• Journal of Radiation Industry
• /
• v.18 no.3
• /
• pp.177-182
• /
• 2024

The purpose of this study is to develop a CNN based deep learning model that can effectively detect pneumonia by analyzing chest X-ray images of adults over the age of 20 and compare it with VUNO, LUNIT a commercialized AI model. The data of chest X-ray image was evaluate based on accuracy, precision, recall, F1 score, and AUC score. The CNN model recored an accuracy of 82%, precision 76%, recall 99%, F1 score 86%, and AUC score 0.7937. The VUNO model recordded an accuracy of 84%, precision 81%, recall 94%, F1 score 87%, and AUC score 0.8233. The LUNIT model recorded an accuracy of 77%, precision 72%, recall 96%, F1 score 83%, and AUC score 0.7436. As a result of the Confusion Matrix analysis, the CNN model showe FN (3), showing the highest recall rate (99%) in the diagnosis of pneumonia. The VUNO model showed excellent overall perfomance with high accuracy (84%) and AUC score (0.8233), and the LUNIT model showed high recall rate (96%) but the accuracy and precision showed relatively low results. This study will be able to provide basic data useful for the development of a pneumonia diagnosis system by comprehensively considers the perfomance of the medel is necessary to effectively discriminate between penumonia and normal groups.

• Clinical and Experimental Pediatrics
• /
• v.58 no.3
• /
• pp.108-111
• /
• 2015

DiGeorge syndrome is an immunodeficient disease associated with abnormal development of 3rd and 4th pharyngeal pouches. As a hemizygous deletion of chromosome 22q11.2 occurs, various clinical phenotypes are shown with a broad spectrum. Conotruncal cardiac anomalies, hypoplastic thymus, and hypocalcemia are the classic triad of DiGeorge syndrome. As this syndrome is characterized by hypoplastic or aplastic thymus, there are missing thymic shadow on their plain chest x-ray. Immunodeficient patients are traditionally known to be at an increased risk for malignancy, especially lymphoma. We experienced a 7-year-old DiGeorge syndrome patient with mediastinal mass shadow on her plain chest x-ray. She visited Severance Children's Hospital hospital with recurrent pneumonia, and throughout her repeated chest x-ray, there was a mass like shadow on anterior mediastinal area. We did full evaluation including chest computed tomography, chest ultrasonography, and chest magnetic resonance imaging. To rule out malignancy, video assisted thoracoscopic surgery was done. Final diagnosis of the mass which was thought to be malignancy, was lymphoproliferative lesion.

• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.455-461
• /
• 2021

Cardiomegaly is one of the most common diseases seen on chest X-rays, but if it is not detected early, it can cause serious complications. In view of this, in recent years, many researches on image analysis in which deep learning algorithms using artificial intelligence are applied to medical care have been conducted with the development of various science and technology fields. In this paper, we would like to evaluate whether the Inception V3 deep learning model is a useful model for the classification of Cardiomegaly using chest X-ray images. For the images used, a total of 1026 chest X-ray images of patients diagnosed with normal heart and those diagnosed with Cardiomegaly in Kyungpook National University Hospital were used. As a result of the experiment, the classification accuracy and loss of the Inception V3 deep learning model according to the presence or absence of Cardiomegaly were 96.0% and 0.22%, respectively. From the research results, it was found that the Inception V3 deep learning model is an excellent deep learning model for feature extraction and classification of chest image data. The Inception V3 deep learning model is considered to be a useful deep learning model for classification of chest diseases, and if such excellent research results are obtained by conducting research using a little more variety of medical image data, I think it will be great help for doctor's diagnosis in future.

• Journal of radiological science and technology
• /
• v.1 no.1
• /
• pp.44-54
• /
• 1978

This study was carried out with statistical materials during the last two years of period from Jan. 1975 to Dec. 1976 which presented at radiologic department of 5 hospitals in Seoul City. The primary purpose of this study was to obtained more detailed informations related to the activities of radiologic technologists in diagnostic X-Ray examinations part and to provide some basic materials for managements in activities of then and manpower managements of their organization and practice. From the results of this study, the following conclusions were obtained [1] During two year from the January of 1975 to the December of 1976, total number of case in X-ray examinations were 464,830 case and 22,029 case in 1975 and 24,461 in 1976. And ratio of icreased in X-Ray examinations by year was 11.09 per cent. [2] Regarding the examined portion of X-Ray examination, a great propotion was chest examination as 56.88 per cent. [3] An average, the required time per case in X-Ray exam. was 9.28 minutes and make used of 1.94 sheets of X-Ray film per case in radiography. [4] An average, ratio of increased in X-Ray film by year was 12.71 per cent and ratio of failed film in it was 2.23 per cent. [5] The frequency rate of film size showed the highest distribution of $8"{\times}10"$(28.17%) and the highest distribution of X-Ray film by month was July(8.93%). [6] An average, the amount of activities per a diagnostic X-Ray equipment was 34.92 case and make used of 67.81 sheets of X-Ray film in a day. [7] The mean number of case in X-Ray examinations by radiologic technologists was 29.29 cases and make used of 56.87 sheets of X-Ray film in a day. Also, the average number of case was reading by radiologists was 32.42 case and 62.97 sheets of X-Ray film in a day.

• 전자공학회논문지 IE
• /
• v.46 no.3
• /
• pp.62-67
• /
• 2009

In this paper, ROC curves were designed by using Fuzzy Logic Systems. ROC curve is used for diagnostic evaluation and the person evaluating ROC curve is chosen as a first-level diagnostician. For rating diagnostic capability on ROC curve through learning, the chest X-ray image is used. The images used for making a diagnosis are X-ray film being both noise and signal. The result over diagnostic capability difference between the male and the female represented a man had better than a woman but that difference can be ignored.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.589-591
• /
• 2022

흉부 X-ray 영상은 폐 질환을 진단하는 기본적인 도구로써 널리 사용되고 있다. 정확한 진단을 위해 흉부 X-ray 영상의 품질을 평가하는 과정을 거쳐야 하는데, 이 과정은 주관적인 기준에 따라 수 작업으로 이루어지기 때문에 많은 시간과 비용이 소요된다. 따라서 본 논문에서는 임상 현장에서 사용되는 흉부 X-ray 영상 화질 평가 가이드라인을 기반으로 인공음영, 포함범위, 환자자세, 흡기정도, 그리고 투과 상태의 5가지 품질 평가를 자동화하는 도구를 제안한다. 제안하는 도구는 품질 판단에 소요되는 시간과 비용을 줄여주고, 더 나아가 흉부 병변 진단을 위한 학습 모델 개발의 양질의 학습 데이터를 선별하는 전처리 과정에 활용될 수 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1046-1052
• /
• 2021

Artificial intelligence is being applied in various industrial fields to the development of the fourth industry and the construction of high-performance computing environments. In the medical field, deep learning learning such as cancer, COVID-19, and bone age measurement was performed using medical images such as X-Ray, MRI, and PET and clinical data. In addition, ICT medical fusion technology is being researched by applying smart medical devices, IoT devices and deep learning algorithms. Among these techniques, medical image-based deep learning learning requires accurate finding of medical image biomarkers, minimal loss rate and high accuracy. Therefore, in this paper, we would like to compare and analyze the performance of the Cross-Entropy function used in the image classification algorithm of the loss function that derives the loss rate in the chest X-Ray image-based deep learning learning process.

• Journal of Radiation Protection and Research
• /
• v.27 no.3
• /
• pp.155-164
• /
• 2002

Methodology to evaluate the effective doses to adults undergoing various diagnostic x-ray examinations were established by Monte Carlo simulation of the x-ray examinations. Anthropomorphic mathematical phantoms, the MIRD5 male phantom and the ORNL female phantom, were used as the target body and x-ray spectra were produced by the x-ray spectrum generation code SPEC78. The computational procedure was validated by comparing the resulting doses to the results of NRPB studies for the same diagnostic procedures. The effective doses as well as the organ doses due to chest, abdomen, head and spine examinations were calculated for x-rays incident from AP, PA, LLAT and RLAT directions. For instance, the effective doses from the most common procedures, chest PA and abdomen AP, were 0.029 mSv and 0.44 mSv, respectively. The fact that the effective dose from PA chest x-ray is far lower than the traditional value of 0.3 mSv(or 30 mrem), which results partly from the advances of technology in diagnostic radiology and partly from the differences in the dose concept employed, emphasizes necessities of intensive assessment of the patient doses in wide ranges of medical exposures. The methodology and tools established in this study can easily be applied to dose assessments for other radiology procedures; dose from CT examinations, dose to the fetus due to examinations of pregnant women, dose from pediatric radiology.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.789-795
• /
• 2020

Many deaths have been reported due to the worldwide pandemic of COVID-19. In order to prevent the further spread of COVID-19, it is necessary to quickly and accurately read images of suspected patients and take appropriate measures. To this end, this paper introduces a deep learning-based COVID-19 chest X-ray reading technique that can assist in image reading by providing medical staff whether a patient is infected. First of all, in order to learn the reading model, a sufficient dataset must be secured, but the currently provided COVID-19 open dataset does not have enough image data to ensure the accuracy of learning. Therefore, we solved the image data number imbalance problem that degrades AI learning performance by using a Stacked Generative Adversarial Network(StackGAN++). Next, the DenseNet-based classification model was trained using the augmented data set to develop the reading model. This classification model is a model for binary classification of normal chest X-ray and COVID-19 chest X-ray, and the performance of the model was evaluated using part of the actual image data as test data. Finally, the reliability of the model was secured by presenting the basis for judging the presence or absence of disease in the input image using Grad-CAM, one of the explainable artificial intelligence called XAI.

• Journal of Chest Surgery
• /
• v.35 no.8
• /
• pp.626-629
• /
• 2002

Cavernous hemangioma in mediastinum is a rare tumor. A 13 year old girl was referred becaused of abnormal mediastinal shadow in simple chest X-ray. Chest CT scan revealed a somewhat inhomogenous cystic legion arround the whole length of SVC. Surgical excision was done through the right posterolateral thorachotomy. The pathology was confirmed as cavernous hemangioma.