Most current image super-resolution (SR) methods based on deep convolutional neural networks (CNNs) use residual learning in network structural design, which contributes to effective back propagation, thus improving SR performance by increasing model scale. However, deep residual network suffers some redundancy in model representational capacity by introducing short paths, thus hindering the full mining of model capacity. In addition, blindly enlarging the model scale will cause more problems in model training, even with residual learning. In this work, a novel network architecture is introduced to fully exploit the representational capacity of the model, where all skip connections are implemented by weighted channel concatenation, followed by a 1 × 1 conv layer. Based on this weighted skip connection, we construct the building modules of our model, and improve the global feature fusion (GFF). Unlike most previous models, all skip connections in our network are channel-concatenated and no residual connection is adopted. It is therefore termed as fully channel-concatenated network (FC 2 N). Due to the full exploitation of model capacity, the proposed FC 2 N achieves better performance than other advanced models with fewer model parameters. Extensive experiments demonstrate the superiority of our method to other methods, in terms of both quantitative metrics and visual quality.
This paper presents a fast, high-precision, and fully automatic windowing method based on deep convolutional neural network (CNN) for magnetic resonance imaging (MRI). Displaying a magnetic resonance (MR) image with a data depth of 12/16 bits on regular 8-bit monitors usually needs a windowing process to remap the full range of pixel intensity to a subrange. However, adaptively and automatically adjusting the windowing parameters of MR images under various viewing conditions is a challenging problem in medical image processing due to the low contrast and high grayscale range. We present a novel method based on the deep CNN's to estimate the windowing parameters that can match the adjustment of human experts precisely and quickly. The network acts as a typical end-to-end mapping function that takes the raw pixels of the MR images as input and directly outputs the corresponding estimation of the optimal windowing parameters. To speed up the inference, we utilize a space-to-depth (STD) conversion to reduce the spatial resolution of input images, and thus the computing burden of the inference process. The extensive experiments on the dataset annotated by clinicians show that the proposed method can accurately predict the optimal windowing parameters of an MR image with a size of 1024×1024 in less than 0.01 s. Due to the high effectiveness and efficiency of the proposed method, it is highly applicable for various clinical and research purposes.INDEX TERMS Automatic windowing, convolutional neural network, deep learning, window width and window level, magnetic resonance imaging.
It has been widely acknowledged that learning-based super-resolution (SR) methods are effective to recover a high resolution (HR) image from a single low resolution (LR) input image. However, there exist two main challenges in learning-based SR methods currently: the quality of training samples and the demand for computation. We proposed a novel framework for single image SR tasks aiming at these issues, which consists of blind blurring kernel estimation (BKE) and SR recovery with anchored space mapping (ASM). BKE is realized via minimizing the cross-scale dissimilarity of the image iteratively, and SR recovery with ASM is performed based on iterative least square dictionary learning algorithm (ILS-DLA). BKE is capable of improving the compatibility of training samples and testing samples effectively and ASM can reduce consumed time during SR recovery radically. Moreover, a selective patch processing (SPP) strategy measured by average gradient amplitude |grad| of a patch is adopted to accelerate the BKE process. The experimental results show that our method outruns several typical blind and non-blind algorithms on equal conditions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.