• Journal of the Korean Society of Radiology
• /
• v.1 no.2
• /
• pp.23-30
• /
• 2007

This paper presents a method of generating 3-dimensional images by preprocessing 2-dimensional abdominal images obtained using CT (computed tomography) and MRI (magnetic resonance imaging) through segmentation, threshold technique, etc. and apply the method to virtual endoscopy. Three-dimensional images were visualized using indirect volume rendering, which can render at high speed using a general-purpose graphic accelerator used in personal computers. The algorithm used in the rendering is Marching Cubes, which has only a small volume of calculation. In addition, we suggested a method of producing 3-dimensional images in VRML (virtual reality modeling language) running on the Web browser without a workstation or an exclusive program. The number of nodes, the number of triangles and the size of a 3-dimensional image file from CT were 85,367, 174,150 and 10,124, respectively, and those from MRI were 34,029, 67,824 and 3,804, respectively.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.702-709
• /
• 2010

The performance of mass segmentation is greatly influenced by an initial position of a mass. Some researchers performed mass segmentation with the initial position of a mass given by radiologists. The purpose of our research is to find the initial position for mass segmentation and to notify the segmented mass to radiologists without any additional information on mammograms. The proposed system consists of breast segmentation by region growing and opening operations, decision of an initial seed with characteristics of masses, and mass segmentation by a level set segmentation. A seed for mass segmentation is set based on mass scoring measure calculated by block-based variances and masked information in a sub-sampled mammogram. We used a DDSM database to evaluate the system. The accuracy of mass detection is 78% sensitivity at 4 FP/image, and it reached 92% if multiple views for masses were considered.

• Journal of the Korean Society of Radiology
• /
• v.8 no.1
• /
• pp.27-33
• /
• 2014

Medical imaging has increased rapidly in the increase of interest in health, with the development of computer technology, digitization of medical imaging is rapidly advancing, PACS has been introduced to the medical field. Increase in the production of medical images by these phenomena made increased the workload of radiologist who must read a medical image. in response to the need for secondary diagnosis using a computer, The term of CAD in medical radiology field was introduced. In this study, we have proposed a CAD algorithm for the interpretation of the image obtained by the digital X-ray mammography equipment. The experiments were performed by programmed in Visual C++ for the proposed algorithm. A result of the execution of the CAD algorithm seven sample images, the results of five samples was confirmed in breast cancer and benign tumors, both the images sample was error processing. If you use a program that implements this with the algorithm proposed in this study it is helpful to reading breast images, and it is considered to contribute significantly to the early detection of breast cancer.

• Radiation Oncology Journal
• /
• v.5 no.2
• /
• pp.169-172
• /
• 1987

Currently, many computer systems are used in many areas of medicine including radiation oncology. For the most part, the computer system has proved to be useful in radiotherapeutic planning and dose calculation. There has been attempts to develop computer system including information management of patients, patient tracing, and office automation in radiation oncology department. But some of these available commercial systems have shortcomings. We developed a management system of patients in our radiation oncology department that integrated most of items for the evaluation of patents. In particular, the data were stored in a natural language (noncoded) and made themselves easily understandable by all clinical groups. In addition , the data could be isolated in files from which the computer could generate graphs and static data by the use of some simple commands. The system provided us with not only the functions of case review but functions of preparation of conferences, lectures and resident teaching.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.179-181
• /
• 2023

본 논문에서는 GAN 기반의 영상 생성 방법론을 이용해 delayed PET 영상을 생성하는 연구를 수행하였다. PET은 양전자를 방출하는 방사성 동위원소를 표지한 방사성의약품의 체내 분포를 시각화함으로서 암 세포 진단에 이용되는 의료영상 기법이다. 하지만 PET의 스캔 과정에서 방사성의약품이 체내에 분포하는 데에 걸리는 시간이 오래 걸린다는 문제점이 존재한다. 따라서 본 연구에서는 방사성의약품이 충분히 분포되지 않은 상태에서 얻은 PET 영상을 통해 목표로 하는 충분히 시간이 지난 후에 얻은 PET 영상을 생성하는 모델을 GAN (generative adversarial network)에 기반한 image-to-image translation(I2I)를 통해 수행했다. 특히, 생성 전후의 영상 간의 영상 쌍을 고려한 paired I2I인 Pix2pix와 이를 고려하지 않은 unpaired I2I인 CycleGAN 두 가지의 방법론을 비교하였다. 연구 결과, Pix2pix에 기반해 생성한 delayed PET 영상이 CycleGAN을 통해 생성한 영상에 비해 영상 품질이 좋음을 확인했으며, 또한 실제 획득한 ground-truth delayed PET 영상과의 유사도 또한 더 높음을 확인할 수 있었다. 결과적으로, 딥러닝에 기반해 early PET을 통해 delayed PET을 생성할 수 있었으며, paired I2I를 적용할 경우 보다 높은 성능을 기대할 수 있었다. 이를 통해 PET 영상 획득 과정에서 방사성의약품의 체내 분포에 소요되는 시간을 딥러닝 모델을 통해 줄여 PET 이미징 과정의 시간적 비용을 절감하는 데에 크게 기여할 수 있을 것으로 기대된다.

• Progress in Medical Physics
• /
• v.8 no.1
• /
• pp.17-24
• /
• 1997

We developed PC-based planning system for linear accelerator based stereotactic radiosurgery. The system was developed under Windows 95 on Pentium Pro$\^$(R) 200 ㎒ IBM PC with 128 MB RAM. It was programed using IDL$\^$(R)/ of Research Systems, Inc. as a programing tool. CT image data obtained with BRW stereotactic frame is transferred to PC through magnetoptical disk. As loading the image, the system automatically recognizes the location of rods and establishes stereotactic coordinates. It accurately calculates and corrects the coordinates, degree of tilting, and magnification rate of axial images. After the coordinates is defined we can delineate and edit the contours of target and organs of interest on axial images. Upon delineating contours of target, isocenter is determined automatically and we can set up the beam configuration for radiosurgery. The system provides beam's eye view and room's eye view for efficient confuguring of beams. The system calculates dose distribution 3-dimensionally. It takes 1 to 2 minutes to calculate dose distribution for 5 arcs. We can verify the dose distribution on serial axial images. We can analyze the dose distribution quantitatively by evaluation of dose-volume histogram of target and organ of interest. This system, PC-based radiosurgery planning system, includes the basic features for radiosurgery planning and calculates dose distribution within reasonable time for clinical application.

• The korean journal of orthodontics
• /
• v.32 no.1 s.90
• /
• pp.59-69
• /
• 2002

The purpose of this study was to evaluate the reproducibility of lateral cephalometric landmarks according to radiographic image enhancement, and to contribute to the identification of cephalometric landmarks. Lateral cephalograms of ten individuals were taken and stored into computer. The images were then enhanced up to four grades by Quick Ceph Image Pro$^{TM}$ on condition that the gray-scale equalization number was 50 and the detail enhancement number was 50. After thirty two landmarks were identified on monitor images by five observers, the deviations from the mean, the distances estimated between identified points and the mean point of five identified points, were evaluated for each landmark at each enhancement grade. Through the statistical analysis, following results were obtained. 1. In case of unenhanced radiographic images, the inter-observer reproducibility of the landmarks showed a large variation. 2. The comparison of deviation from the mean according to the degree of radiographic image enhancement for each landmark showed that the inter-observer reproducibility was significantly different at 5 landmarks. 3. The landmark of pterygomaxillary fissure showed higher reproducibility at enhancement grade 1 and 2 images than at unenhanced images. So did the landmark of posterior nasal spine at enhancement grade 1 images, and the landmark of menton at enhancement grade 2, 3 and 4 images respectively. The above results suggest that the reproducibility of some landmarks can be increased by radiographic image enhancement during the identification of the lateral cephalometric landmarks on the monitor.

• Journal of Yeungnam Medical Science
• /
• v.18 no.1
• /
• pp.123-137
• /
• 2001

Background: The purpose of this study is to evaluate the accuracy of measurements obtained from 3-dimensional computerized tomography and 3-dimensional cephalogram constructed by using the frontal and lateral cephalogram of six human dry skulls. Materials and Methods: After CT scans and each cephalograms were taken, 3-dimensional coordinates (X, Y, Z) of landmarks were obtained using computer programs. In this study, the accuracy of both methods were determined by means of 14 linear measurements compare with caliper measurements. Results: The standard deviation of landmarks of 3-dimensional CT and 3-dimensional cephalogram were 0.23 mm, and 0.30 mm in X axis, 0.27 mm and 0.25 mm in Y axis, and 0.27 mm and 0.31 mm in Z axis. In both methods, the standard deviation were less than 0.5 mm in all landmarks, and the most of landmarks showed less than 1 mm in range. Concerning the accuracy, the mean difference between 3-dimensional CT and manual measurements was 0.33 mm, and 1.13 mm between 3-dimensional cephalogram and manual measurements. The distance between RGo and LGo showed the largest difference (2.03 mm). There were highly significant, and large correlation with manual measurements in both methods (p<0.01). Conclusion: It is concluded that closeness of repeated measures to each skulls reveal the precision of both methods. Computerized tomography and cephalogram for 3-dimensional measurement of maxillofacial structure are equivalent in quality to caliper measurements.

• Journal of the Korean Society of Radiology
• /
• v.12 no.6
• /
• pp.793-799
• /
• 2018

As interest in artificial intelligence has increased, artificial intelligence has been actively studied in the medical field. In Korea, artificial intelligence has been applied to medical imaging devices such as X-ray imaging, Computer Tomography and Magnetic Resonance Imaging and artificial intelligence capable of acquiring radiation images of patients without radiologists in the future Medical devices are expected to be invented. This study was an initial study on the automation of patient positioning in X - ray imaging. We used x-ray equipment and human phantoms to evaluate the positioning. The program used Visual Studio 2010 MFC and the image was in the size $1450{\times}1814$. The pixel values were converted to contrasts with values of 0 to 255 that can be visually recognized and output to the monitor. We developed a procedure algorithm program that predicts the angle of the output image through three pixel coordinate values and induces the patient to perform correct positioning according to the voice guidance according to the angle. In the next study, we will study the artificial intelligence to grasp the structure itself and calculate the angle, rather than conveying the reference of coordinates to artificial intelligence. In the future, it is expected that it will be helpful in the study of artificial intelligence from shooting to positioning through the automation of positioning.

• Journal of Veterinary Clinics
• /
• v.29 no.6
• /
• pp.488-493
• /
• 2012

Two Maltese (2-year-old, intact female and 4-month-old, intact female) and a Pekingese (10-year-old, intact male) dogs were referred due to vomiting, anorexia, head-pressing and hypersalivation. Physical examinations, complete blood count, serum chemical analysis, radiography, ultrasonography and computed tomography (CT) were evaluated. Laboratory findings in these dogs included high hepatic enzyme, serum bile acid and ammonia concentration. Microhepatia was found on abdominal radiographs in two dogs. The existence of portosystemic shunt was presented in abdominal ultrasonography. The shunt vessel was identified in all dogs by CT imaging. Based on three-dimensional CT reconstruction, the origin and termination of each shunt vessel were defined certainly. In consequence, each dog was diagnosed single extrahepatic portosystemic shunt. After diagnosis, surgical treatment was performed in all dogs. This case report describes clinical finding, imaging characteristics, and three-dimensional CT imaging of single extrahepatic portosystemic shunt cases.