Following this, a simple yet effective algorithm is developed to solve the proposed H-PnP based IR problems. Extensive experimental results on several representative IR tasks, including image deblurring, image CS and image deblocking, demonstrate that the proposed H-PnP algorithm achieves favorable performance compared to many popular or state-of-the-art IR methods in terms of both objective and visual perception.Object detection has gained great improvements with the advances of convolutional neural networks and the availability of large amounts of accurate training data. Though the amount of data is increasing significantly, the quality of data annotations is not guaranteed from the existing crowd-sourcing labeling platforms. In addition to noisy category labels, imprecise bounding box annotations are commonly existed for object detection data. When the quality of training data degenerates, the performance of the typical object detectors is severely impaired. In this paper, we propose a Meta-Refine-Net (MRNet) to train object detectors from noisy category labels and imprecise bounding boxes. First, MRNet learns to adaptively assign lower weights to proposals with incorrect labels so as to suppress large loss values generated by these proposals on the classification branch. Second, MRNet learns to dynamically generate more accurate bounding box annotations to overcome the misleading of imprecisely annotated bounding boxes. Thus, the imprecise bounding boxes could impose positive impacts on the regression branch rather than simply be ignored. Third, we propose to refine the imprecise bounding box annotations by jointly learning from both the category and the localization information. By doing this, the approximation of ground-truth bounding boxes is more accurate while the misleading would be further alleviated. Our MRNet is model-agnostic and is capable of learning from noisy object detection data with only a few clean examples (less than 2%). Extensive experiments on PASCAL VOC 2012 and MS COCO 2017 demonstrate the effectiveness and efficiency of our method.Coronary flow reserve (CFR), relating to the volumetric flow rate, is an effective functional parameter to assess the stenosis in left anterior descending (LAD) coronary artery. We have recently proposed to use high frame rate (HFR) contrast enhanced ultrasound (CEUS) to estimate the volumetric flow rate using ultrasound speckle decorrelation (SDC) without any assumptions about the velocity profile. However, this method still has challenges in imaging deep and small vessels such as LAD. In this study we proposed to address the challenges and demonstrate the feasibility of volumetric flow rate measurement in a coronary mimicking phantom with pulsatile flow using a 1D array cardiac probe, vector Doppler and an optimal probe rotation/tilting for flow direction detection. Both simulations and in vitro experiments were conducted to validate the proposed method. It is shown that in-plane velocities estimated by vector Doppler under a 10-degree probe tilting resulted in smaller percentage error (+5.2%) in flow rate estimates than that in ultrasound imaging velocimetry (-20.2%) although their relative standard deviations were very close, being 2.6 ml/min and 2.8 ml/min, respectively. The flow rate estimated by SDC without direction detection had an error higher than 70%. A 10-degree tilting of the probe had the best results in flow rate estimation when compared to the 5 or 15-degree tilting. Realistic global motions in the LAD increased the flow rate estimation error from 5.2% to 14.2%. It is concluded that it is feasible to measure the volumetric flow rate in a coronary artery flow phantom with a conventional cardiac probe, using HFR acquisition, Doppler and SDC analysis. Potentially, this technique could also be applied to investigate the volumetric flow rate in other small vessels similar to the LAD.Recently, deep learning approaches for MR motion artifact correction have been extensively studied. Although these approaches have shown high performance and lower computational complexity compared to classical methods, most of them require supervised training using paired artifact-free and artifact-corrupted images, which may prohibit its use in many important clinical applications. For example, transient severe motion (TSM) due to acute transient dyspnea in Gd-EOB-DTPA-enhanced MR is difficult to control and model for paired data generation. To address this issue, here we propose a novel unpaired deep learning scheme that does not require matched motion-free and motion artifact images. Specifically, the first step of our method is k-space random subsampling along the phase encoding direction that can remove some outliers probabilistically. In the second step, the neural network reconstructs fully sampled resolution image from a downsampled k-space data, and motion artifacts can be reduced in this step. Last, the aggregation step through averaging can further improve the results from the reconstruction network. We verify that our method can be applied for artifact correction from simulated motion as well as real motion from TSM successfully from both single and multi-coil data with and without k-space raw data, outperforming existing state-of-the-art deep learning methods.Liver lesion segmentation is an essential process to assist doctors in hepatocellular carcinoma diagnosis and treatment planning. Multi-modal positron emission tomography and computed tomography (PET-CT) scans are widely utilized due to their complementary feature information for this purpose. see more However, current methods ignore the interaction of information across the two modalities during feature extraction, omit the co-learning of the feature maps of different resolutions, and do not ensure that shallow and deep features complement each others sufficiently. In this paper, our proposed model can achieve feature interaction across multi-modal channels by sharing the down-sampling blocks between two encoding branches to eliminate misleading features. Furthermore, we combine feature maps of different resolutions to derive spatially varying fusion maps and enhance the lesions information. In addition, we introduce a similarity loss function for consistency constraint in case that predictions of separated refactoring branches for the same regions vary a lot.