• Korean Journal of Rural Living Science
• /
• v.7 no.2
• /
• pp.189-194
• /
• 1996

포괄적 의료서비스를 제공하는 가정의에게 농촌지역의 질병 양상 및 실태에 대한 파악은 중요하고 지역사회를 이해하는데 도움이 될 것이다. 하지만 노령화된 농촌지역의 만성질환의 유병율 및 실태에 대한최근의 연구는 많지 않을 것 같다. 본 연구를 위 한 진료활동은 농촌지 역의 2개면에서 가정의학과, 내과, 정형외과, 흉부외과 전문의에 의해 행해졌고 흉부 방사선 촬영 및 CBC, LFT, 요 검사, B형간염항원, 항체 등의 임상병리 검사를 병행하였다. 본 연구의 조사대상은 479명으로 성별로는 남자가 194명 (40.5%), 여자가 285명 (59.5%)였고 연령별로는 60세가 남녀에서 가장 높았다. 조사 대상자의 만성질환 유병율은 66.2%였고 남녀에서 비슷한 수준이였고 질병의 빈도는 근 골격계 질환이 40.9%로 가장 높았고 순환기 질환, 소화기 질환, 호흡기 질환, 내분비 질환의 순서로 많았다. 농촌사회는 과거에 비해 더욱 고령화되고 만성질환의 유병율은 더욱 증가하고 있다. 농촌에 대한 보건복지정책의 수립과 더불어 지속적, 총체적, 포괄적인 의료서비스를 지향하는 가정의는 더욱 많은 관심과 연구를 지속적으로 하여야 할 것이다.

• Clinical and Experimental Pediatrics
• /
• v.45 no.11
• /
• pp.1311-1316
• /
• 2002

단순 흉부 X-선 사진은 흉곽내에 공기를 함유하고 있는 폐실질, 심장과 대혈관을 포함한 연부조직, 그리고 흉곽을 이루는 골격 등의 다양한 조직으로 이루어진 3차원적인 해부학적 구조물을 X-선 film이라는 2차원적 평면에 흑백의 음영으로 표현하는 검사이다. 뿐만아니라 이들 구조물들이 전후, 좌우로 겹쳐져 있어 병변이 쉽게 가려질 수 있고, 폐실질 질환 뿐만 아니라 심장 질환 또한 폐실질의 변화를 유발시킬 수 있으므로, 단순히 각 질환의 X-선 소견에 대한 지식을 습득하는 것보다는 병인과 해부학적인 지식에 대한 이해를 기본으로 X-선 판독에 임하는 것이 중요하다. 또한 환자들의 임상 증상과 부합되지 않는 X-선 소견이 관찰되거나, 치료 도중 임상 경과와 판독소견이 일치되지 않는다면 방사선과 전문의와의 긴밀한 의견교환이 진단과 치료에 중요하리라 생각된다.

• Journal of the Korean Society of Radiology
• /
• v.14 no.6
• /
• pp.773-780
• /
• 2020

With the development of the 4th industrial, research is being conducted to prevent diseases and reduce damage in various fields of science and technology such as medicine, health, and bio. As a result, artificial intelligence technology has been introduced and researched for image analysis of radiological examinations. In this paper, we will directly apply a deep learning model for classification and detection of pneumonia using chest X-ray images, and evaluate whether the deep learning model of the Inception series is a useful model for detecting pneumonia. As the experimental material, a chest X-ray image data set provided and shared free of charge by Kaggle was used, and out of the total 3,470 chest X-ray image data, it was classified into 1,870 training data sets, 1,100 validation data sets, and 500 test data sets. I did. As a result of the experiment, the result of metric evaluation of the Inception V3 deep learning model was 94.80% for accuracy, 97.24% for precision, 94.00% for recall, and 95.59 for F1 score. In addition, the accuracy of the final epoch for Inception V3 deep learning modeling was 94.91% for learning modeling and 89.68% for verification modeling for pneumonia detection and classification of chest X-ray images. For the evaluation of the loss function value, the learning modeling was 1.127% and the validation modeling was 4.603%. As a result, it was evaluated that the Inception V3 deep learning model is a very excellent deep learning model in extracting and classifying features of chest image data, and its learning state is also very good. As a result of matrix accuracy evaluation for test modeling, the accuracy of 96% for normal chest X-ray image data and 97% for pneumonia chest X-ray image data was proven. The deep learning model of the Inception series is considered to be a useful deep learning model for classification of chest diseases, and it is expected that it can also play an auxiliary role of human resources, so it is considered that it will be a solution to the problem of insufficient medical personnel. In the future, this study is expected to be presented as basic data for similar studies in the case of similar studies on the diagnosis of pneumonia using deep learning.

• Journal of radiological science and technology
• /
• v.41 no.3
• /
• pp.223-229
• /
• 2018

The purpose of this study is to present the reference values for cardiac size and cardiothoracic ratio change, normal range and diagnosis of cardiovascular disease in pregnancy and non pregnancy of normal Korean women using chest X-ray. The subjects of this study were 58 women, who were read as normal by chest radiologist, had chest radiography taken on both last month of pregnancy, pre-pregnancy and within 2 years following delivery. In this study, we defined the last month of pregnancy as pregnancy and before or post pregnancy as non-pregnancy. CS and CTR were measured by two radiological technologist who had clinical experience more ten years with Danzer's method. Statistical methods were paired t-test and one-way ANOVA. Significance level ${\alpha}$ was 0.05 and p-value 0.05 or less was statistically significant. For pregnancy, the mean of left and right cardiac size was $40.11{\pm}8.73mm$ and $89.51{\pm}11.9mm$, CS was $128.60{\pm}13.15mm$, CTR was $44.51{\pm}4.21%$. In non pregnancy, $36.50{\pm}8.18mm$ and $77.68{\pm}13.1mm$. CS and CTR were $114.18{\pm}14.28mm$ and $42.03{\pm}4.04%$. Both pregnancy and non pregnancy, the difference of the mean value in left and right cardiac size, CS and CTR were statistically significant (p<0.01). but comparing mean on age, height and weight, the difference of the mean value between groups was not (p>0.05). In the result of this study, the mean size of CS increased by 12.6% in pregnancy($128.60{\pm}13.15mm$) compared to the non pregnancy($114.18{\pm}14.28mm$), and increased by 9.8% in the right side of the heart and 15.2% in the left side. The mean size of CTR increased about 5.9% in pregnancy ($44.5{\pm}4.21%$) compared to non pregnancy($42.03{\pm}4.04%$).

• Proceedings of the KOR-BRONCHOESO Conference
• /
• 1983.05a
• /
• pp.9.2-9
• /
• 1983

We have observed 74 cases of radiolucent foreign bodies in food and air passage in E. N. T. department of Hang Gang Sacred Hospital, from Jan. 1972 to Mar. 1983. The following results were obtained. 1) Distribution of location was 56 cases(75.6 %) in food passage and 18 cases (24.4 %) in air passage. 2) In age distribution, 46 cases (82.1 %) of F. B. in food passage were found in patient over 21 years old and 12 cases (66.7 %) of F. B. in air passage were found in patient under 5 years old. 3) Female seems to be more frequently involved than male in cases of F. B. of food passage and in cases of air passage, male is more frequent. Food passage male: female - - - 25 : 31 Air passage male: female - - - 10 : 8 4) Meats was the most frequent foreign body in food passage (19 cases-33.9%), and the bony pieces was next (17 cases-30.4 %). Plastic material was the most frequent foreign body in air passage (9 cases-49.9 %), and the vegetable seed was the second (4cases-22.0 %). 5) In the location of F. B. in food passage, the first narrowing of the esophagus was the most frequent site and in air passage, the bronchus-especially right bronchus-was the most frequent site. 6) In the duration of lodgement, 44 cases(78.6 %) of F.B. in food passage were visited with - in 24 hours, and 11 cases (61 %) of F. B. in air passage were visited with - in 24 hours. 7) Simple chest PA was checked in all patient and then, esophagogram was checked in 34 cases of F.B. in food passage, among them positive finding was noticed in 23 cases. 8) Removal of F. B. in food passage by esophagoscopy was performed in 54 cases (96.4 %), but in the cases of air passage, removal of F. B. by bronchoscopy was performed in 14 cases (77.8 %). 9) Complications of food passage by the F. B. itself or esophagoscopy were esophageal mucosal laceration (1 cases-1.8 %) and esophageal perforation (1 case -1. 8 %) and complication of air passage by F. B. itself or bronchoscopy were atelectasis (2 cases -11.1 %) and pneumonia (3 cases-16.7 %).

• Journal of radiological science and technology
• /
• v.38 no.4
• /
• pp.347-353
• /
• 2015

The purpose of this study is to suggest proper additional filtration by comparisons patient dose and image quality among additional filters in digital chest tomosynthesis (DTS). We measured the effective dose, dose area product (DAP) by changing thickness of Cu, Al and Ni filter to compare image quality by CD curve and SNR, CNR. Cu, Al and Ni exposure dose were similar thickness 0.3 mm, 3 mm and 0.3 mm respectively. The exposure dose using filter was decreased average about 33.1% than non filter. The DAP value of 0.3 mm Ni were decreased 72.9% compared to non filter and the lowest dose among 3 filter. The effective dose of 0.3 mm Ni were decreased 48% compared to 0.102 mSv effective dose of non filter. At the result of comparison of image quality through CD curve there were similar aspect graph among Cu, Al and Ni. SNR was decreased average 19.07%, CNR was average decreased 18.17% using 3 filters. In conclusion, Ni filtration was considered to be most suitable when considered comprehensive thickness, character, sort of filter, dose reduction and image quality evaluation in DTS.

• Journal of Life Science
• /
• v.16 no.1
• /
• pp.58-63
• /
• 2006

There was cross-sectional study on investigating the factors related asbestos-related disease on chest radiograph of workers exposed to asbestos in ship repair. According to Occupational Safety & Health Administration asbestos standard, medical surveillance, chest radiologic study, pulmonary function test and medical questionnaire are performed in 118 subjects exposed to asbestos for 10 years or more in ship repair. The sixteen out of 118 subjects $(13.6\%)$ were observed asbestos-related disease finding on chest radiography. Significant factors related to those finding on chest radiography were abnormal pulmonary function test, cough, sputum, past history of respiratory disease, work duration. Workers with Significant factors related asbestos-related disease finding on chest radiography should be managed on a strict program. Further, factors unrelated with asbestos-related disease finding on this study should be evaluated prospectively for medical surveillance program of workers exposed to asbestos.

• Journal of the Korean Society of Radiology
• /
• v.15 no.3
• /
• pp.301-306
• /
• 2021

The use of tin filters as a way to reduce the medical radiation in computed tomography (CT). However, due to the changed X-ray spectrum with the use of tin filters, disease diagnosis could be affected because it appears as images of different impressions from previous images. Therefore, this study evaluates the changes in images when using tin filter and high pitch in chest low-dose CT. In this study, images were acquired in groups of three for comparison. Group 1 did not apply to tin filter, and used the existing pitch 0.8. Group 2 used a tin filter, pitch 0.8, Group 3 used a tin filter, and pitch 2.5. To compare the image quality, the natural image quality evaluator (NIQE) and the blind/referenceless image quality evaluator (BRISQUE) were used among the blind quality evaluation factors depended on a no-reference basis. As a result, the NIQE values were low in the order of Group 1, Group 3, and Group 2. BRISQUE values were low in the order of Group 3, Group 2 and Group 1. This study confirms the superiority of images of tin filter and high pitch techniques in chest low-dose CT, which is considered to be a fundamental study for acquiring accurate images of patients with difficult breathing control.

• Journal of the Korean Society of Radiology
• /
• v.17 no.6
• /
• pp.939-945
• /
• 2023

This study analyzes the 'performance efficiency' of AI-based reading assistance systems in the field of radiology by measuring their 'time behavior' properties. Due to the increase in medical images and the limited number of radiologists, the adoption of AI-based solutions is escalating, stimulating a multitude of studies in this area. Contrary to the majority of past research which centered on AI's diagnostic precision, this study underlines the significance of time behavior. Using 50 chest X-ray PA images, the system processed images in an average of 15.24 seconds, demonstrating high consistency and reliability, which is on par with leading global AI platforms, suggesting the potential for significant improvements in radiology workflow efficiency. We expect AI technology to play a large role in the field of radiology and help improve overall healthcare quality and efficiency.

• The Journal of Korean Society for Radiation Therapy
• /
• v.26 no.2
• /
• pp.321-327
• /
• 2014

Purpose : To verify the accuracy of the Ecilpse's dose calculation algorithm(AAA:Analytic anisotropic algorithm) in case of a radiation treatment on Inhomogeneous tissues using FFF beam comparing dose distribution at TPS with actual distribution. Materials and Methods : After acquiring CT images for radiation treatment by the location of tumors and sizes using the solid water phantoms, cork and chest tumor phantom made of paraffin, we established the treatment plan for 6MV photon therapy using our radiation treatment planning system for chest SABR, Ecilpse's AAA(Analytic anisotropic algorithm). According to the completed plan, using our TrueBeam STx(Varian medical system, Palo Alto, CA), we irradiated radiation on the chest tumor phantom on which EBT2 films are inserted and evaluated the dose value of the treatment plan and that of the actual phantom on Inhomogeneous tissue. Results : The difference of the dose value between TPS and measurement at the medial target is 1.28~2.7%, and, at the side of target including inhomogeneous tissues, the difference is 2.02%~7.40% at Ant, 4.46%~14.84% at Post, 0.98%~7.12% at Rt, 1.36%~4.08% at Lt, 2.38%~4.98% at Sup, and 0.94%~3.54% at Inf. Conclusion : In this study, we discovered the possibility of dose calculation's errors caused by FFF beam's characteristics and the inhomogeneous tissues when we do SBRT for inhomogeneous tissues. SBRT which is most popular therapy method needs high accuracy because it irradiates high dose radiation in small fraction. So, it is supposed that ideal treatment is possible if we minimize the errors when planning for treatment through more study about organ's characteristics like Inhomogeneous tissues and FFF beam's characteristics.