• Journal of the Semiconductor & Display Technology
• /
• v.5 no.2 s.15
• /
• pp.19-25
• /
• 2006

This paper focuses on lossy medical image compression methods for medical images that operate on three-dimensional(3-D) irreversible integer wavelet transform. We offer an application of unbalanced tree structure algorithm to medical images, using a 3-D unbalanced wavelet decomposition and a 3-D unbalanced spatial dependence tree. The wavelet decomposition is accomplished with integer wavelet filters implemented with the lifting method. We have tested our encoder on volumetric medical images using different integer filters and coding unit sizes. The coding unit sizes of 16 slices save considerable dynamic memory(RAM) and coding delay from full sequence coding units used in previous works. If we allow the formation of trees of different lengths, then we can accomodate more transaxial scales than three. The encoder and decoder can then keep track of the length of the tree in which each pixel resides through the sequence of decompositions. Results show that, even with these small coding units, our algorithm with certain filters performs as well and better in lossy coding than previous coding systems using 3-D integer unbalanced wavelet transforms on volumetric medical images.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.517-520
• /
• 1999

In this paper, we propose a non-invasive method to estimate blood velocity from the real medical images. To measure the magnitude and direction components associated with the blood velocity, we apply the optical flow analysis algorithm. It is demonstrated that the accuracy of the blood velocity estimate could possibly be increased by segmenting the optical flow region. We call this the Region Optical Flow(ROF) algorithm. We carried out some preliminary experiments using the aorta medical images, and corresponding regional optical flow diagrams are provided.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2005.04a
• /
• pp.68-70
• /
• 2005

To precisely localize target in prostate cancer, image-guided radiotherapy was performed using the $ExacTrac^{\circledR}$ x-ray system (Brainlab, Germany) with implanted markers. For three prostate cancer patients, three gold markers were implanted into prostate. Orthogonal portal images were acquired every treatment and CT scans were repeated 3～5 times during the course of treatment. After correcting setup errors calculated by the system, the position of the implanted markers and the distance between them were detected in daily portal images and in CT images, and analyzed retrospectively. Deviation of the relative position of the implanted markers and the distance between them were less than 1 mm in lateral, longitudinal, and vertical direction for three patients, both in portal images and CT images. This study reveals that image-guided radiotherapy using the $ExacTrac^{\circledR}$ system is useful to verify positioning errors and localize prostate target with implanted markers, reducing the planning target volume (PTV) margin as well as irradiation to rectum and bladder.

• Korean Journal of Radiology
• /
• v.20 no.6
• /
• pp.976-984
• /
• 2019

Objective: To establish diagnostic criteria for pulmonary arterial hypertension (PAH) in children by using parameters obtained through noninvasive cardiac computed tomography (CCT). Materials and Methods: We retrospectively measured parameters from CCT images of children from a single institution in a multiple stepwise process. A total of 208 children with mean age of 10.5 years (range: 4 days-18.9 years) were assessed. The variables were classified into three groups: the great arteries; the ventricular walls; and the bilateral ventricular cavities. The relationship between the parameters obtained from the CCT images and mean pulmonary arterial pressure (mPAP) was tested and adjusted by the children's body size. Reference curves for the pulmonary trunk diameter (PTD) and ratio of diameter of pulmonary trunk to ascending aorta (rPTAo) of children with CCT images of normal hearts, adjusted for height, were plotted. Threshold lines were established on the reference curves. Results: PTD and rPTAo on the CCT images were significantly positively correlated with mPAP (r > 0.85, p < 0.01). Height was the body size parameter most correlated with PTD (r = 0.91, p < 0.01) and rPTAo (r = -0.69, p < 0.01). On the basis of the threshold lines on the reference curves, PTD and rPTAo both showed 88.9% sensitivity for PAH diagnosis, with negative predictive values of 93.3% and 92.9%, respectively. Conclusion: PTD and rPTAo measured from CCT images were significantly correlated with mPAP in children. Reference curves and the formula of PTD and rPTAo adjusted for height could be practical for diagnosing PAH in children.

• Journal of the Korean Society of Radiology
• /
• v.1 no.2
• /
• pp.13-22
• /
• 2007

The purpose of this study was to survey a development of the wireless transmission system of medical images for ubiquitous medicine. There have been many changes in medical equipments and medical record medical treatment and medical record within hospital and PACS(Picture Archiving Communication System) which is picture management system for patients can be typical cases. It is difficult to use these automated medical systems unless they are within hospital and in case of rapid image reading in the emergency cases or in absence of doctor, it is difficult to perform it immediately. The present study implemented an image transmission system using CDMA connection so that images in the server can be viewed at any time and in any place. Remote wireless diagnosis based on medical images using PDA is applicable to medical areas that require mobility, and the use of PDA can be an ideal alternative for point of care. The use of PDA enables prompt and accurate access to digital medical images, which in turn reduces medical accidents and improves the quality of medical services through high productivity and efficiency of medical practitioners' works. It also enables quick response to patients' demands and high-quality medical services and, consequently, patients' high satisfaction.

• Journal of radiological science and technology
• /
• v.25 no.2
• /
• pp.57-64
• /
• 2002

The recent development of embodiment technology of the medical images makes most medical institutions introduce PACS(Picture Archiving and Communication System) in haste. However lots of PACS solutions, currently developed and distributed, haven't been able to serve the convenience of users and to satisfy user's demand because of economic limitations and administrator-oriented considerations in the process of development. So we have developed MIH(Medical Image History), by which we can search and refer to the patient's medical images and information with few restrictions of time and space for diagnosis and treatment. This program will contribute to the improvement in the medical environment and meet the clients' need. We'll make more effort to develop the application which insures the better quality of medical images. MIH manages the patient's image files and medical records like film chart in connection with time. This trial will contribute to the reduction of the economical loss caused by unnecessary references and improve the quality in the medical services. The demand on the development or the program which refers to the medical +ata quickly and keeps them stable will be continued by the medical institute. This will satisfy the client's demand and improve the service to the patients in that tile program will be modified from the standpoint of the users. MIH is trying to keep user-oriented policy and to apply the benefit of the analog system to the digital environment. It is necessary to lead the public to the better understanding that the systematic management and referring of the medical images is as important as the quality of the images.

• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.167-174
• /
• 2021

The purpose of this study is to classify TIFF images, PNG images, and JPEG images using deep learning, and to compare the accuracy by verifying the classification performance. The TIFF, PNG, and JPEG images converted from chest X-ray DICOM images were applied to five deep neural network models performed in image recognition and classification to compare classification performance. The data consisted of a total of 4,000 X-ray images, which were converted from DICOM images into 16-bit TIFF images and 8-bit PNG and JPEG images. The learning models are CNN models - VGG16, ResNet50, InceptionV3, DenseNet121, and EfficientNetB0. The accuracy of the five convolutional neural network models of TIFF images is 99.86%, 99.86%, 99.99%, 100%, and 99.89%. The accuracy of PNG images is 99.88%, 100%, 99.97%, 99.87%, and 100%. The accuracy of JPEG images is 100%, 100%, 99.96%, 99.89%, and 100%. Validation of classification performance using test data showed 100% in accuracy, precision, recall and F1 score. Our classification results show that when DICOM images are converted to TIFF, PNG, and JPEG images and learned through preprocessing, the learning works well in all formats. In medical imaging research using deep learning, the classification performance is not affected by converting DICOM images into any format.

• The Korean Journal of Nuclear Medicine
• /
• v.26 no.2
• /
• pp.274-279
• /
• 1992

Clinical role of $^{99m}Tc-MIBI$ myocardial scintigraphy in the diagnosis of coronary artery disease (CAD) is now well accepted, however, the role of it in the identification of viable myocardium in patients with chronic CAD has not yet been clarified. To determine the usefulness of rest-injected $^{99m}Tc-MIBI$ scan as a marker of myocardial viability, the regional uptake of this agent at rest was compared with that of $^{201}Tl$ on reinjection and 24 hours after reinjection images. Subject patients were 13 chronic CAD patients who showed irreversible perfusion defect(s) on standard pharmacologic (dipyridamole) stress-redistribution images. Immediately after the redistribution images were obtained, 37 MBq thallium was injected at rest, and images were reacquired at 10 minutes and 24 hours after reinjection. After then 740 MBq $^{99m}Tc-MIBI$ was injected, and 1 hour later rest MIBI myocardial imaging was performed. Five sets of imagestress, redistribution, reinjection, delayed images of thallium, and rest image of MIBI) were then analyzed qualitatively and quantitatively. Left ventricle was arbitrarily divided into 9 segments (apex, basal and apical portions of anterior, septal, inferior, and lateral walls). Seven patients and 30 regions showed a fixed perfusion defect on the stress-redistribution images. Among 30 regions, 15 showed positive uptakes and 6 showed negative uptakes on both $^{201}Tl$ reinjection/delayed images and $^{99m}Tc-MIBI$ rest images. Five regions showed only thallium uptake and were regarded as viable clinically. Of four regions which showed only $^{99m}Tc-MIBI$ uptake, two were regarded as viable, while the other two were regarded as a nonviable scar tissue clinically. In conclusion, $^{201}Tl$ reinjection technique was more reliable in the identification of viable myocardium. However, the role of $^{99m}Tc-MIBI$ in identification of viable myocardium was still remained to be clarified because 2 of 9 regions showed only $^{99m}Tc-MIBI$ uptake and were regarded as viable tissues.

• Journal of Korea Multimedia Society
• /
• v.12 no.12
• /
• pp.1701-1709
• /
• 2009

The mobile terminal system plays a key role in medical industries which require in fast and accurate diagnosis from heterogeneous acquisition equipment. The demand for PACS (picture archiving and communication systems) has continued to increase in major hospitals and private clinics. Patient care depends on how fast the medical imaging system provides images and how accurately the images are interpreted by physicians. In this paper, we propose an efficient method to decipher the hundreds of images required by physicians to accurately diagnose patients. By exploring Motion- JPEG (M-JPEG), this paper has demonstrates the possibilities for efficient management of medical images with a newly designed image file format and improvement in imaging diagnoses through the replaying of moving pictures of a patient in a mobile environment.

• Journal of information and communication convergence engineering
• /
• v.2 no.3
• /
• pp.167-171
• /
• 2004

The evolution of modern imaging modalities, followed by the rapid development of computer technology has introduced many new features in the communication networks used in medical facilities. Since it is very important to keep patient's record accurately, the ability to exchange medical data securely over the communication network is essential for any medical information. In this paper, therefore, we introduce some problems which occur from digitizing medical images such as MRI (Magnetic Resonance Imaging), CT (Computed Tomography), CR(Computed Radiography), etc., and then we propose a authentication mechanism for medical image verification using secret watermark images.