CG-SENSE revisited: Results from the first ISMRM reproducibility challenge.
CG-SENSE revisited: Results from the first ISMRM reproducibility challenge.
复制标题
DOI：
10.1002/mrm.28569
复制
发表时间：
2021-04
影响因子：
3.3
通讯作者：
Knoll F
中科院分区：
文献类型：
--
作者：
Maier O;Baete SH;Fyrdahl A;Hammernik K;Harrevelt S;Kasper L;Karakuzu A;Loecher M;Patzig F;Tian Y;Wang K;Gallichan D;Uecker M;Knoll F
这项工作的目的是阐明在挑战的背景下磁共振图像重建的再现性问题。参与者必须重现Pruessmann等人的“用任意k空间轨迹进行灵敏度编码的进展”的结果。挑战的任务是按照原论文中的方法重建径向获取的多线圈k空间数据（大脑/心脏），再现其关键数字。结果与挑战后创建的综合参考实现进行了比较，考虑了提交中使用的两种最常见的编程语言（Matlab/Python）。从视觉上看，提交作品之间的差异很小。像素方面的差异源于图像方向、假设的视场或分辨率。参考实现在视觉上和图像相似度量方面都很一致。虽然已发布的算法的描述水平使参与者能够在总体上重现CG-SENSE，但实现的细节各不相同，例如密度补偿或吉洪诺夫正则化。关于数据的隐式假设导致进一步的差异，强调了与开放数据集配套的足够元数据的重要性。在缺乏真实结果的情况下，定量地定义再现性对于图像重建挑战来说是非平凡的。典型的相似性度量，如SSIM的NMSE，受到图像强度缩放和离群像素的误导。因此，为了促进再现性，鼓励研究人员将代码和数据与原始论文一起发表。未来关于磁共振图像重建的方法学论文可能会受益于这里提出的CG-SENSE的综合参考实现，作为方法比较的基准。
The aim of this work is to shed light on the issue of reproducibility in MR image reconstruction in the context of a challenge. Participants had to recreate the results of “Advances in sensitivity encoding with arbitrary k-space trajectories” by Pruessmann et al. The task of the challenge was to reconstruct radially acquired multicoil k-space data (brain/heart) following the method in the original paper, reproducing its key figures. Results were compared to consolidated reference implementations created after the challenge, accounting for the two most common programming languages used in the submissions (Matlab/Python). Visually, differences between submissions were small. Pixel-wise differences originated from image orientation, assumed field-of-view, or resolution. The reference implementations were in good agreement, both visually and in terms of image similarity metrics. While the description level of the published algorithm enabled participants to reproduce CG-SENSE in general, details of the implementation varied, for example, density compensation or Tikhonov regularization. Implicit assumptions about the data lead to further differences, emphasizing the importance of sufficient metadata accompanying open datasets. Defining reproducibility quantitatively turned out to be nontrivial for this image reconstruction challenge, in the absence of ground-truth results. Typical similarity measures like NMSE of SSIM were misled by image intensity scaling and outlier pixels. Thus, to facilitate reproducibility, researchers are encouraged to publish code and data alongside the original paper. Future methodological papers on MR image reconstruction might benefit from the consolidated reference implementations of CG-SENSE presented here, as a benchmark for methods comparison.
登录
查看更多内容
DOI：
10.1126/science.1213847
发表时间：
2011-12-02
期刊：
Science (New York, N.Y.)
影响因子：
--
作者：
Peng RD
通讯作者：
Peng RD
DOI：
10.1109/tau.1970.1162132
发表时间：
1970-01-01
期刊：
IEEE TRANSACTIONS ON AUDIO AND ELECTROACOUSTICS
影响因子：
--
作者：
BLUESTEIN, LI
通讯作者：
BLUESTEIN, LI
影响因子：
10.6
作者：
JACKSON, JI;MEYER, CH;MACOVSKI, A
通讯作者：
MACOVSKI, A
影响因子：
19.6
作者：
Chen, Xiaoli;Dallmeier-Tiessen, Suenje;Neubert, Sebastian
通讯作者：
Neubert, Sebastian
影响因子：
2.5
作者：
GOLUB, GH;HEATH, M;WAHBA, G
通讯作者：
WAHBA, G