• Progress in Medical Physics
• /
• v.19 no.4
• /
• pp.241-246
• /
• 2008

Patient's respiration can have an effect on movement of tumor range and peripheral organs. Therefore, the respiratory signal was acquired by relation between external markers and movement of patient's abdomen during radiational therapy in order to minimize the effect of respiration. Based on this technique, many studies of rational therapy to irradiate at particular part of stable respiratory signals have executed and they have been clinically applied. Nevertheless, the phase-based method is preferred to the amplitude-based method for the rational therapy related to respiration. Because stabilization of the respiratory signal are limited. In this study, a in-house respiratory signal analysis program was developed for the phase reassignment and the analysis of the irregular respiratory signals. Various irregular respiratory patterns was obtained from clinical experimental volunteers. After then, the in-house program analyzed the factors affecting to phase assignment which is directly related to irradiated sector. Subsequently, accuracy of phase assignment was improved with removement of irregular signals by self-developed algorithm. This study is considered to be useful for not only image reconstruction and elevation of irradiating accuracy through phase assignment of RPM system but also analysis of respiratory signals. Moreover, development of 4D CT image is planed with phantom researches or clinical experiments based on this program.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.2
• /
• pp.3-12
• /
• 2010

In previous studies, the digital measurement systems and analysis algorithms were developed by using the related techniques, such as the aerial photograph detection and high resolution satellite image process. However, these studies were limited in 2-dimensional geo-processing. Therefore, it is necessary to apply the 3-dimensional spatial information and coordinate system for higher accuracy in recognizing and locating of geo-features. The objective of this study was to develop a stochastic algorithm for the optimal sensor placement using the 3-dimensional spatial analysis method. The 3-dimensional information of the LiDAR was applied in the sensor field algorithm based on 2- and/or 3-dimensional gridded points. This study was conducted with three case studies using the optimal sensor placement algorithms; the first case was based on 2-dimensional space without obstacles(2D-non obstacles), the second case was based on 2-dimensional space with obstacles(2D-obstacles), and lastly, the third case was based on 3-dimensional space with obstacles(3D-obstacles). Finally, this study suggested the methodology for the optimal sensor placement - especially, for ground-settled sensors - using the LiDAR data, and it showed the possibility of algorithm application in the information collection using sensors.

• Journal of KIISE:Databases
• /
• v.29 no.5
• /
• pp.367-380
• /
• 2002

Due to recent increase in applications requiring huge amount of data such as spatial data analysis and image analysis, clustering on large databases has been actively studied. In a hierarchical clustering method, a tree representing hierarchical decomposition of the database is first created, and then, used for efficient clustering. Existing hierarchical clustering methods mainly adopted the bottom-up approach, which creates a tree from the bottom to the topmost level of the hierarchy. These bottom-up methods require at least one scan over the entire database in order to build the tree and need to search most nodes of the tree since the clustering algorithm starts from the leaf level. In this paper, we propose a novel top-down hierarchical clustering method that uses multidimensional indexes that are already maintained in most database applications. Generally, multidimensional indexes have the clustering property storing similar objects in the same (or adjacent) data pares. Using this property we can find adjacent objects without calculating distances among them. We first formally define the cluster based on the density of objects. For the definition, we propose the concept of the region contrast partition based on the density of the region. To speed up the clustering algorithm, we use the branch-and-bound algorithm. We propose the bounds and formally prove their correctness. Experimental results show that the proposed method is at least as effective in quality of clustering as BIRCH, a bottom-up hierarchical clustering method, while reducing the number of page accesses by up to 26～187 times depending on the size of the database. As a result, we believe that the proposed method significantly improves the clustering performance in large databases and is practically usable in various database applications.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.7
• /
• pp.31-37
• /
• 2023

Since tunnels are built underground, it is impossible to check visually the location and degree of deterioration of steel ribs. Therefore, in tunnel maintenance, GPR images are generally used to detect steel ribs. While research on GPR image analysis employing artificial neural networks has primarily focused on detecting underground pipes and road damage, there have been limited applications for analyzing tunnel GPR data, specifically for steel rib detection, both internationally and domestically. In this study, a one-step object detection algorithm called YOLO, based on a convolutional neural network, was utilized to automate the localization of steel ribs using GPR data. The performance of the algorithm is then analyzed. Two datasets were employed for the analysis. A dataset comprising 512 original images and another dataset consisting of 2,048 augmented images. The omission rate, which represents the ratio of undetected steel ribs to the total number of steel ribs, was 0.38% for the model using the augmented data, whereas the omission rate for the model using only the original data was 7.18%. Thus, from an automation standpoint, it is more practical to employ an augmented dataset.

• The KIPS Transactions:PartB
• /
• v.16B no.5
• /
• pp.341-346
• /
• 2009

The motion data glove is a representative human-computer interaction tool that inputs human hand gestures to computers by measuring their motions. The motion data glove is essential equipment used for new computer technologiesincluding home automation, virtual reality, biometrics, motion capture. For its popular usage, this paper attempts to develop an inexpensive visual.type motion data glove that can be used without any special equipment. The proposed approach has the special feature; it can be developed as a low-cost one becauseof not using high-cost motion-sensing fibers that were used in the conventional approaches. That makes its easy production and popular use possible. This approach adopts a visual method that is obtained by improving conventional optic motion capture technology, instead of mechanical method using motion-sensing fibers. Compared to conventional visual methods, the proposed method has the following advantages and originalities Firstly, conventional visual methods use many cameras and equipments to reconstruct 3D pose with eliminating occlusions But the proposed method adopts a mono vision approachthat makes simple and low cost equipments possible. Secondly, conventional mono vision methods have difficulty in reconstructing 3D pose of occluded parts in images because they have weak points about occlusions. But the proposed approach can reconstruct occluded parts in images by using originally designed thin-bar-shaped optic indicators. Thirdly, many cases of conventional methods use nonlinear numerical computation image analysis algorithm, so they have inconvenience about their initialization and computation times. But the proposed method improves these inconveniences by using a closed-form image analysis algorithm that is obtained from original formulation. Fourthly, many cases of conventional closed-form algorithms use approximations in their formulations processes, so they have disadvantages of low accuracy and confined applications due to singularities. But the proposed method improves these disadvantages by original formulation techniques where a closed-form algorithm is derived by using exponential-form twist coordinates, instead of using approximations or local parameterizations such as Euler angels.

• The Journal of Korean Society for Radiation Therapy
• /
• v.16 no.1
• /
• pp.57-65
• /
• 2004

Introduction : The phantom that includes high density materials such as steel was custom-made to fix lung and bone in order to evaluation inhomogeneity correction at the time of conducting radiation therapy to treat lung cancer. Using this, values resulting from the inhomogeneous correction algorithm are compared on the 2 and 3 dimensional radiation therapy planning systems. Moreover, change in dose calculation was evaluated according to inhomogeneous by comparing with the actual measurement. Materials and Methods : As for the image acquisition, inhomogeneous correction phantom(Pig's vertebra, steel(8.21g/cm3), cork(0.23 g/cm3)) that was custom-made and the CT(Volume zoom, Siemens, Germany) were used. As for the radiation therapy planning system, Marks Plan(2D) and XiO(CMS, USA, 3D) were used. To compare with the measurement value, linear accelerator(CL/1800, Varian, USA) and ion chamber were used. Image, obtained from the CT was used to obtain point dose and dose distribution from the region of interest (ROI) while on the radiation therapy planning device. After measurement was conducted under the same conditions, value on the treatment planning device and measured value were subjected to comparison and analysis. And difference between the resulting for the evaluation on the use (or non-use) of inhomogeneity correction algorithm, and diverse inhomogeneity correction algorithm that is included in the radiation therapy planning device was compared as well. Results : As result of comparing the results of measurement value on the region of interest within the inhomogeneity correction phantom and the value that resulted from the homogeneous and inhomogeneous correction, gained from the therapy planning device, margin of error of the measurement value and inhomogeneous correction value at the location 1 of the lung showed $0.8\%$ on 2D and $0.5\%$ on 3D. Margin of error of the measurement value and inhomogeneous correction value at the location 1 of the steel showed $12\%$ on 2D and $5\%$ on 3D, however, it is possible to see that the value that is not correction and the margin of error of the measurement value stand at $16\%$ and $14\%$, respectively. Moreover, values of the 3D showed lower margin of error compared to 2D. Conclusion : Revision according to the density of tissue must be executed during radiation therapy planning. To ensure a more accurate planning, use of 3D planning system is recommended more so than the 2D Planning system to ensure a more accurate revision on the therapy plan. Moreover, 3D Planning system needs to select and use the most accurate and appropriate inhomogeneous correction algorithm through actual measurement. In addition, comparison and analysis through TLD or film dosimetry are needed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.7
• /
• pp.84-91
• /
• 2017

This study was performed using Somatom Definition Flash (Siemens, Enlarge, Germany) and GE 64-MDCT (Discovery 750 HD, GE HEALTHCARE, Milwaukee, USA.) using high-density medical materials that (are indispensable to?) computed tomography. We analyzed quantitatively the rate of change of the CT number of the CT reconstruction images by means of the IMAR and MAR algorithms using the phantom images acquired after scanning and previously captured raw data images. As a result, it was shown that the IMAR and MAR algorithms provided if ferent phantom images in the case of all medical high-density materials (p <0.05). The black streak artifacts were analyzed using the MAR and IMAR algorithms to determine if they corresponded to stainless steel materials (p>0.05). Also, it was found that the application of the IMAR algorithm affects the attenuation deviation, because there is a change in the image CT number compared to that before. The results suggest that, in the future, after the implant procedure, it would be useful to observe the surgical site and surrounding tissues during follow-up CT scans.

• Progress in Medical Physics
• /
• v.12 no.2
• /
• pp.177-184
• /
• 2001

The goal of radiation treatment is to deliver a prescribed radiation dose to the target volume accurately while minimizing dose to normal tissues. Due to inaccurate placement of field and shielding block and patient's movement, there could be displacement errors between the planed and treatment regions. In order to verify the location of radiation treatment, we in this study developed the registration algorithm of the x-ray simulator images and portal images and quantified the inaccuracy in terms of shift, scale and rotation. The algorithm for registration of pairs of radiation fields consists of the alignment of pairs of radiation images by points matching and field displacement analysis by field boundary matching. In the first step, paired surface landmarks are matched to calculate the transformation parameters (scale, rotation and shift) using the corresponding line pairs which are created by connecting two landmarks of each image. In the next step, portal field boundary is extracted and then the two field boundaries are matched by the $\rho$-$\theta$ technique. Applying the phantom portal images, detection errors were calculated to be less than 2mm in translation, 1$^{\circ}$ in rotation and 1% in scale. In conclusion, we quantitatively analyzed the displacement error of x-ray simulator images and portal images. The present results could contribute to the study of the radiation treatment verification.

• The KIPS Transactions:PartB
• /
• v.16B no.2
• /
• pp.131-140
• /
• 2009

This paper presents a new algorithm to the segmentation of the FISH images. First, for segmentation of the cell nuclei from background, a threshold is estimated by using the gaussian mixture model and maximizing the likelihood function of gray value of cell images. After nuclei segmentation, overlapped nuclei and isolated nuclei need to be classified for exact nuclei analysis. For nuclei classification, this paper extracted the morphological features of the nuclei such as compactness, smoothness and moments from training data. Three probability density functions are generated from these features and they are applied to the proposed Bayesian networks as evidences. After nuclei classification, segmenting of overlapped nuclei into isolated nuclei is necessary. This paper first performs intensity gradient transform and watershed algorithm to segment overlapped nuclei. Then proposed stepwise merging strategy is applied to merge several fragments in major nucleus. The experimental results using FISH images show that our system can indeed improve segmentation performance compared to previous researches, since we performed nuclei classification before separating overlapped nuclei.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.2
• /
• pp.163-171
• /
• 2014

Based on the GPS/IMU integration, the car navigation has unstable conditions as well as drastically reduces accuracies in urban region. Nowadays, many cars mounted the camera to record driving states. If the ground coordinates of street furniture are known, the position and attitude of camera can be determined through SPR(Single Photo Resection). Therefore, an estimated position and attitude from SPR can be applied measurements in Kalman filter for updating errors of navigation solutions from GPS/IMU integration. In this study, the GPS/IMU/SPR integration algorithm was developed in loosely coupled modes through extended Kalman filters. Also, in order to analyze performances of GPS/IMU/SPR, simulation tests were conducted in GPS signal reception environments and the GCPs (Ground Control Points) distributions. In fact, the position and attitude gathered from GPS/IMU/SPR integration are more precise than the position and attitude from GPS/IMU integration. When IPs (image points), corresponded to GCPs, were concentrated in the center of image, the position error in the optical axis respectively increased. To understand effects from SPR, we plan to carry additional test on the magnitude of GCP, IP and initial exterior orientation errors.