School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA.
IEEE Trans Biomed Eng. 2013 Sep;60(9):2511-20. doi: 10.1109/TBME.2013.2259625.
An important problem of neuroimaging data analysis for traumatic brain injury (TBI) is the task of coregistering MR volumes acquired using distinct sequences in the presence of widely variable pixel movements which are due to the presence and evolution of pathology. We are motivated by this problem to design a numerically stable registration algorithm which handles large deformations. To this end, we propose a new measure of probability distributions based on the Bhattacharyya distance, which is more stable than the widely used mutual information due to better behavior of the square root function than the logarithm at zero. Robustness is illustrated on two TBI patient datasets, each containing 12 MR modalities. We implement our method on graphics processing units (GPU) so as to meet the clinical requirement of time-efficient processing of TBI data. We find that 6 sare required to register a pair of volumes with matrix sizes of 256 × 256 × 60 on the GPU. In addition to exceptional time efficiency via its GPU implementation, this methodology provides a clinically informative method for the mapping and evaluation of anatomical changes in TBI.
外伤性脑损伤（TBI）的神经影像学数据分析中的一个重要问题是在存在广泛变化的像素运动的情况下，使用不同序列获取的 MR 体积的配准任务，这些运动是由于病理学的存在和演变引起的。我们受到这个问题的启发，设计了一种数值稳定的配准算法，该算法可以处理大变形。为此，我们提出了一种新的基于 Bhattacharyya 距离的概率分布度量，它比广泛使用的互信息更稳定，因为平方根函数的行为比对数函数在零时更好。稳健性在两个 TBI 患者数据集上得到了说明，每个数据集包含 12 个 MR 模式。我们在图形处理单元（GPU）上实现了我们的方法，以满足 TBI 数据的高效处理的临床要求。我们发现，在 GPU 上，对于矩阵大小为 256×256×60 的一对体积进行配准需要 6 个。除了通过 GPU 实现的卓越的时间效率外，这种方法还为 TBI 中的映射和评估解剖结构变化提供了一种临床信息丰富的方法。
