Cooper Lee A D, Saltz Joel H, Catalyurek Umit, Huang Kun
Center for Comprehensive Informatics, Emory University, Atlanta, GA.
Department of Biomedical Informatics, The Ohio State University, Columbus, OH.
Proc IEEE Int Conf Healthc Inform Imaging Syst Biol. 2011 Jul;2011:174-181. doi: 10.1109/HISB.2011.10. Epub 2011 Oct 27.
The segmentation of tissue regions in high-resolution microscopy is a challenging problem due to both the size and appearance of digitized pathology sections. The two point correlation function (TPCF) has proved to be an effective feature to address the textural appearance of tissues. However the calculation of the TPCF functions is computationally burdensome and often intractable in the gigapixel images produced by slide scanning devices for pathology application. In this paper we present several approaches for accelerating deterministic calculation of point correlation functions using theory to reduce computation, parallelization on distributed systems, and parallelization on graphics processors. Previously we show that the correlation updating method of calculation offers an 8-35× speedup over frequency domain methods and decouples efficient computation from the select scales of Fourier methods. In this paper, using distributed computation on 64 compute nodes provides a further 42× speedup. Finally, parallelization on graphics processors (GPU) results in an additional 11-16× speedup using an implementation capable of running on a single desktop machine.
由于数字化病理切片的尺寸和外观，在高分辨率显微镜下对组织区域进行分割是一个具有挑战性的问题。两点相关函数（TPCF）已被证明是解决组织纹理外观的有效特征。然而，TPCF函数的计算在计算上非常繁重，并且在用于病理应用的玻片扫描设备产生的千兆像素图像中通常难以处理。在本文中，我们提出了几种方法来加速点相关函数的确定性计算，方法包括利用理论减少计算量、在分布式系统上进行并行化以及在图形处理器上进行并行化。之前我们表明，计算的相关更新方法比频域方法提供了8到35倍的加速，并将高效计算与傅里叶方法的选定尺度解耦。在本文中，在64个计算节点上进行分布式计算可进一步加速42倍。最后，使用能够在单个台式机上运行的实现方式，在图形处理器（GPU）上进行并行化可额外加速11到16倍。
