MR CONTRAST SYNTHESIS FOR LESION SEGMENTATION.
MR CONTRAST SYNTHESIS FOR LESION SEGMENTATION.
复制标题
DOI：
10.1109/isbi.2010.5490140
复制
发表时间：
2010-06-21
期刊：
影响因子：
--
通讯作者：
Prince JL
中科院分区：
文献类型：
--
作者：
Roy S;Carass A;Shiee N;Pham DL;Prince JL
神经成像数据集的磁共振对比度对数据在图像分析任务（如配准和分割）中的效用有很大影响。漫长的采集时间往往阻碍常规采集多幅磁共振对比图像，并且使用这些数据进行详细分析的机会似乎不可挽回地失去了。本文描述了一种基于示例的方法，该方法使用来自多个对比度图集的补丁匹配，其预期目标是生成替代MR对比度图像，从而有效地模拟彼此的替代脉冲序列。在本文中，我们专门处理从T1和T2脉冲序列中产生的流体衰减反演恢复（FLAIR）序列。证明了这种合成FLAIR对估计白质病变分割的适用性。
The magnetic resonance contrast of a neuroimaging data set has strong impact on the utility of the data in image analysis tasks, such as registration and segmentation. Lengthy acquisition times often prevent routine acquisition of multiple MR contrast images, and opportunities for detailed analysis using these data would seem to be irrevocably lost. This paper describes an example based approach which uses patch matching from a multiple contrast atlas with the intended goal of generating an alternate MR contrast image, thus effectively simulating alternative pulse sequences from one another. In this paper, we deal specifically with Fluid Attenuated Inversion Recovery (FLAIR) sequence generation from T1 and T2 pulse sequences. The applicability of this synthetic FLAIR for estimating white matter lesions segmentation is demonstrated.