Parallel biomedical image processing with GPGPUs in cancer research

Abstract

The main aim of this work is to show, how GPGPUs can facilitate certain type of image processing methods. The software used in this paper is used to detect special tissue part, the nuclei on (HE -hematoxilin eosin) stained colon tissue sample images. Since pathologists are working with large number of high resolution images -thus require significant storage space -, one feasible way to achieve reasonable processing time is the usage of GPGPUs. The CUDA software development kit was used to develop processing algorithms to NVIDIA type GPUs. Our work focuses on how to achieve better performance with coalesced global memory access when working with three-channel RGB tissue images, and how to use the on-die shared memory efficiently.

Business process modeling — Simulation of administrative activities

“…With smaller modifications the model can effectively be used in other fields as in e.g. Remény et al [12], Erdődi [13] and Bencsik et al [16]. Certainly in fields that are not closely related to workflow where the description of an algorithm is rather necessary as in Sergyán et al [14], Györök et al [15] and Cseri et al [18] or Misra [19] a more thorough modification would be necessary for an application of the model.…”

Automatic segmentation of arterial tree from 3D computed tomographic pulmonary angiography (CTPA) scans

“…The performance is limited because these methods are often interfered by the pulmonary vein. Most 3D pulmonary artery segmentation methods take structural and anatomical information into account, either tracking vessels starting at given seed points or calculating a voxel-wise distinction of arteries and veins [3][4][5], and incorporating different anatomical features like proximity of arteries and bronchi [6]. Saha et al [7] introduced fuzzy distance transform to realize the separation of arteries and veins, however, in which the interactive refinement is complex and indispensable.…”

Framework for Comparison and Evaluation of Image Segmentation Algorithms for Medical Imaging

“…Hav ing the slides containing the t issue samples digitalized at a high resolution also makes it possible to use sophisticated image p rocessing algorith ms of d ifferent sorts, some help diagnose illnesses by finding malignous cells [15] [16], some [11] just aid the pathologist by doing a pre-filtering that eliminates parts of the image that do not hold significant data so that the expert can focus on the parts which truly require their expertise. Image segmentation is usually a key element in any such algorith ms [3].…”