• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.19 no.1
• /
• pp.43-46
• /
• 2008

Background and Objectives : Clinical suspicion and appropriate diagnostic procedures are essential for the timely management of extrapulmonary type of mycobacterial disease. In the hope of suggesting a suitable guideline for the early diagnosis of laryngeal tuberculosis, the authors reviewed their clinical pathways and the characteristics of patients with laryngeal tuberculosis who were managed in the recent 10 years at a single tertiary referral hospital, Samsung Medical Center. Subjects and Method : Retrospective chart review was performed for the 25 adult patients with laryngeal tuberculosis. Among 25 cases, 12 were pathologically confirmed by laryngeal biopsy and the other 13 were clinically diagnosed by cumulative clinical information; definite laryngitis on laryngoscopy, positive AFB (acid fast bacillus) smear/culture or active pulmonary tuberculosis on chest X-ray, and substantial response to anti-tuberculosis medication. Results : Chest X-ray revealed active pulmonary tuberculosis in 72% of patients (N=18/25). Sputum AFB smear/culture was positive in 95% of all tested patients (N=21/22) and in 100% of the tested patients who have stable or no evidence of pulmonary tuberculosis (N=5/5). All patients except one who had coexisting laryngeal malignancy showed considerable improvement in their subjective symptoms and laryngeal findings within the first 2 months of anti-tuberculosis medications and they achieved complete response on subsequent sputum studies, chest X-ray and laryngeal findings after $7.0{\pm}2.3$ months of the medications. Conclusion : We suggest that chest X-ray and sputum AFB smear/culture to be the first step of work-up for the patients having laryngeal tuberculosis in suspicion since laryngeal tuberculosis is largely associated with active pulmonary tuberculosis and/or sputum AFB study offers high yield even in case of primary laryngeal tuberculosis. However laryngeal biopsy must be considered in case showing unsatisfactory response to the anti-tuberculosis medication for more than 2 months.

• Korean Journal of Bronchoesophagology
• /
• v.6 no.2
• /
• pp.159-163
• /
• 2000

The patient with findings of diffuse infiltrative lung on chest X-ray has various causes; therefore, the prognosis is different and the treatment should be changed according to the cause. We are trying to identify the meaning of operative lung biopsy and to 11nd a more accurate and effective procedure. We reviewed 46 medical records of patients with the findings of diffuse infiltrative lung on chest X-ray who had undergone operative lung biopsy or biopsies for 8 years. The open lung biopsy were done in 22 cases(47.8%) and thoracoscopic lung biopsy in 24 cases(52.2%). There is no significant difference in the rate of diagnosis(p=0.452) and the incidence of complications(p=0.155) between these groups. The number of cases with more than two biopsies are 9(19.6%) and that of one biopsy are 37(80.4%). There are no statistical difference in the rate of diagnosis(p=0.928) and the incidence of complications(p=0.125). The postoperative complications occurred in 8 cases,7 cases of air leak more than 7 days and 1 case of respiratory insufficiency. In the diagnosis and treatment of the patients with findings of infiltrative lung on chest X-ray, the operative lung biopsy is the very necessary course, and shows satisfactory rate of diagnosis with negligible complications.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.170-176
• /
• 2024

Since the World Health Organization (WHO) has declared COVID-19 as pandemic, many researchers have started working on developing vaccine and developing AI systems to detect COVID-19 patient using Chest X-ray images. The purpose of this work is to improve the performance of pre-trained Deep convolution neural nets (DCNNs) on Chest X-ray images dataset specially COVID-19 which is developed by collecting from different sources such as GitHub, Kaggle. To improve the performance of Deep CNNs, data augmentation is used in this study. The COVID-19 dataset collected from GitHub was containing 257 images while the other two classes normal and pneumonia were having more than 500 images each class. There were two issues whike training DCNN model on this dataset, one is unbalanced and second is the data is very less. In order to handle these both issues, we performed data augmentation such as rotation, flipping to increase and balance the dataset. After data augmentation each class contains 510 images. Results show that augmentation on Chest X-ray images helps in improving accuracy. The accuracy before and after augmentation produced by our proposed architecture is 96.8% and 98.4% respectively.

• Journal of the Korean Society of Radiology
• /
• v.12 no.7
• /
• pp.827-832
• /
• 2018

Research on effective dose analysis of actual conditions of use based on large data is scarce. In this study, the exposure conditions of Chest X-Ray examinations used by 324 medical institutions in Korea were calculated and evaluated using computer simulations. As a result of the experiment, the effective dose in the low energy parameter bands was 0.024 mSv, followed by spleen, adrenal glands, and lung. The effective dose in the high-energy exposure parameter band was 0.123 mSv, followed by height, spleen and adrenal glands. The effective dose was 0.017 mSv when the optimal conditions considered the quality and exposure proposed in Park's study were used. The results of the study will be a reference for chest X-rays and will help reduce patient exposure.

• Journal of radiological science and technology
• /
• v.13 no.1
• /
• pp.19-24
• /
• 1990

In appilcation of wide latitude HR-C film to chest x-ray examination, former x-ray diagnosis area is larger and diagnostic information has great deal of promotion. HR-C film is compare to former x-ray film is larger latitude and density level is small, reading is very easily. Especially, high estimate that is in characteristic curve linearity of toe part is good, contrast of low density made good shape and not good describe to overlap is diagnostic information increase mediastinum portion etc.

• Journal of Chest Surgery
• /
• v.26 no.8
• /
• pp.654-660
• /
• 1993

The incidence of pulmonary leiomyosarcoma is very rare as a primary lung tumor. Usually, pulmonary leiomyosarcoma arise from the smooth muscle present in the bronchi or blood vessles. We had experienced two cases of primary pulmonary leiomyosarcoma. The first case was 28-year old male patient who had been in good health until admission, when he experienced an episode of dyspnea and sudden hemoptysis. The chest X-ray film revealed a large round tumor mass in left lower lobe measuring 6.5x9.5x5.3cm in dimension. On physical examination,the patient was friction rub and rales on the left lower chest and postoperative course was smooth and non-eventful. Emergency left lower lobectomy was performed due to repeated hemoptysis. Chemotheraphy was done postoperatively as an adjuvant therapy.The second case was 52-year-old man who had been well prior to admission, when recently he noticed a abrupt growing tendency of old pulmonary coin lesion in right lower lobe on routine physical examination. Since 1968, small round mass was gradually enlarged very slowly, during recent one year interval, the tumor mass was enlarged abruptly as twice in size on chest X-ray. Bronchoscopic examination revealed no specipic findings. Right lower lobectomy was performed and pathologic examination was answered as primary leiomyosarcoma without lymph node metastasis. Postoperative course was smooth, except local wound infection.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.27-40
• /
• 2022

Medical AI, which has lately made significant advances, is playing a vital role, such as assisting clinicians with diagnosis and decision-making. The field of chest X-rays, in particular, is attracting a lot of attention since it is important for accessibility and identification of chest diseases, as well as the current COVID-19 pandemic. However, despite the vast amount of data, there remains a limit to developing an effective AI model due to a lack of labeled data. A research that used federated learning on chest X-ray data to lessen this difficulty has emerged, although it still has the following limitations. 1) It does not consider the problems that may occur in the Non-IID environment. 2) Even in the federated learning environment, there is still a shortage of labeled data of clients. We propose a method to solve the above problems by using the self-supervised learning model as a global model of federated learning. To that aim, we investigate a self-supervised learning methods suited for federated learning using chest X-ray data and demonstrate the benefits of adopting the self-supervised learning model for federated learning.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.51-58
• /
• 2023

In this paper, we propose an organ segmentation technique for the automatic extraction of medical diagnostic indicators from X-ray images. In order to calculate diagnostic indicators of heart disease and spinal disease such as VHS(vertebral heart scale) and Cobb angle, it is necessary to accurately segment the thoracic spine, carina, and heart in a chest X-ray image. A deep neural network model in which the high-resolution representation of the image for each layer and the structure converted into a low-resolution feature map are connected in parallel was adopted. This structure enables the relative position information in the image to be effectively reflected in the segmentation process. It is shown that learning performance can be improved by combining the OCR module, in which pixel information and object information are mutually interacted in a multi-step process, and the channel attention module, which allows each channel of the network to be reflected as different weight values. In addition, a method of augmenting learning data is presented in order to provide robust performance against changes in the position, shape, and size of the subject in the X-ray image. The effectiveness of the proposed theory was evaluated through an experiment using 145 human chest X-ray images and 118 animal X-ray images.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.794-798
• /
• 2009

We introduce an implementation of plug-ins on PLUTO. These plug-ins discriminate inflammatory nodules from other types of nodules in chest X-ray CT images. The PLUTO is a common platform for computer-aided diagnosis systems on Microsoft Windows series and it is easy to add new functions as plug-ins. We coded two plug-ins. One of the them calculates features based on medical knowledge. The other plug-in calculates parameters to classify the type of nodules, and it also classifies nodules into inflammatory nodules and others using SVM. These plug-ins are coded using MIST library which is produced at Nagoya University, Japan. In our previous study, the MIST library was parallelized, so that we can utilize a number of CPUs to calculate features and SVM learning/classifying depending on the amount of computation. Using these plug-ins, it became easy to extract features to discriminate inflammatory nodules from other types of nodules and to change parameters for feature extraction and SVM learning/classifying with GUI interface. The accuracy of the classifying result is 100% with 78 solid nodules which contains 43 inflammatory nodules and 35 other type of nodules.

• Journal of radiological science and technology
• /
• v.45 no.3
• /
• pp.205-211
• /
• 2022

This study aimed to provide basic data for 3D printing in the medical health field by developing upper wear fixation device (UWFD), an auxiliary device for shortening chest AP examination time on emergency room beds and non-contact with patients. The standard of hooks was modeled according to the bed frame using the Autodesk Fusion 360. It was printed with Form2 (Formlabs, Somerville, MA, USA), as SLA (stereo lithography apparatus) method, and was washed and hardened using Form Wash and Form Cure. The completed UWFD conducted an online survey on 4 items of stability, convenience, availability, preference and general characteristics. The total stability average was 3.93±0.80, the total convenience average was 3.93±0.68, the total availability average was 4.01±0.89, and the total preference average was 3.80±1.08. This study was significant in suggesting improvements in the general X-ray examination process in the emergency room by designing and making aids to easily fixing the patient's top to the frame of the emergency bed while meeting promptness and non-contact with the patient.