In dynamic cardiac cine magnetic resonance imaging, the spatiotemporal resolution is limited by the low imaging speed. Compressed sensing (CS) theory has been applied to improve the imaging speed and thus the spatiotemporal resolution. In this paper, we propose a novel technique that employs a patch-based 3-D spatiotemporal dictionary for sparse representations of dynamic image sequence in the CS framework. Specifically, the dynamic image sequence is divided into overlapping patches along both the spatial and temporal directions. The dictionary is used to provide flexible sparse expressions for these patches. The underlying optimization problem is solved by variable splitting and the alternating direction method with multiplier. Experimental results based on in vivo cardiac data demonstrate that the proposed method is able to accelerate cardiac cine imaging by a factor up to 8 and outperforms the existing state-of-the-art CS methods at high accelerations. The method is expected to be useful in dynamic imaging with a higher spatiotemporal resolution.

While many low rank and sparsity-based approaches have been developed for accelerated dynamic magnetic resonance imaging (dMRI), they all use low rankness or sparsity in input space, overlooking the intrinsic nonlinear correlation in most dMRI data. In this paper, we propose a kernel-based framework to allow nonlinear manifold models in reconstruction from sub-Nyquist data. Within this framework, many existing algorithms can be extended to kernel framework with nonlinear models. In particular, we have developed a novel algorithm with a kernel-based low-rank model generalizing the conventional low rank formulation. The algorithm consists of manifold learning using kernel, low rank enforcement in feature space, and preimaging with data consistency. Extensive simulation and experiment results show that the proposed method surpasses the conventional low-rank-modeled approaches for dMRI.

Polarimetric high resolution range profile (HRRP) holds great potential for radar automatic target recognition (RATR) owing to its capability of providing both polarimetric and spatial scattering information. Conventional polarimetric HRRP recognition methods generally extract a set of features and put them into a well-trained classifier, which heavily rely on expertise. On the contrary, deep learning can automatically learn deep features of the training data and has obtained state-of-the-art results in many classification tasks. In this paper, a novel deep model based on convolutional long short-term memory (ConvLSTM) network and self-attention mechanism is proposed for polarimetric HRRP recognition. In the proposed model, ConvLSTM employs the convolutional operator and recurrent LSTM structure to capture and aggregate target polarimetric and spatial scattering information from different dimensions simultaneously. Self-attention mechanism is introduced before ConvLSTM to make the model focus on the discriminative range cells and help improve the learning capacity of ConvLSTM. Experiment results on the simulated and measured datasets demonstrate the effectiveness of the proposed model for multi-class targets recognition. The results of two expanded experiments also show that this model performs well in noise and small training sample cases, showcasing good potentials in practical applications.

In radar automatic target recognition (RATR), high-resolution range profile (HRRP) has received intensive attention due to its low computational cost. As HRRP is sensitive to the aspect of the target, a training set covering sufficient aspects is essential to the success of an RATR model, which is however intractable in complex environment with noncooperative targets. In this article, an aspect-directed attention generative adversarial network is proposed to generate multiview HRRPs using real samples from few aspects. The key is that the HRRPs from the similar targets share the same aspect variation pattern. Hence, an HRRP is decomposed into its identity and aspect features via an aspect-directed disentangled representation network with self-attention modules. In the training stage, the decomposition network and the aspect variation pattern are learned from full aspect samples of cooperative targets. When generation, the desired multiview HRRPs of the noncooperative target are synthesized by its identity features extracted from few aspect samples and the learned aspect variation pattern. Three types of experiments on the simulated and measured datasets demonstrate the generation performances of our method. First, the generated HRRPs are visually compared with the truth. Second, the similarity of the scattering center power and handcrafted feature distributions are quantitatively evaluated. Finally, recognition experiments verify the feasibility of data augmentation with the generated HRRPs. Extensive results show the superior performance of our method over other state-of-the-art methods.