MAGNETIC RESONANCE IMAGE SYNTHESIS THROUGH PATCH REGRESSION.
MAGNETIC RESONANCE IMAGE SYNTHESIS THROUGH PATCH REGRESSION.
复制标题
DOI：
10.1109/isbi.2013.6556484
复制
发表时间：
2013-12-31
期刊：
影响因子：
--
通讯作者：
Prince JL
中科院分区：
文献类型：
--
作者：
Jog A;Roy S;Carass A;Prince JL
磁共振成像（MRI）被广泛用于分析人脑的结构和功能。MRI是非常通用的，可以根据研究设计的要求产生不同的组织对比度。出于诸如患者舒适度、成本和改进技术等原因，在成像会话期间可能尚未采集用于群组分析的某些组织对比度。这种缺失的脉冲序列阻碍了神经解剖学的研究。一个可能的解决方案是合成缺失的序列。本文提出了一种数据驱动的图像合成方法，它提供了平等的，如果不是上级合成相比，国家的最先进的，除了是一个数量级更快。合成变换是通过经过训练的袋装回归树集合对图像块进行的。通过合成T1加权扫描的T2加权对比度，对幻影和真实的数据进行验证。我们还合成了3特斯拉T1加权磁化准备快速梯度回波（MPRAGE）图像从1.5特斯拉的MPRAGE证明这种方法的通用性。
Magnetic resonance imaging (MRI) is widely used for analyzing human brain structure and function. MRI is extremely versatile and can produce different tissue contrasts as required by the study design. For reasons such as patient comfort, cost, and improving technology, certain tissue contrasts for a cohort analysis may not have been acquired during the imaging session. This missing pulse sequence hampers consistent neuroanatomy research. One possible solution is to synthesize the missing sequence. This paper proposes a data-driven approach to image synthesis, which provides equal, if not superior synthesis compared to the state-of-the-art, in addition to being an order of magnitude faster. The synthesis transformation is done on image patches by a trained bagged ensemble of regression trees. Validation was done by synthesizing T2-weighted contrasts from T1-weighted scans, for phantoms and real data. We also synthesized 3 Tesla T1-weighted magnetization prepared rapid gradient echo (MPRAGE) images from 1.5 Tesla MPRAGEs to demonstrate the generality of this approach.