Zhuge Ying, Cao Yong, Miller Robert W
Radiation Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD 20892, USA.
Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:6341-4. doi: 10.1109/IEMBS.2009.5333158.
Image segmentation techniques using fuzzy connectedness principles have shown their effectiveness in segmenting a variety of objects in several large applications in recent years. However, one problem of these algorithms has been their excessive computational requirements when processing large image datasets. Nowadays commodity graphics hardware provides high parallel computing power. In this paper, we present a parallel fuzzy connected image segmentation algorithm on Nvidia's Compute Unified Device Architecture (CUDA) platform for segmenting large medical image data sets. Our experiments based on three data sets with small, medium, and large data size demonstrate the efficiency of the parallel algorithm, which achieves a speed-up factor of 7.2x, 7.3x, and 14.4x, correspondingly, for the three data sets over the sequential implementation of fuzzy connected image segmentation algorithm on CPU.
近年来，基于模糊连接原理的图像分割技术在多个大型应用中对各种物体的分割已展现出其有效性。然而，这些算法的一个问题是在处理大型图像数据集时计算需求过大。如今，商用图形硬件具备强大的并行计算能力。在本文中，我们在英伟达的统一计算设备架构（CUDA）平台上提出了一种并行模糊连接图像分割算法，用于分割大型医学图像数据集。我们基于三个小、中、大数据规模的数据集进行的实验证明了该并行算法的效率，与在CPU上顺序执行模糊连接图像分割算法相比，对于这三个数据集，该并行算法的加速因子分别达到了7.2倍、7.3倍和14.4倍。
