• 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.

• The Journal of the Korea Contents Association
• /
• v.12 no.7
• /
• pp.255-260
• /
• 2012

This study aims to examine the generation of scatter rays by dividing it into the presence of the subject at the chest X-ray examination, the X-ray tube and detector in the X-ray room, the front of the patient window, the outside of the entrance door of the patient waiting room, opening of the entrance door, the outside of the radiological technologist's entrance door, and the opening of the radiological technologist's entrance door, etc. When there is a subject, as the subject is thicker, more scatter rays occur at each of the spots for measurement. And when the entrance door is closed at the measurement, fewer scatter rays are generated.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.1
• /
• pp.49-55
• /
• 2000

Recently, X-ray chest rediography is showing a tendency to take an image of digital radiography so as to diagnose the pathology of chest in a usual. When the radiologist observes the chest image derived from digital radiography system on the monitor, he feels difficult to find out the pathological pattern because the quality of chest radiography is unequal. It takes amount of time to adjust the proper image for diagnosis. Therefore, we propose the method of the chest image equalization using neural networks and provide the compared result with histogram equalization method.

• Journal of Internet Computing and Services
• /
• v.24 no.1
• /
• pp.49-59
• /
• 2023

Recently, attention to the pandemic situation represented by COVID-19 emerged problems caused by unexpected shortage of medical personnel. In this paper, we present a method for diagnosing the presence or absence of lesional sign on PA chest X-ray images as computer vision solution to support diagnosis tasks. Method for visual anomaly detection based on feature modeling can be also applied to X-ray images. With extracting feature vectors from PA chest X-ray images and divide to patch unit, region-specific abnormality can be detected. As preliminary experiment, we created simulation data set containing multiple objects and present results of the comparative experiments in this paper. We present method to improve both efficiency and performance of the process through hard masking of patch features to aligned images. By summing up regional specificity and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to previous studies. By aggregating region-specific and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to our last study.

• Journal of the Korean Society of Radiology
• /
• v.15 no.5
• /
• pp.613-620
• /
• 2021

The purpose of this study is to propose a convolutional neural network model that can classify normal and abnormal(cardiomegaly) in chest X-ray images. The training data and test data used in this paper were used by acquiring chest X-ray images of patients diagnosed with normal and abnormal(cardiomegaly). Using the proposed deep learning model, we classified normal and abnormal(cardiomegaly) images and verified the classification performance. When using the proposed model, the classification accuracy of normal and abnormal(cardiomegaly) was 99.88%. Validation of classification performance using normal images as test data showed 95%, 100%, 90%, and 96% in accuracy, precision, recall, and F1 score. Validation of classification performance using abnormal(cardiomegaly) images as test data showed 95%, 92%, 100%, and 96% in accuracy, precision, recall, and F1 score. Our classification results show that the proposed convolutional neural network model shows very good performance in feature extraction and classification of chest X-ray images. The convolutional neural network model proposed in this paper is expected to show useful results for disease classification of chest X-ray images, and further study of CNN models are needed focusing on the features of medical images.

• Clinical and Experimental Pediatrics
• /
• v.48 no.5
• /
• pp.534-538
• /
• 2005

Purpose : Kawasaki disease(KD) is a multisystemic inflammatory vasculitis of unknown etiology. Many complications other than cardiovascular involvement have been recognized in KD. However, there have been few reports published concerning involvement of the lungs in this disease. The purpose of this study was to examine the relationship between serum TNF-${\alpha}$, the degree of coronary artery dilatation and chest X-ray(CXR) findings. In addition, we have investigated serum anti-Mycoplasma antibody(AMA) titers in patients with KD who have abnormal CXR findings. Methods : Eighty four patients with KD were included in this study(group I; 41 patients with normal CXR fndings, group II; 43 patients with abnormal CXR findings). Serum levels of TNF-${\alpha}$ and AMA titer were measured. Results : We reviewed the CXR findings and clinical courses of 84 patients with Kawasaki disease and found abnormal CXR findings in 43 patients(51.2 percent). Peribronchial cuffing was the most frequent abnormality(22.4 percent). In the group with abnormal CXR findings(group II), a statistical difference was not noted in age, sex, duration of fever, hemoglobin, WBC, platelet, ESR, and CRP levels and incidence of coronary arterial lesions as compared with the group having normal CXR findings(group I). No difference was noted in serum TNF-${\alpha}$ level between group I and group II. 2 patients(12.5 percent) of 16 KD patients with abnormal CXR findings have positive AMA titer(above 1 : 320). Conclusion : Most of the abnormal CXR findings in KD patients were peribronchial cuffing. The abnormal CXR findings in KD patients did not mean severe inflammations. It is difficult to consider that CXR abnormalities are related to coronary arterial lesions. In addition, further study on the relationship between Mycoplasma infection and Kawasaki disease is needed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.2
• /
• pp.371-378
• /
• 2000

In this study, we proposed pathological pattern detection system for X-ray chest image using artificial neural network. In a physical examination, radiologists have checked on the chest image projected the view box by a magnifying glass and found out what the disease is. Here, the detection of X-ray fluoroscopy is tedious and time-consuming for human doing. Lowering of efficiency for chest diagnosis is caused by lots mistakes of radiologist because of detecting the micro pathology from the film of small size. So, we proposed the method for disease detection using artificial neural network and digital image processing on a X-ray chest image. This method composes the function of image sampling, median filter, image equalizer used neural network and pattern recognition used neural network. We confirm this method has improved the problem of a conventional method.

• Journal of Chest Surgery
• /
• v.42 no.2
• /
• pp.226-232
• /
• 2009

Background: Blunt chest trauma accounts for 90% of all chest traumas in Europe and the United States and this causes 20% of all trauma-related deaths. The major cause of morbidity and mortality after blunt chest trauma is undetected injuries. For this reason, chest computerized tomography has gained popularity for the evaluation of trauma, but it is expensive and it exposes patients to radiation. This study identified the clinical features associated with the diagnosic information obtained on a CT chest scan, as compared with a standard chest X-ray, for patients who sustained blunt trauma to the chest. This study also evaluated the role of a routine computed tomographic (CT) scan for these patients. The patients who had chest computed tomography done after the initial chest x-ray were analyzed separately for the presence of occult injuries. Material and Method: We studied 100 consecutive patients from November 2006 to July 2007: 74 patients after motor vehicle crashes and 26 patients after a fall from a height >2m. Simultaneous with the initial clinical evaluation, an anteroposterior chest radiograph and a helical chest CT scan were obtained for all the patients. The data extracted from the medical record included the vital signs, the interventions and the type and severity of injury (RTS). Result: Among the 100 cases, 79 patients showed at least more than one pathologic sign on their chest radiograph, and 21 patients had a normal chest radiograph. For 17 of the patients who had a normal chest X ray, the CT scan showed multiple injuries, which were pneumothorax, hemothorax, lung contusion, sternal fracture etc. This represents that a CT scan is statistically superior to a chest radiograph to diagnose the pathologic signs. But on the other hand, as for treatment, only 31 patients were diagnosed by CT scan and they were treated with chest tube insertion ect. 42 patients needed ony conservative management without invasive thoracosurgical treatment such as chest tube insertion or open thoracotomy. 27 patients were treated based on the diagnosis made by the chest radiograph and physical examination. Conclusion: Chest computerized tomography was significantly more effective than routine chest X-ray for detecting lung contusion, pneumothorax and mediastinal hematoma, as well as fractured ribs, scapula and, sternum. Although the occult findings increased, the number of patients who needed treatment was small. Therefore, we suggest making selective use of a CT scan to avoid its overuse in ERs.

• Journal of radiological science and technology
• /
• v.45 no.3
• /
• pp.249-254
• /
• 2022

The purpose of this study was to examine the importance of proper positioning in chest PA X-ray examination. As a study method, this author searched for and analyzed materials related to chest PA X-ray examination from theses and books that had been published previously to understand the importance of proper positioning in chest PA X-ray examination. Generally, one of the examinations frequently done in most of the hospitals is chest PA X-ray examination. Also, in any kinds of X-ray examination, proper positioning is the most fundamental and definite way to provide accurate information about the patient. Poor positioning in chest PA X-ray examination may jeopardize the diagnosis and treatment, increase social cost due to examination needed to be done additionally, and generate additional radiation exposure unnecessarily above all. In conclusion, it is expected that proper positioning in chest PA X-ray examination will exert positive effects such as the provision of accurate information about the patient, prevention of misdiagnosis, reduction in social cost, and lastly decrease in radiation exposure.

• Tuberculosis and Respiratory Diseases
• /
• v.39 no.1
• /
• pp.15-23
• /
• 1992

Background: The prognosis of lung cancer remains poor and early detection and curative surgery is still the most effective treatment for many. In the early detection of lung cancer, sputum cytology and simple chest x-ray are used, but both of these tests are far from being perfect. So we studied the characteristics of patients diagnosed as lung cancer without demonstrable mass lesion on simple chest x-ray to help in the early diagnosis of lung cancer. Methods: We conducted a retrospective study on 11 subjects who were diagnosed as lung cancer at Seoul National University Hospital between August 1986 and June 1989 and had no demonstrable mass lesion on simple chest x-rays. Results: Ten of 11 patients were male, 8 had a history of smoking, most frequent symptoms were sputum, cough, and hemoptysis, and 3 patients either had wheezing or stridor. In 3 of the cases, although there were no mass lesion, there were ill-defined infiltration, major fissure thickening, and fibrostreaky density mimiking tuberculosis where the tumor was eventually found and in one patient tumor was masked by a rib shadow. Also in one case, lateral chest film demonstrated a retrocardiac mass. Both bronchoscopy and computed tomogram were useful in the localization of the tumor. Seven of 11 had relatively early disease (less than StageII). Four of 11 are still alive without any evidence of recurrence between 2 and a half and 4 years after the operation. Conclusion: We conclude that in patients with respiratory symtoms in whom cancer cannot be ruled out, sputum cytology and lateral chest x-rays should be taken and that if necessary further studies like computed tomogram and bronchoscopy should be done to aid in the early diagnosis of lung cancer.