• Journal of Biomedical Engineering Research
• /
• v.42 no.5
• /
• pp.241-249
• /
• 2021

Recently, artificial intelligence for diagnosis system of obstetric diseases have been actively studied. Artificial intelligence diagnostic assist systems, which support medical diagnosis benefits of efficiency and accuracy, may experience problems of poor learning accuracy and reliability when inappropriate images are the model's input data. For this reason, before learning, We proposed an algorithm to exclude unread cervical imaging. 2,000 images of read cervical imaging and 257 images of unread cervical imaging were used for this study. Experiments were conducted based on the statistical method Radiomics to extract feature values of the entire images for classification of unread images from the entire images and to obtain a range of read threshold values. The degree to which brightness, blur, and cervical regions were photographed adequately in the image was determined as classification indicators. We compared the classification performance by learning read cervical imaging classified by the algorithm proposed in this paper and unread cervical imaging for deep learning classification model. We evaluate the classification accuracy for unread Cervical imaging of the algorithm by comparing the performance. Images for the algorithm showed higher accuracy of 91.6% on average. It is expected that the algorithm proposed in this paper will improve reliability by effectively excluding unread cervical imaging and ultimately reducing errors in artificial intelligence diagnosis.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.10
• /
• pp.715-723
• /
• 2009

The use of medical imaging in hospitals is being gradually increased as it is of utmost importance in treatment and diagnosis of patients. With the drastic increase of the usage of medical imaging in hospitals per day necessitates more speedy and accurate systems for precise diagnosis and the treatment. Hence the modality and development of network infrastructure are also need to be improved day by day and this trend may be continued. Thus there is a great need improvement of PACS concerned. In this paper, by using the computational grid technology, we design a medical image storage system that improve the compression speed, and implement a prototype as a part of PACS. We also demonstrate the performance improvement from experimental results of the prototype.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.18
• /
• pp.7769-7773
• /
• 2014

Background: Some tumor types are related to HIV, including non-Hodgkin lymphoma (NHL). The morbidity and mortality of NHL has remained high, even after highly active antiretroviral therapy (HAART) was introduced. We collected cases of AIDS with NHL, and evaluated the imaging features and strategies for diagnosis. Materials and Methods: There were 27 patients with AIDS and tumors confirmed by pathology. There were 9 patients with Burkitt lymphoma, 16 with diffuse large B cell lymphomas (DLBCLs), and 2 with primary central nervous system (PCNS) lymphomas. All of the patients underwent a series of imaging studies. Three radiologists analyzed the images, and any disagreement was discussed until consensus was reached. Results: The radiologic manifestations of AIDS with NHL were mainly masses and lymphadenopathy, 3 patients having one mass and 12 two or more masses. 7 patients had lymphadenopathy in one site and 3patients had lymphadenopathy in two or more sites. Coarse mucosal folds, thickening of the gastrointestinal wall, and lumen narrowing were typical manifestations of NHL within the gastrointestinal tract. There were 4 patients with masses and 5 with lymphadenopathy inthe 9 with Burkitt lymphoma, and 11 patients with masses 5 with lymphadenopathy in the 16 with DLBCLs. Conclusion: NHL is a malignancy that usually occurs in patients with AIDS. Imaging is an important method by which to evaluate lesions, masses, and lymphadenopathy. Fine needle aspiration biopsy and stereotaxis biopsy are useful methods by which to diagnose NHL.

• Journal of Radiopharmaceuticals and Molecular Probes
• /
• v.7 no.2
• /
• pp.93-98
• /
• 2021

meta-iodobenzylguanidine is one of the norepinephrine analogs and reuptakes together with norepinephrine with norepinephrine transporter. The radioiodinated ligand, ¹²³I-meta-iodobenzylguanidine, is the most widely used for single photon emission computed tomography imaging to diagnose functional abnormalities and tumors of the sympathetic nervous system. In this study, we performed cellular uptake studies of ¹²³I-meta-iodobenzylguanidine in positive- and negative-norepinephrine transporter cells in vitro to verify the uptake activity for norepinephrine transporter. After ¹²³I-meta-iodobenzylguanidine was injected via a tail vein into normal mice, Single photon emission computed tomography/computed tomography images were acquired at 1 h, 4 h, and 24 h post-injection, and quantified the distribution in each organ including the adrenal medulla as a norepinephrine transporter expressing organ. In vitro cell study showed that ¹²³I-meta-iodobenzylguanidine specifically uptaked via norepinephrine transporter, and significant uptake of ¹²³I-meta-iodobenzylguanidine in the adrenal medulla in vivo single photon emission computed tomography images. These results demonstrated that single photon emission computed tomography imaging with ¹²³I-meta-iodobenzylguanidine were able to quantify the biodistribution in vivo in the adrenal medulla in normal mice.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.32 no.5
• /
• pp.551-563
• /
• 2012

Medical ultrasound systems have been used since 1950s, and are now widely used in most hospitals as indispensable diagnostic imaging systems. Since array probe was introduced in 1970s, beamforming technology using electronic signal processing has been adopted to the medical ultrasound system, and has been improved. Beamforming is a important technology which defines the resolution of the ultrasound system. In this paper, the technologies are introduced from basic beamforming principles to current trend. They include principles of beamforming using array probe, basic theory, and practical implementation, and recent topics of synthetic aperture imaging, adaptive beamforming, 2-dimensional beamforming using 2-dimensional array are also introduced. These various technologies will improve system performances continuously by merging innovatively with various technologies in other fields.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.2
• /
• pp.163-170
• /
• 2010

Multi-planar reformatting(MPR) is a volume rendering technique which generates images of sectional planes users define, so that it is essential for medical imaging system. Due to the recent advances of medical imaging system, users require to place plural planes on a single dataset and to enable an individual and easy control for each plane. In this paper, we enumerate various user operations for recent MPR and analyze user requirements to update the plane equation. For the effective control of coordinate system, each plane is considered in a separated coordinate system and all informations which form a coordinate system are grouped into two components: the individual components and the common components. The proposed system is implemented on a graphics hardware, so that it smoothly performs MPR including recent requirements.

• Imaging Science in Dentistry
• /
• v.53 no.3
• /
• pp.269-269
• /
• 2023

• Korean Journal of Digital Imaging in Medicine
• /
• v.6 no.1
• /
• pp.19-23
• /
• 2003

In recent years, many computer systems that are used for patient diagnostic and treatment purpose s are being introduced within hospitals. Therefore, being in a position to manage the hospital entirely, efforts to integrate their own unique system into one have started. A system values humans and creates the surrounding atmosphere into one which maximizes the abilities of individuals. For this, a scientific integration management operation system is required. The type of system that is demanded due to this requirement is an ERP(Enterprise Resource Planning) system. Lately, even the hospital industry is beginning to show interest in efficient administrative methods. To deliver more predominant medical services, hospitals are trying to introduce scientific administrative methods, whose superiority were proven in enterprises, to the operation system of the hospital organization. ERP values humans over systems, and within a superior system, emphasizes the efficiency of the organization. This sort of process does not just evaluate and manage the working abilities of individuals, but provides an advanced working environment that increases the abilities of members within the organization by fold. Therefore, this research estimates through questionnaires and introductive cases how the introduction of ERP may change the work of customers within hospitals such as the radiologic technology department, and how it may also change the environment of medical services, thus striving to create a radiologic technology department that will not fall behind the times.

• Journal of Biomedical Engineering Research
• /
• v.26 no.4
• /
• pp.185-191
• /
• 2005

In this paper, we proposed a downscaled 3D object technique using medical images for telediagnostic use. The proposed system consisted of downscaling/thresholding processes for building a downscaled 3D object and a process for obtaining 2D images at specific angles for diagnosis support. We used 80 slices of Digital Imaging and Communication in Medicine(DICOM) CT images as sample images and the platform-independent Java language for the experiment. We confirmed that the total image set size and transmission time of the original DICOM image set using a down-scaled 3D object decreased approximately $99\%\;and\;98.41\%,$ respectively. With additional studies, the proposed technique obtained from these results will become useful in supporting diagnosis for home and hospital care.

• The Korean Journal of Pain
• /
• v.34 no.4
• /
• pp.427-436
• /
• 2021

Background: Pharmacological and non-pharmacological therapies have been used to treat patients with chemotherapy-induced peripheral neuropathy (CIPN). However, the effect of therapies in cancer patients has yet to be investigated comprehensively. We hypothesized that cyclic thermal therapy would improve blood flow and microcirculation and improve the symptoms driven by CIPN. Methods: The criteria of assessment were blood volume in region of interest (ROI) in the images, and European Organization for Research and Treatment of Cancer-Quality of Life Questionnaire-Chemotherapy-Induced Peripheral Neuropathy 20 questionnaire scores. The blood volume was quantified by using red blood cell (RBC) scintigraphy. All patients were treated 10 times during 10 days. The thermal stimulations, between 15° and 41°, were repeatedly delivered to the patient's hands. Results: The total score of the questionnaires, the score of questions related to the upper limbs, the score of questions closely related to the upper limbs, and the score excluding the upper limbs questions was decreased. The blood volume was decreased, and the variance of blood volume was decreased. During cooling stimulation, the blood volume was decreased, and its variance was decreased. During warming stimulation, the blood volume was decreased, and its variance was decreased. Conclusions: We suggest that cyclic thermal therapy is useful to alleviate CIPN symptoms by blood circulation improvement. RBC scintigraphy can provide the quantitative information on blood volume under certain conditions such as stress, as well as rest, in peripheral tissue.