No abstract

No abstract

We demonstrate the possibility of a domain-adaptation when only a limited amount of MR data is available. The proposed method surpasses the existing compressed sensing algorithms in terms of the image quality and computation time.

a) Inputs (c) PhotoWCT (d) Ours (WCT 2 ) (b) WCT Figure 1: Photorealistic stylization results. Given (a) an input pair (top: content, bottom: style), the results of (b) WCT [20], (c) PhotoWCT [21], and (d) our model are shown. Every result is produced without any post-processing. While WCT and PhotoWCT suffer from spatial distortions, our model successfully transfers the style and preserves the fine details. AbstractRecent style transfer models have provided promising artistic results. However, given a photograph as a reference style, existing methods are limited by spatial distortions or unrealistic artifacts, which should not happen in real photographs. We introduce a theoretically sound correction to the network architecture that remarkably enhances photorealism and faithfully transfers the style. The key ingredient of our method is wavelet transforms that naturally fits in deep networks. We propose a wavelet corrected transfer based on whitening and coloring transforms (WCT 2 ) that allows features to preserve their structural information and statistical properties of VGG feature space during stylization. This is the first and the only end-to-end model that can stylize a 1024×1024 resolution image in 4.7 seconds, giving a pleasing and photorealistic quality without any postprocessing. Last but not least, our model provides a stable video stylization without temporal constraints. Our code, generated images, and pre-trained models are all available at ClovaAI/WCT2.

Purpose: Compressed sensing MRI (CS-MRI) from single and parallel coils is one of the powerful ways to reduce the scan time of MR imaging with performance guarantee. However, the computational costs are usually expensive. This paper aims to propose a computationally fast and accurate deep learning algorithm for the reconstruction of MR images from highly down-sampled k-space data.Theory: Based on the topological analysis, we show that the data manifold of the aliasing artifact is easier to learn from a uniform subsampling pattern with additional low-frequency k-space data. Thus, we develop deep aliasing artifact learning networks for the magnitude and phase images to estimate and remove the aliasing artifacts from highly accelerated MR acquisition. Methods:The aliasing artifacts are directly estimated from the distorted magnitude and phase images reconstructed from subsampled k-space data so that we can get an aliasing-free images by subtracting the estimated aliasing artifact from corrupted inputs. Moreover, to deal with the globally distributed aliasing artifact, we develop a multi-scale deep neural network with a large receptive field. Results:The experimental results confirm that the proposed deep artifact learning network effectively estimates and removes the aliasing artifacts. Compared to existing CS methods from single and multi-coli data, the proposed network shows minimal errors by removing the coherent aliasing artifacts. Furthermore, the computational time is by order of magnitude faster. Conclusion:As the proposed deep artifact learning network immediately generates accurate reconstruction, it has great potential for clinical applications. IntroductionMR imaging is one of the most valuable imaging methods in the clinic for the needs of diagnostic and therapeutic indications. However, the physical and physiological constraints basically limit the rate of MR acquisition. Since the long scan time is one of the shortcomings of MR imaging, the efficient acceleration scheme for MR acquisition is important to reduce the acquisition time. Accordingly, under-sampling of k-space is necessary, and many researchers have developed various reconstruction methods such as parallel imaging [1, 2] and compressed sensing MRI (CS-MRI) [3,4] that allow for accurate reconstruction from the insufficient k-space samples.For example, generalized autocalibrating partial parallel acquisition (GRAPPA) [2] is a representative parallel MRI (pMRI) technique that interpolates the missing k-space data by exploiting the diversity of the coil sensitivity maps. On the other hand, CS-MRI reconstructs a high-resolution image from randomly sub-sampled k-space data by utilizing the sparsity of the data in the transformed domain. CS algorithms are commonly formulated as penalized inverse problems that minimize the tradeoff between the data fidelity term in the k-space and the sparsity penalty in the transform domain. The state-of-the-art CS algorithm in this field is the annihilating filter-based low-rank Hankel matrix approach (ALOHA), in ...