• Journal of the Korean Society of Radiology
• /
• v.83 no.6
• /
• pp.1298-1311
• /
• 2022

Purpose To develop and validate a deep learning-based screening tool for the early diagnosis of scoliosis using chest radiographs with a semi-supervised generative adversarial network (GAN). Materials and Methods Using a semi-supervised learning framework with a GAN, a screening tool for diagnosing scoliosis was developed and validated through the chest PA radiographs of patients at two different tertiary hospitals. Our proposed method used training GAN with mild to severe scoliosis only in a semi-supervised manner, as an upstream task to learn scoliosis representations and a downstream task to perform simple classification for differentiating between normal and scoliosis states sensitively. Results The area under the receiver operating characteristic curve, negative predictive value (NPV), positive predictive value, sensitivity, and specificity were 0.856, 0.950, 0.579, 0.985, and 0.285, respectively. Conclusion Our deep learning-based artificial intelligence software in a semi-supervised manner achieved excellent performance in diagnosing scoliosis using the chest PA radiographs of young individuals; thus, it could be used as a screening tool with high NPV and sensitivity and reduce the burden on radiologists for diagnosing scoliosis through health screening chest radiographs.

• Journal of Chest Surgery
• /
• v.32 no.4
• /
• pp.383-387
• /
• 1999

Background: We analysed simple chest PA and high-resolution CT findings in patients with spontaneous pneumothorax in order to help selecting the kind of treatment, provide a guidline during surgical treatment, and to recognize the bulla which may not be detected by simple radiographs or may be a potential cause of recurrence. Material and Method: We retrospectively analysed the presence and number of bulla in each side, combined pulmonary disease on simple chest films and high-resolution CT, and methods and frequency of the treatment in 70 patients with spontaneous pneumothorax excluing traumatic origin. Result: 45 patients were revealed primary spontaneous pneumothorax, and the remaining 25 patients were revealed secondary spontaneous pneumothorax. All secondary spontaneous pneumothorax were from the longstanding sequelle of pulmonary tuberculosis. The patients with primary spontaneous pneumothorax group was younger(mean:26.0 years old) than secondary group (mean: 44.1 years old). On simple radiography, bulla was detected in 16 patients(30.2%). On HRCT, the bulla was detected in 53 patients(75.7%) of the total 70 patients. In 48 patients(68.6%), the bulla or bleb was noted in ipsilateral side to the pneumothorax, and 34 patients(48.6%) of them showed bulla or bleb bilaterally. 39 patients(55.7%) showed bulla or bleb in contralateral side. The number of bulla or bleb was variable. In secondary spontaneous pneumothorax group, the incidence of multiple(more than 10) bulla or bleb was higher than primary type. Most of the patients were treated by thoracostomy(36 patients) or bullectomy( 7 patients). Conclusion: HRCT was superior to detect bulla and analyse the combined pulmonary disease than simple radiography. Therefore, HRCT can help to determine the mothod of treatment, provide a guidline during surgical treatment, and notify the bulla as a possible cause of recurrent pneumothorax.

• Progress in Medical Physics
• /
• v.19 no.3
• /
• pp.143-149
• /
• 2008

The aim of this study is to suggest the method for image enhancement of digital chest radiograph and evaluate clinically the quality of the resultant image. A nonlinear iterative filter was developed in order to reduce quantum noise preserving edge. Dynamic range was adjusted and adaptive image enhancement was performed based on the property of anatomic region and the degree of compatibility with neighboring pixels. The lung fields were enhanced appropriately to visualize effectively vascular tissue, bronchus and lung tissue with the desired mediastinum enhancement. Clinic evaluation was performed by three radiologists with at least 8 years experience. The anatomic regions of 11 in PA and 9 in Lateral were observed carefully in each 100 radiographs according to ITU (International Telecommunication Union) recommendation 500 protocol. The result showed the mean 3.4 between good and adequate. This means that the clinical utility of the image quality is enough. In this study, image enhancement was carried out considering image display device and human perceptual system to prevent the loss of useful anatomic information. In order to increase the diagnostic accuracy in digital radiograph, the continuous study on image enhancement is needed.

• Journal of radiological science and technology
• /
• v.37 no.3
• /
• pp.177-185
• /
• 2014

This study focused on effects of patient exposure dose reduction with AEC (Auto Exposure Control) marker that is designed for showing location of AEC in X-ray Chest radiography. It included 880 adults who have to use Chest X-ray Digital Radiography system (DRS, LISTEM, Korea). AEC (Ion chambers are posited in top of both sides) are used to every adult and set X-ray system as Field size $17{\times}17inch$, 120kVp, FFD 180cm. 440 people of control group are posited on detector to include both sides of lung field and the other 440 people of experimental group are set to contact their lung directly to Ion chamber (making marker to shows location). Then, measured every DAP and, estimated patient effective dose by using PCXMC 2.0. The average age of control group (M:F=245:195) is 53.9 and the average BMI is 23.4. BMI ranges from under weight: 35, normal range: 279, over weight: 106 to obese: 20 and average DAP is 223.56mGycm2, Mean effective dose is 0.045mSv. The average age of experimental group (M:F=197:243) is 53.7 and the average BMI is 22.7. BMI ranges from under weight: 34, normal range: 315, over weight: 85 to obese: 6 and average DAP is 207.36mGycm2, Mean effective dose is 0.041mSv. Experimental group shows less Mean effective dose as 0.004mSv (9.7%) than control group. Also, patient numbers who got over exposure more than 0.056mSv (limit point to know efficiency of AEC marker) is 65 in control group (14.7%), 19 in experimental group (4.3%) and take statistics with t-Test. The statistical difference between two groups is 0.006. In order to use proper amount of X-ray in auto exposure controlled chest X-ray system, matching location between ion chamber and body part is needed, and using AEC marker (designed for showing location of ion chamber) is a way to reduce unnecessary patient exposure dose.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2004.11a
• /
• pp.59-63
• /
• 2004

IAEA's Guidance Levels have been provided for Western people to the end. Guidance levels lower than the IAEA'S will be necessary in view of korean people's proportions. Therefore, We need to develope the standard doses for korean people. And we conducted a nationwide survey of patient dose from x-ray examinations in korea. 278 institutions were selected from Members Book of Korean Hospital Association. The valid response rate was approximately 57.9%. Doses were calculated from the questionnaires by NDD method. The results were as follows; 1) General radiographic equipments were 43%, fluoroscopic equipments 29%, dental equipments 13%, CT units 8% and mamographic units 7%. 2) According to classification by rectification way, three-phase equipments were 30%, inverter-type generators 29%, single- phase equipments 26%, unknown units 6%. 3) According to classification by receptor system, film-screen types were 46%, CR types 27%, OR types18% and unknown types 9%. 4) The number of examinations were chest 48%, spine 17% and abdomen 13%. 5) Patient doses were head AP 3.1 mGy, abdomen AP 3.5 mGy and chest PA 0.4 mGy.

• Tuberculosis and Respiratory Diseases
• /
• v.42 no.4
• /
• pp.624-628
• /
• 1995

Lymphangioleiomyomatosis is a rare disease which afflicts young women of childbearing age. We experienced a 32-year-old female who was admitted because of worsening exertional dyspnea after hormonal therapy with Clomifen for five months and intermittent hemoptysis. Chest PA showed diffuse ground glass appearance with some reticular infiltrations. High resolution CT scan showed multiple small thin walled cysts distributed homogeneously throughout the entire lung. Pulmonary function test showed characteristic obstructive pattern despite the restrictive interstitial pattern of chest radiography. Thoracoscopic lung biopsy specimen showed abnormal proliferation of smooth muscle cells in the walls of lymphatic vessels, bronchioles, and pulmonary vessels typical of pulmonary lymphangioleiomyomatosis. Hormonal therapy with medroxyprogesterone was initiated.

• Journal of the Korean Society of Radiology
• /
• v.15 no.2
• /
• pp.139-145
• /
• 2021

This study is to confirm the range of tube voltage for Chest X-ray in DR system by comparing with dose area product (DAP) and effective dose in efficient detector exposure index (DEI) range. GE definium 8000 was used to for the phantom study. The range of tube voltage is 60~130 kVp and of mAs is 2.5~40 mAs. The acquired images were classified into efficient DEI groups, then calculated effective dose with DAP by using a PC-Based Monte Carlo Program 2.0. The signal to noise ratio (SNR) was measured at 4 regions, including the thoracic spine, the lung area with the ribs, the lung area without the ribs, and the liver by using Picture Archiving and Communication System. The significance of the group for each tube voltage was verified by performing the kruskal-wallis test and the mann-whitney test as a post-test. When set to 4 groups dependned on the tube voltage, DAP showed significant differences; 60 kVp and 80 kVp, and 60 kVp and 90 kVp (p= 0.034, 0.021). Effective dose exhibited no statistically significant differences from the all of the group (p>0.05). SNR exhibited statistically significant differences from the all of the group in the liver except compared to 80 kVp and 90 kVp (p<0.05). Therefore, high tube voltages of 100 kVp or more need to be reconsidered in terms of patient dose and imaging in order to represent an appropriate chest X-ray image in a digital system.

• Tuberculosis and Respiratory Diseases
• /
• v.56 no.6
• /
• pp.670-676
• /
• 2004

Chemical pneumonitis is caused by the inhalation of noxious chemical substances and is a cause of occupational lung disease. Nitric acid, which is a one of the common air pollutants and a potential oxidant for refining and cleansing of metals, has a chance for occupational and environmental exposure. A 52-year-old man visited our hospital due to coughing and dyspnea after the inhalation of nitric acid fumes at his workplace. He had conditions of tachypnea (respiratory rate 26 /min) and hypoxemia ($PaO_2$ 42.6 mmHg, $SaO_2$ 80.2% in room air) in our emergency department. The chest radiographs showed diffuse interstitial infiltrates and ground glass opacity in both lungs. The patient made improvements in clinical symptoms and chest radiography after being given a supply of oxygen, antibiotics, and bronchodilator therapy without systemic glucocorticoid therapy. On his follow up visit after 4 weeks, he showed no symptoms and sequelae, and the pulmonary function test showed a normal pulmonary function.

• The Journal of the Korea Contents Association
• /
• v.15 no.1
• /
• pp.316-323
• /
• 2015

In this study, we analyzed radiation dose and MTF with setting of Ion chamber and changing kVp so that we are able to suggest acquiring optimized diagnostic images and minimizing patient dose. we assumed right lateral decubitus position among chest decubitus projection and set 7 combination of Ion chamber. By changing kVp(100, 110, 120, 130kVp), we exposed x-ray five times respectively and calculated average value after measuring entrance dose. we input the entrance dose value to PCXMC Monte carlo simulation tool and calculated organ dose and effective dose. Then we did physical image evaluation with MTF for the purpose to compare image quality. As a result, the high kVp, entrance dose is reduced. As change of ion chamber, when selecting second ion chamber, both organ dose and effective dose were the lowest. In contrast, selecting first ion chamber was the highest. MTF is superior to set second Ion chamber and using 120 kVp. Consequently, when taking chest right lateral decubitus using Digital radiography, the optimized combination which have both reducing dose efficiently without declining image quality and aquring good qualified image is set 120 kVp and selecting second Ion chamber.

• Journal of the Korean Society of Radiology
• /
• v.16 no.7
• /
• pp.871-877
• /
• 2022

This study was conducted to improve the problems of exposure dose and image reading applied to patients due to the incorrect use of AEC during chest radiography. Images were acquired by dividing the case where AEC was used as the test condition and the case where AEC was not used. As a result of the study, the dose was reduced by 1.17% in 110 kVp without AEC than with AEC, 17.2% decrease at 100 kVp, 30.19% decrease at 90 kVp, and 46.45% decrease at 80 kVp. There was a significant difference in the statistical values according to the tube voltage change in the lung, trachea, and heart SNR average values with AEC and without AEC 110 kVp, but the difference in image quality was insignificant in actual images. When AEC was not applied at the same tube voltage, the dose could be reduced by 17.2% while maintaining the image quality similar to that of with AEC at 100 kVp without AEC. Therefore, rather than relying on AE conditions during chest radiographic examination, it is considered that the conditions should be considered for the examination while lowering the dose by selecting an appropriate tube voltage.