文章基本信息

标题：Hybrid CPU and GPU Computation to Detect Lung Nodule in Computed Tomography Images
本地全文：下载
作者：I Wayan Budi Sentana ; Naser Jawas ; Sri Andriati Asri 等
期刊名称：International Journal on Electrical Engineering and Informatics
印刷版ISSN：2085-6830
出版年度：2018
卷号：10
期号：3
页码：466-478
DOI：10.15676/ijeei.2018.10.3.4
出版社：School of Electrical Engineering and Informatics
摘要：Lung Nodule is a white patch on the thorax medical image, usually used as an earlymarker of lung cancer. This research aims to produce algorithms that can detect lung nodulesautomatically in CT images, by utilizing a combination of hybrid computing between CentralProcessing Unit (CPU) and Graphical Processing Unit (GPU). The framework used isCompute Unified Device Architecture, which consists of platform and programming model.The algorithm consists of several steps; read DICOM and data normalization, lungsegmentation, candidate nodule extraction, and classification. Normalization is required tofacilitate calculation by changing the data type ui16 to ui8. Furthermore, segmentation is usedto separate the lung parts with other organs, where at this stage the Otsu Algorithm and MooreNeighborhood Tracing (MNT) are used. The next step is Lung Nodule Extraction, whichaims to find the nodule candidate. The last step is a classification that utilizes the SupportVector Machine (SVM) to distinguish which one is nodule or not. The algorithm successfullydetects near round nodules that are free-standing or not attached to other parts of organs.After undergoing ground truth tests, it was found that under some conditions, the algorithmhas not been able to distinguish nodules and other strokes that resemble nodules. While interms of computing speed is found a very surprising result because overall single CPUcomputing provides better results compared to hybrid CPU and GPU computing. Multiplemorphology and transmission time to GPU contributed to the double execution time of hybridmodel compared to single CPU. Adjustment in dataset grouping by detecting the nodulesimultaneously for several dataset will also improve the performance of hybrid CPU andGPU computation.
关键词：Lung Nodule; Hybrid Computing; GPU and CPU; CT images