results: 在三个数学研究中,DISCUS比CS和DIP better,并且通过群 sparse鼓励编码向量,可以更好地描述动态图像的低维抽象 manifold,提高图像重建的性能。Abstract
High-quality training data are not always available in dynamic MRI. To address this, we propose a self-supervised deep learning method called deep image prior with structured sparsity (DISCUS) for reconstructing dynamic images. DISCUS is inspired by deep image prior (DIP) and recovers a series of images through joint optimization of network parameters and input code vectors. However, DISCUS additionally encourages group sparsity on frame-specific code vectors to discover the low-dimensional manifold that describes temporal variations across frames. Compared to prior work on manifold learning, DISCUS does not require specifying the manifold dimensionality. We validate DISCUS using three numerical studies. In the first study, we simulate a dynamic Shepp-Logan phantom with frames undergoing random rotations, translations, or both, and demonstrate that DISCUS can discover the dimensionality of the underlying manifold. In the second study, we use data from a realistic late gadolinium enhancement (LGE) phantom to compare DISCUS with compressed sensing (CS) and DIP and to demonstrate the positive impact of group sparsity. In the third study, we use retrospectively undersampled single-shot LGE data from five patients to compare DISCUS with CS reconstructions. The results from these studies demonstrate that DISCUS outperforms CS and DIP and that enforcing group sparsity on the code vectors helps discover true manifold dimensionality and provides additional performance gain.
摘要
高品质训练数据不总是可用于动态MRI。为解决这个问题,我们提出了一种自愿supervised深度学习方法,即深度图像先验(DISCUS),用于重建动态图像。DISCUS受到深度图像先验(DIP)的激发,并通过联合网络参数和输入代码向量的优化来重建一系列图像。然而,DISCUS还强制了几何簇节点的簇节点簇节点,以发现时间变化的低维数据 manifold。与对于几何学习的先前工作不同,DISCUS不需要指定数据维度。我们验证DISCUS使用三个数据分析。在第一个研究中,我们使用静态Shepp-Logan假象,将几帧帧进行随机旋转、平移或 Both,并证明DISCUS可以发现底层数据的维度。在第二个研究中,我们使用实际的LGE假象来比较DISCUS、压缩感知(CS)和DIP,并证明了几何簇节点的正面影响。在第三个研究中,我们使用实际的单击LGE数据,将DISCUS与CS重建相比较。结果显示DISCUS比CS和DIP表现更好,并且强制几何簇节点簇节点帮助发现真正的数据维度,提供了额外的性能优化。
paper_authors: Xuan Lei, Philip Schniter, Chong Chen, Rizwan Ahmad
for: corrections of undesired spatial variation in intensity of MR images
methods: utilizes pre-scan data and proposes an intensity correction method
results: demonstrated on a digital phantom and cardiac MRI data collected from a commercial scannerAbstract
Modern MRI scanners utilize one or more arrays of small receive-only coils to collect k-space data. The sensitivity maps of the coils, when estimated using traditional methods, differ from the true sensitivity maps, which are generally unknown. Consequently, the reconstructed MR images exhibit undesired spatial variation in intensity. These intensity variations can be at least partially corrected using pre-scan data. In this work, we propose an intensity correction method that utilizes pre-scan data. For demonstration, we apply our method to a digital phantom, as well as to cardiac MRI data collected from a commercial scanner by Siemens Healthineers. The code is available at https://github.com/OSU-MR/SCC.
摘要
现代MRI仪器使用一个或多个小 receive-only磁场探测器来收集k空间数据。传统方法估算探测器的敏感地图,与真实的敏感地图不同,这会导致重建MR图像中的空间变化。这些变化可以至少部分通过先行数据进行修正。在这个工作中,我们提出了一种使用先行数据进行强度修正的方法。为了示例,我们对数字phantom进行了应用,以及从商业SCANNER中收集的卡达MRI数据。代码可以在https://github.com/OSU-MR/SCC中找到。
results: 可以高效探索适用于图像 interpolating 和缩放的核函数空间,并将最佳核函数选择为特定应用程序I hope that helps! Let me know if you have any other questions.Abstract
We propose a new class of kernels to simplify the design of filters for image interpolation and resizing. Their properties are defined according to two parameters, specifying the width of the transition band and the height of a unique sidelobe. By varying these parameters it is possible to efficiently explore the space with only the filters that are suitable for image interpolation and resizing, and identify the filter that is best for a given application. These two parameters are also sufficient to obtain very good approximations of many commonly-used interpolation kernels. We also show that, because the Fourier transforms of these kernels have very fast decay, these filters produce better results when time-stretched for image downsizing.
摘要
我们提出一种新的kernel类型,用于简化图像 interpolate和缩放过程中的筛子设计。这些kernel的性质由两个参数定义,即过渡带宽和唯一侧LOB的高度。通过调整这两个参数,可以快速探索适用于图像 interpolate 和缩放的filter空间,并identify最佳的filter для给定应用。此外,我们还证明了这些kernel的傅立叶变换具有非常快的衰落,因此这些筛子在图像缩放时产生更好的结果。
Bitstream Organization for Parallel Entropy Coding on Neural Network-based Video Codecs
results: 降低 overhead,可以将其降到小于1%和0.1%的水平Abstract
Video compression systems must support increasing bandwidth and data throughput at low cost and power, and can be limited by entropy coding bottlenecks. Efficiency can be greatly improved by parallelizing coding, which can be done at much larger scales with new neural-based codecs, but with some compression loss related to data organization. We analyze the bit rate overhead needed to support multiple bitstreams for concurrent decoding, and for its minimization propose a method for compressing parallel-decoding entry points, using bidirectional bitstream packing, and a new form of jointly optimizing arithmetic coding termination. It is shown that those techniques significantly lower the overhead, making it easier to reduce it to a small fraction of the average bitstream size, like, for example, less than 1% and 0.1% when the average number of bitstream bytes is respectively larger than 95 and 1,200 bytes.
摘要
Translation in Simplified Chinese:视频压缩系统需要支持增长的带宽和数据传输速率,同时具有低成本和低功耗。然而,这些系统可能受到Entropy编码瓶颈的限制。我们可以通过并行编码来大幅提高效率,但是这会导致一些数据组织related的压缩损失。我们分析了多个bit流的支持成本,并提出了一种压缩并行解码入口点的方法,使用双向bit流压缩和一种新的共同优化加密编码终止方法。我们发现,这些技术可以减少成本,使其变得更容易减少到小于1%和0.1%的比例,例如在95个字节的平均bit流大小时和1200个字节的平均bit流大小时。
Technical description of the EPFL submission to the JPEG DNA CfP
results: 作者提供了代码、对象指标结果、图表和生化约束分析,可以在ISO文档系统上获取,文档编号WG1M101013-ICQ-EPFL。Abstract
This document provides a technical description of the codec proposed by EPFL to the JPEG DNA Call for Proposals. The codec we refer to as V-DNA for its versatility, enables the encoding of raw images and already compressed JPEG 1 bitstreams, but the underlying algorithm could be used to encode and transcode any kind of data. The codec is composed of two main modules: the image compression module, handled by the state-of-the-art JPEG XL codec, and the DNA encoding module, implemented using a modified Raptor Code implementation following the RU10 (Raptor Unsystematic) description. The code for encoding and decoding, as well as the objective metrics results, plots and biochemical constraints analysis are available on ISO Documents system with document number WG1M101013-ICQ-EPFL submission to the JPEG DNA CfP.
摘要
这份文档提供了由EPFL提出的代码生成器的技术描述,我们称之为V-DNA,它允许对原始图像和已经压缩的JPEG1位流进行编码,但是下面的算法可以用于任何数据类型的编码和转码。代码生成器由两个主要模块组成:图像压缩模块,使用现有的JPEG XL代码生成器,以及DNA编码模块,使用修改后的Raptor Code实现,按照RU10(RaptorUnsystematic)的描述进行实现。代码生成器的编码和解码代码、目标指标结果、图表和生物化约束分析都可以在ISO文档系统上找到,文档号为WG1M101013-ICQ-EPFL提交到JPEG DNA calls for proposals。
Suppression of the Talbot effect in Fourier transform acousto-optic imaging
results: 实验和理论研究表明,对 acoustic periodic structure进行额外相位调制可以消除 Talbot 效应,提高图像重建质量和可读性。Abstract
We report on the observation and correction of an imaging artifact attributed to the Talbot effect in the context of acousto-optic imaging using structured acoustic waves. When ultrasound waves are emitted with a periodic structure, the Talbot effect produces $\pi$ -phase shifts of that periodic structure at every half of the Talbot distance in propagation. This unwanted artifact is detrimental to the image reconstruction, which assumes near-field diffraction is negligible. Here, we demonstrate both theoretically and experimentally how imposing an additional phase modulation on the acoustic periodic structure induces a symmetry constraint leading to the annihilation of the Talbot effect. This will significantly improve the acousto-optic image reconstruction quality and allows for an improvement of the reachable spatial resolution of the image.
摘要
我们报道了对听音镜像扩散 artifact的观察和修正,这种扩散 artifact被归因于坦博效应在音频普散频率场中。当 ultrasound 波发射 periodic 结构时,坦博效应会在每个坦博距离的一半处产生 $\pi$ 期延迟,这种不良扩散 artifact会导致图像重建失败,图像重建假设近场干扰可以忽略。在这里,我们理论和实验表明,对音频 periodic 结构增加额外的相位调制可以导致对称约束,使坦博效应消失。这将改善音频普散图像重建质量,并允许更高的可见范围。