• Progress in Medical Physics
• /
• v.24 no.2
• /
• pp.99-107
• /
• 2013

The surgical resection was occurred mainly in liver metastasis before the development of radiation therapy techniques. Recently, Radiation therapy is increased gradually due to the development of radiation dose delivery techniques. 18F-FDG PET image showed better sensitivity and specificity in liver metastasis detection. This image modality is important in the radiation treatment with planning CT for tumor delineation. In this study, we applied automatic image segmentation methods on PET image of liver metastasis and examined the impact of image factors on these methods. We selected the patients who were received the radiation therapy and 18F-FDG PET/CT in Korea Cancer Center Hospital from 2009 to 2012. Then, three kinds of image segmentation methods had been applied; The relative threshold method, the Gradient method and the region growing method. Based on these results, we performed statistical analysis in two directions. 1. comparison of GTV and image segmentation results. 2. performance of regression analysis for relation between image factor affecting image segmentation techniques. The mean volume of GTV was $60.9{\pm}65.9$ cc and the $GTV_{40%}$ was $22.43{\pm}35.27$ cc, and the $GTV_{50%}$ was $10.11{\pm}17.92$ cc, the $GTV_{RG}$ was $32.89{\pm}36.8$4 cc, the $GTV_{GD}$ was $30.34{\pm}35.77$ cc, respectively. The most similar segmentation method with the GTV result was the region growing method. For the quantitative analysis of the image factors which influenced on the region growing method, we used the standardized coefficient ${\beta}$, factors affecting the region growing method show GTV, $TumorSUV_{MAX/MIN}$, $SUV_{max}$, TBR in order. The result of the region growing (automatic segmentation) method showed the most similar result with the CT based GTV and the region growing method was affected by image factors. If we define the tumor volume by the auto image segmentation method which reflect the PET image parameters, more accurate and consistent tumor contouring can be done. And we can irradiate the optimized radiation dose to the cancer, ultimately.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.6
• /
• pp.251-256
• /
• 2019

A capsule endoscopy is a medical device that can capture an entire digestive organ from the esophagus to the anus at one time. It produces a vast amount of images consisted of about 8~12 hours in length and more than 50,000 frames on a single examination. However, since the analysis of endoscopic images is performed manually by a medical imaging specialist, the automation requirements of the analysis are increasing to assist diagnosis of the disease in the image. Among them, this study focused on automatic detection of polyp images. A polyp is a protruding lesion that can be found in the gastrointestinal tract. In this paper, we propose a weighted-image generation method to enhance the polyp image learning by multi-scale analysis. It is a way to extract the suspicious region of the polyp through the multi-scale analysis and combine it with the original image to generate a weighted image, that can enhance the polyp image learning. We experimented with SVM and RF which is one of the machine learning methods for 452 pieces of collected data. The F1-score of detecting the polyp with only original images was 89.3%, but when combined with the weighted images generated by the proposed method, the F1-score was improved to about 93.1%.

• Journal of East-West Nursing Research
• /
• v.8 no.1
• /
• pp.113-125
• /
• 2003

This study is a descriptive investigation into the image of nurses, and attempted to help to advance the profession of nursing and to provide basic data for developing strategies to improve the image of nurses. The Subject of this study was a group of 380 persons from a K Medical Centre in Seoul, including the hospital patients and their guardians, as well as the doctors, assistants and hospital administrative staff. The data have been collected from the 10th to the 30th of May, 2003. We have developed a research tool of 40 questions divided into three categories using a tool developed by Kim, H.J and KIm, H.O.(2001) verifying its construct validity. The reliability of the tool was Cronbache's ${\alpha}=.97$, and by categories, Cronbach's ${\alpha}=.86$ for service image, Cronbach's ${\alpha}=.96$ for professional image and Cronbache's ${\alpha}=.90$ for social image. The collected data have been analysed according to the purpose of this study using SPSS WIN 11.0 for real number, percentage, factors analysis, multiple regression analysis, ANOVA and $x^2$-test, and the results are as follows: 1) There was a significant difference in the image of nurses by job series of the subjects; from patients and guardians for 4.01 to doctors 3.62, assistants 3.54 and staff members 3.41 (F=36.14, p=.000). As well, there was a significant difference in service, professional and social image categories according to the position of the subjects ($F=20.36{\sim}42.35$, p=.000). 2) The main factors that affect on formation the nurse's imaging came by direct experiences with nurses at hospitals for 81.3%, by looking at the every life of the nurses that the subjects personally know for 15.5%, by mass media for 1.6% and by the accounts from the others for 1.6%. 3) 78.4% of the subjects considered that the image of nurses on mass media is described better than for real, 8.2% believed that the image is described worse than for real, and only 13.2% of the subjects perceived that the image of nurses on mass media corresponds the image of nurses in actual life. 4) 74.5% of the subjects said that they got a better image of nurses after their hospitalization while 2% got a worse one and 23.5% said to have had no changes, and the period of hospitalization had no relevance to the image of nurses (X2=5.04, P=.489). However, while 16.8% of the subjects who spent less than one week in hospital said that they got a better image of nurses, 27.5% of those who spent longer than four weeks got a better image of nurses. 5) There was a significant difference in the total image points of nurses by the patients and their guardians according to the period of hospitalization; 4.14 for 1 to 2 weeks, 4.07 for 2 to 4 weeks, 4.02 for 4 weeks and longer and 3.80 for less than a week (F=3.40, P=.019). Upon the results stated above, I should like to propose as below: 1) An investigative enquiry is needed to improve the image of nurses as though being a nurse is very hard and difficult. 2) A continuous monitoring in mass media is needed to create a positive image of nurses.

• Journal of Korean Society for Quality Management
• /
• v.41 no.4
• /
• pp.541-553
• /
• 2013

Purpose: This study intends to offer strategic implications that can be used in emergency medical service of large-size hospital through analysis of causal relationship among factors such as emergency medical service, patient value, patient satisfaction and reuse intention. Methods: Differential model was introduced to test causal relationship. Questionnaire was developed, and data was collected and analyzed with Structural Equation Modeling. Results: As a result of empirical analysis, we found that emergency medical service qualities of general hospital could be six components. Image of hospital, medical facilities, and attitude of medical staff are positively related to patient satisfaction and reuse intention. Conclusion: This study offers practical implications to relevant managers, at the same time it has limitations to be solved through additional study in future.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.16 no.1
• /
• pp.19-22
• /
• 2005

Background and Objectives : While considerable progress has been made in enhancing the quality of laryngoscopy and image processing, the evaluation of laryngeal erythema is still based on the clinician's judgement. The purpose of this study is to quantitatively measure the degree of erythema and to examine the relationship with clinical grading. Materials and Methods : Color images of larynx from 100 subjects were captured from video-documented examinations of laryngoscopy. The amount of erythema within the digitized larynx image was quantified using software developed and was compared with a grading system (0 to 3 scale) based on visual inspection by 4 experienced clinicians. The results were compared by deriving Kappa, Kendall and Spearman statistic. Results : There was high intra-observer(R=0.402-0.755) and inter-observer correlation (R=0.789). Among parameters, the red composite value had most remarkable agreement with clinical grading(R=0.827). Conclusion : The result suggest that the computer based analysis of laryngeal erythema can provide quantiative data on degree of erythema and the basis for further development of an expert system.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.457-460
• /
• 2002

The image quality of three-dimensional (3D) images has been widely investigated by the qualitative analysis method. A need remains for an objective and quantitative method to assess the image quality of 3D volume-rendered images. The purpose of this study was to evaluate the quantitative accuracy of distance measurements on 3D volume-rendered images of a dry human skull by using multi-detector computed tomography (MDCT). A radiologist measured five times the twenty-one direct measurement line items composed among twelve reference points on the skull surface with a digital vernier caliper. The water filled skull specimen was scanned with a MDCT according to the section thicknesses of 1.25, 2.50, 3.75, and 5.00 mm for helical (high quality; pitch 3:1) scan mode. MDCT data were reconstructed with its acquisition section thickness and with 1.25 mm section thickness for all scans. An observer also measured seven times the corresponding items on 3D volume-rendered images with measuring tools provided by volumetric analysis software. The quantitative accuracy of distance measurements on the 3D volume-rendered images was statistically evaluated (p-value < 0.05) by comparatively analyzing these measurements with the direct distance measurements. The accuracy of distance measurements on the 3D volume-rendered MDCT images acquired with 1.25, 2.50, 3,75 and 5.00 mm section thickness and reconstructed with its section thickness were 48%, 33%, 23%, and 14%, respectively. Meanwhile, there were insignificant statistical differences in accuracy of distance measurements among 3D volume-rendered images reconstructed with 1.25 mm section thickness for the each acquisition section thickness. MDCT images acquired with thick section thickness and reconstructed with thin section thickness in helical scan mode should be effectively used in medical planning of 3D volume-rendered images. The quantitative analysis of distance measurement may be a useful tool for evaluating the quantitative accuracy and the defining optimal parameters of 3D volume-rendered CT images.

• Journal of Biomedical Engineering Research
• /
• v.10 no.2
• /
• pp.106-108
• /
• 1989

A new method of digital image analysis technique for discrimination of cancer cell was presented in this paper. The object image was the Thyroid eland cells image that was diagnosed as normal and abnormal (two types of abnormal: follicular neoplastic cell, and papillary neoplastic cell), respectively. By using the proposed region segmentation algorithm, the cells were segmented into nucleus. The 16 feature parameters were used to calculate the features of each nucleus. A9 a consequence of using dominant feature parameters method proposed in this paper, discrimination rate of 91.11% was obtained for Thyroid Gland cells.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.9
• /
• pp.802-812
• /
• 2013

Recently, Capsule Endoscope(CE) system is receiving great attention as a innovative convergence technology that allows doctors to examine the digestive tract of a human body in the minimum invasive way. Once patients swallow the vitamin pill-sized capsule, doctors can detect disease such as blood-based abnormalities, polyps, ulcers, and Crohn's disease through the image information delivered by wireless or human body communication module in CE. Although CE is really a innovative technology, it still suffers from some drawbacks in terms of correct diagnosis of lesion and analysis required time. Due to the massive images approximately 60~120 thousand frames taken by miniature camera in the CE, doctors spend too much time examining the images and analyzing the lesions. Therefore, to lighten the burden of doctors, software tools for fast diagnosis and medical image processing techniques for correct diagnosis of lesion are essential in CE system. In this paper, we investigate the latest trends of diagnosis tools and image processing techniques based on major makers of CE systems, which are hardly known to the general public.

• Progress in Medical Physics
• /
• v.28 no.1
• /
• pp.22-26
• /
• 2017

We have developed an analytic software that can easily analyze the spot position and width of proton beam therapy nozzles in a periodic quality assurance. The developed software consists of an image processing method that conducts an analysis using center-of-spot geometry and a Gaussian fitting method that conducts an analysis through Gaussian fitting. By using the software, an analysis of 210 proton spots with energies 150, 190, and 230 MeV showed a deviation of approximately 3% from the mean. The software we developed to analyze proton spot positions and widths provides an accurate analysis and reduces the time for analysis.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1207-1212
• /
• 2018

The ultrasound image uses ultrasonic pulses to receive the reflected waves and construct an image necessary for diagnosis. At this time, when the signal becomes weak, noise is generated and a slight difference in brightness occurs. In addition, fluctuation of image due to breathing phenomenon, which is the characteristic of ultrasound image, and change of motion in real time occurs. Such a noise is difficult to recognize and diagnose visually in the analysis process. In this paper, morphological features are automatically extracted by using image processing technique on ultrasound acquired images. In this paper, we implemented a GPU - based fast filter using a cloud big data processing platform for image processing. In applying the GPU - based high - performance filter, the algorithm was run with performance 4.7 times faster than CPU - based and the PSNR was 37.2dB, which is very similar to the original.