http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Automatic Detection of GGO in CT Lung Images by Using Statistical Features and Neural Networks
Hyoungseop Kim,Yoshifumi Katsumata,Joo Kooi Tan,Seiji Ishikawa 대한전자공학회 2009 ITC-CSCC :International Technical Conference on Ci Vol.2009 No.7
In this paper, we described an algorithm of automatic detection of GGO candidate region to develop a CAD system from lung CT images by use of statistical features which is obtained density and shape features. In this algorithm, first, image pre-processing techniques such as segmentation of lung areas, binarization technique are introduced. In the second step, statistical features based on density features which are obtained mean, standard deviation, skewness, and kurtosis. Also two shape features which are obtained spiral scanning filter, and Gabor filter are introduced. In our clustering step, GGO area can be detect by using artificial neural networks. The proposed technique applied to 31 lung CT image sets. From this database, classification rates of a true positive rate of 84.2%, false positive rate of 57% and number of false positive 1.07/slice under the receiver operating characteristic analysis were achieved. The aim of this study is segmentation of lungs region and detection of abnormal area for the GGO by using thoracic MDCT image sets. This study also tried to decrease the amount of false positive rates and increase the amount of true positive rates so that the accuracy of performance.
Optimal registration method based on ICP algorithm from head CT and MR image sets
Kouhei Harada,Hyoungseop Kim,Joo Kooi Tan,Seiji Ishikawa,Akiyoshi Yamamoto 제어로봇시스템학회 2008 제어로봇시스템학회 국제학술대회 논문집 Vol.2008 No.10
Image registration is an important problem and a fundamental task for understanding the internal organ or internal structure of human body, analyzing the temporal change from the image sets which is obtained different time series in computer vision and image processing field. Especially, CT and MR imaging of the head for diagnosis and surgical planning indicate that physicians and surgeons gain important information from these modalities. In radiotherapy planning, manual registration techniques are performed on MR and CT images of the brain. In general, physicians segment the volumes of interest (VOIs) from each set of slices on the MR and CT images manually. However, manual registration of the object area may require several hours for analysis based on anatomical knowledge. In this paper, to register two images which are obtained from different modalities we develop a new method for automatic registration of the head CT and MR images by using ICP (iterative closest point) algorithm in several extracted data and maximization of mutual information. One of the benefits of using the ICP algorithm is that computational costs can be reduced on the registration. The primary objective of this study is to increase the registration accuracy and reduce the computational processing time. The technique was applied to five real image sets which are obtained from the two different modalities and the satisfactory results are obtained. Some experimental results are shown with discussion.
Daisuke YUKI,Hyoungseop KIM,Joo Kooi TAN,Seiji ISHIKAWA,Masanori TSUKUDA,Ichiro OMURA 제어로봇시스템학회 2015 제어로봇시스템학회 국제학술대회 논문집 Vol.2015 No.10
Recently, the necessity of environmental regulation, low fuel consumption, and natural energy development is proposed by environmental issues. So the demands of power transistor devices are increased. But measurement technique of the current distribution is not keeping up with further miniaturized and integrated were needed in present condition. Now, therefore, ensuring security attended high functionalization is a subject. IGBT (Insulated Gate Bipolar Transistor) is the device that used for wide range of power devices. So we are developing imaging system used non-contact sensor arrays aimed to IGBT production line. In this paper, we propose a development of a supporting system for visual inspection IGBT device based on statistical feature and complex multi-resolution analysis. First, this performs signal de-noising after entering well-known good data and measured data. Second, the statistical feature is expressed the difference between good data and measured data are calculated. Last, classifying of good and inferiority is performed based on the result of threshold processing. In the paper, we applied our algorithm to 28 sample data including 20 good data and 8 inferiority data.
Extraction of multi organs by use of level set method from CT images
Masafumi Komatsu,Hyoungseop Kim,Joo Kooi Tan,Seiji Ishikawa,Akiyoshi Yamamoto 제어로봇시스템학회 2008 제어로봇시스템학회 국제학술대회 논문집 Vol.2008 No.10
Recently, various imaging equipments have been introduced into medical fields. Especially, HRCT is one of the most useful diagnosis systems because it provides a high resolution image to physicians. Accordingly, many related image processing techniques are proposed into medical fields for extraction of abnormal area. In the medical image processing field, segmentation is one of the most important problems for analyzing the abnormalities and recognition of internal structures before the operation. Many related segmentation techniques have been developed for automatic extraction of regions of interest. Especially, in order to extract multi organs and to understand the structure of them, several approaches have been developed in the past. But there are still no fully automatic segmentation methods that are generally applicable to regions of interest based on CT image set. In this paper, we propose a new technique for automatic extraction of the multi organs on the MDCT images employing the level set method. We apply the proposed technique to three CT cases and satisfactory results are achieved.