC), assuming the multi-view data are generated from a latent subspace, has attracted considerable attention in multi-view clustering. To recover the underlying subspace structure, a successful approach adopted recently is subspace clustering based on tensor nuclear norm (TNN). But there are some limitations to this approach that the existing TNN-based methods usually fail to exploit the intrinsic cluster structure and high-order correlations well, which leads to limited clustering performance. To address this problem, the main purpose of this paper is to propose a novel tensor low-rank representation (TLRR) learning method to perform multi-view clustering. First, we construct a 3rd-order tensor by organizing the features from all views, and then use the t-product in the tensor space to obtain the self-representation tensor of the tensorial data. Second, we use the ℓ1,2 norm to constrain the self-representation tensor to make it capture the class-specificity distribution, that is important for depicting the intrinsic cluster structure. And simultaneously, we rotate the self-representation tensor, and use the tensor singular value decomposition-based weighted TNN as a tighter tensor rank approximation to constrain the rotated tensor. For the challenged mathematical optimization problem, we present an effective optimization algorithm with a theoretical convergence guarantee and relatively low computation complexity. The constructed convergent sequence to the Karush-Kuhn-Tucker (KKT) critical point solution is mathematically validated in detail. We perform extensive experiments on four datasets and demonstrate that TLRR outperforms state-of-the-art multi-view subspace clustering methods.

Multiple graphs learning with a new weighted tensor nuclear norm.

As an effective convex relaxation of the rank minimization model, the tensor nuclear norm minimization based multi-view clustering methods have been attracting more and more interest in recent years. However, most existing clustering methods regularize each singular value equally, restricting their capability and flexibility in tackling many practical problems, where the singular values should be treated differently. To address this problem, we propose a novel weighted tensor nuclear norm minimization (WTNNM) based method for multi-view spectral clustering. Specifically, we firstly calculate a set of transition probability matrices from different views, and construct a 3-order tensor whose lateral slices are composed of probability matrices. Secondly, we learn a latent high-order transition probability matrix by using our proposed weighted tensor nuclear norm, which directly considers the prior knowledge of singular values. Finally, clustering is performed on the learned transition probability matrix, which well characterizes both the complementary information and high-order information embedded in multi-view data. An efficient optimization algorithm is designed to solve the optimal solution. Extensive experiments on five benchmarks demonstrate that our method outperforms the state-of-the-art methods.

Enhanced Tensor RPCA and its Application.

Despite the promising results, tensor robust principal component analysis (TRPCA), which aims to recover underlying low-rank structure of clean tensor data corrupted with noise/outliers by shrinking all singular values equally, cannot well preserve the salient content of image. The major reason is that, in real applications, there is a salient difference information between all singular values of a tensor image, and the larger singular values are generally associated with some salient parts in the image. Thus, the singular values should be treated differently. Inspired by this observation, we investigate whether there is a better alternative solution when using tensor rank minimization. In this paper, we develop an enhanced TRPCA (ETRPCA) which explicitly considers the salient difference information between singular values of tensor data by the weighted tensor Schatten p-norm minimization, and then propose an efficient algorithm, which has a good convergence, to solve ETRPCA. Extensive experimental results reveal that the proposed method ETRPCA is superior to several state-of-the-art variant RPCA methods in terms of performance.

Multiview Clustering by Joint Latent Representation and Similarity Learning.

Subspace learning-based multiview clustering has achieved impressive experimental results. However, the similarity matrix, which is learned by most existing methods, cannot well characterize both the intrinsic geometric structure of data and the neighbor relationship between data. To consider the fact that original data space does not well characterize the intrinsic geometric structure, we learn the latent representation of data, which is shared by different views, from the latent subspace rather than the original data space by linear transformation. Thus, the learned latent representation has a low-rank structure without solving the nuclear-norm. This reduces the computational complexity. Then, the similarity matrix is adaptively learned from the learned latent representation by manifold learning which well characterizes the local intrinsic geometric structure and neighbor relationship between data. Finally, we integrate clustering, manifold learning, and latent representation into a unified framework and develop a novel subspace learning-based multiview clustering method. Extensive experiments on benchmark datasets demonstrate the superiority of our method.

Adaptive latent similarity learning for multi-view clustering.

Most existing clustering methods employ the original multi-view data as input to learn the similarity matrix which characterizes the underlying cluster structure shared by multiple views. This reduces the flexibility of multi-view clustering methods due to the fact that multi-view data usually contains noise or the variation between multi-view data points, which should belong to the same cluster, is larger than the variation between data points belonging to different clusters. To address these problems, we propose a novel multi-view clustering model, namely adaptive latent similarity learning (ALSL) for multi-view clustering. ALSL employs the adaptively learned graph, which characterizes the relationship between clusters, as the new input to learn the latent data representation and integrates the latent similarity representation learning, manifold learning and spectral clustering into a unified framework. With the complementarity of multiple views, the latent similarity representation characterizes the underlying cluster structure shared by multiple views. Our model is intuitive and can be optimized efficiently by using the Augmented Lagrangian Multiplier with Alternating Direction Minimization (ALM-ADM) algorithm. Extensive experiments on benchmark datasets have demonstrated the superiority of the proposed method.

In vivo blind-deconvolution photoacoustic ophthalmoscopy with total variation regularization.

Photoacoustic ophthalmoscopy (PAOM) is capable of noninvasively imaging anatomic and functional information of the retina in living rodents. However, the strong ocular aberration in rodent eyes and limited ultrasonic detection sensitivity affect PAOM's spatial resolution and signal-to-noise ratio (SNR) in in vivo eyes. In this work, we report a computational approach to combine blind deconvolution (BD) algorithm with a regularizing constraint based on total variation (BDTV) for PAOM imaging restoration. We tested the algorithm in retinal and choroidal microvascular images in albino rat eyes. The algorithm improved PAOM's lateral resolution by around 2-fold. Moreover, it enabled the improvement in imaging SNR for both major vessels and capillaries, and realized the well-preserved blood vessels' edges simultaneously, which surpasses conventional Richardson-Lucy BD algorithm. The reported results indicate that the BDTV algorithm potentially facilitate PAOM in extracting retinal pathophysiological information by enhancing in vivo imaging quality without physically modifying PAOM's optical configuration.

Robust DLPP With Nongreedy $\ell _1$ -Norm Minimization and Maximization.

Recently, discriminant locality preserving projection based on L1-norm (DLPP-L1) was developed for robust subspace learning and image classification. It obtains projection vectors by greedy strategy, i.e., all projection vectors are optimized individually through maximizing the objective function. Thus, the obtained solution does not necessarily best optimize the corresponding trace ratio optimization algorithm, which is the essential objective function for general dimensionality reduction. It results in insufficient recognition accuracy. To tackle this problem, we propose a nongreedy algorithm to solve the trace ratio formula of DLPP-L1, and analyze its convergence. Experimental results on three databases illustrate the effectiveness of our proposed algorithm.

F-norm distance metric based robust 2DPCA and face recognition.

Two-dimensional principal component analysis (2DPCA) employs squared F-norm as the distance metric for dimensionality reduction. It is commonly known that squared F-norm is sensitive to the presence of outliers. To address this problem, we use F-norm instead of squared F-norm as the distance metric in the objective function and develop a non-greedy algorithm, which has a closed-form solution in each iteration and can maximize the criterion function, to solve the optimal solution. Our approach not only is robust to outliers but also well characterizes the geometric structure of data. Experimental results on several face databases illustrate that our method is more effective and robust than the other robust 2DPCA algorithms.