• Journal of Radiation Protection and Research
• /
• v.40 no.2
• /
• pp.118-123
• /
• 2015

The frequency of diagnostic radiation examinations in medical institutions has recently increased to 220 million cases in 2011, and the annual exposure dose per capita was 1.4 mSv, 51% and 35% respectively, compared to those in 2007. The number of chest radiography was found to be 27.59% of them, the highest frequency of normal radiography. In this study, we developed a shielding device to minimize radiation exposure by shielding areas of the body which are unnecessary for image interpretation, during the chest radiography. And in order to verify its usefulness, we also measured the difference in entrance surface dose (ESD) and the absorbed dose, before and after using the device, by using an international standard pediatric (10 years) phantom and a glass dosimeter. In addition, we calculated the effective dose by using a Monte Carlo simulation-based program (PCXMC 2.0.1) and evaluated the reduction ratio indirectly by comparing lifetime attributable risk of cancer incidence (LAR). When using the protective device, the ESD decreased by 86.36% on average, nasal cavity $0.55{\mu}Sv$ (74.06%), thyroid $1.43{\mu}Sv$ (95.15%), oesophagus $6.35{\mu}Sv$ (78.42%) respectively, and the depth dose decreased by 72.30% on average, the cervical spine(upper spine) $1.23{\mu}Sv$ (89.73%), salivary gland $0.5{\mu}Sv$ (92.31%), oesophagus $3.85{\mu}Sv$ (59.39%), thyroid $2.02{\mu}Sv$ (73.53%), thoracic vertebrae(middle spine) $5.68{\mu}Sv$ (54.01%) respectively, so that we could verify the usefulness of the shielding mechanism. In addition, the effective dose decreased by 11.76% from $8.33{\mu}Sv$ to $7.35{\mu}Sv$ before and after wearing the device, and in LAR assessment, we found that thyroid cancer decreased to male 0.14 people (95.12%) and female 0.77 people (95.16%) per one million 10-year old children, and general cancers decreased to male 0.14 people (11.70%) and female 0.25 people (11.70%). Although diagnostic radiation examinations are necessary for healthcare such as the treatment of diseases, based on the ALARA concept, we should strive to optimize medical radiation by using this shielding device actively in the areas of the body unnecessary for the diagnosis.

• Clinical and Experimental Pediatrics
• /
• v.46 no.7
• /
• pp.655-660
• /
• 2003

Purpose : The relationship between chest X-ray findings and respiratory indices, including the arterial-alveolar oxygen partial pressure ratio($a/APO_2$) and the ventilatory index(VI), indicators of the clinical respiratory status in neonates with respiratory distress syndrome(RDS), was examined in the present study. Methods : The records of 50 neonates, randomly chosen from 174 neonates treated with pulmonary surfactant(PS) in the Neonatal Intensive Care Unit of Kyunghee University Hospital from 1996 to 2000 were analyzed retrospectively. Chest radiographs taken at the time after birth were classified into four groups according to Bomsel's classification. The $a/APO_2$ and VI values were calculated and compared with the corresponding chest radiographs. Results : Among the 50 cases of RDS examined, three cases were classified into grade I(6%), eight cases into grade II(16%), 20 cases into grade III(40%), and 19 cases into grade IV(38%). The mean $a/APO_2$ of the cases classified into grades I or II was 0.32 and the mean $a/APO_2$ of those classified into grades III and IV was 0.18 and 0.09, respectively. The mean VI was 0.049 for the cases classified into grades I or II and 0.076 and 0.161 for those classified into grades III and IV, respectively. Conclusion : The severity of RDS according to chest X-ray findings correlate to the values of respiratory indices, $a/APO_2$ and VI.

• 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.33 no.2
• /
• pp.85-91
• /
• 2010

Digital radiography has been replacing rapidly the analog radiography for diagnosis of pneumoconiosis. The purpose of this study is to compare quality control of digital radiography (DR) and analog radiography (AR) for chest radiography in medical institution for pneumoconiosis (MIP) For the first time, we visited MIP to evaluate the chest radiography which is used for patients with pneumoconiosis, including equipment, technical parameters and reading environment. There were 33 institutions. DR and AR were installed in 24 and 9 institutions, respectively. Between DR and AR, we compared the radiological technique (RT), image quality (IQ) and reading environment (RE) to use the guideline published by Occupational Safety and Health Research Institute (OSHRI). The image quality was rated by two experienced chest radiologists for pneumoconiosis with certified from OSHRI. The chest radiography equipment was not significantly difference between AR and DR, but there were significantly difference in tube voltage and grid ratio used for chest radiography except to tube current, exposure time. Statistically, DR is significantly higher in RT(70.3 vs. 43.8, p = 0.009), RE(77.7 vs. 33.3, p = 0.004) than AR, but it's not significantly difference in IQ (65.6 vs. 52.8, p = 0.050). AR and DR in RT were passed 33.3%, 75.0% respectively (p = 0.044) and 44.4%, 79.2% (p = 0.090) in IQ and 44.4%, 91.7% (p = 0.009) in RE. In MIP, DR needs to replace AR in diagnosis of pneumoconiosis.

• Journal of the Korean Society of Radiology
• /
• v.16 no.4
• /
• pp.411-417
• /
• 2022

This study aimed to learn and evaluate the effectiveness of VGGNet in the detection of pulmonary emphysema using low-dose chest computed tomography images. In total, 8000 images with normal findings and 3189 images showing pulmonary emphysema were used. Furthermore, 60%, 24%, and 16% of the normal and emphysema data were randomly assigned to training, validation, and test datasets, respectively, in model learning. VGG16 and VGG19 were used for learning, and the accuracy, loss, confusion matrix, precision, recall, specificity, and F1-score were evaluated. The accuracy and loss for pulmonary emphysema detection of the low-dose chest CT test dataset were 92.35% and 0.21% for VGG16 and 95.88% and 0.09% for VGG19, respectively. The precision, recall, and specificity were 91.60%, 98.36%, and 77.08% for VGG16 and 96.55%, 97.39%, and 92.72% for VGG19, respectively. The F1-scores were 94.86% and 96.97% for VGG16 and VGG19, respectively. Through the above evaluation index, VGG19 is judged to be more useful in detecting pulmonary emphysema. The findings of this study would be useful as basic data for the research on pulmonary emphysema detection models using VGGNet and artificial neural networks.

• Journal of the Korean Society of Radiology
• /
• v.8 no.2
• /
• pp.75-79
• /
• 2014

The aim of this retrospective research was to investigate the influence of the patient's arm position on radiation dose and scanning during CT. Chest CT image created image degradation, artifact and overdose to the patient due to the difference of the chest thickness. Therefore, the patient's arm should up position during the CT chest examination. In 2012, 1,642 patients underwent chest CT examination in Seoul K hospital. 118 chest CT examination performed hands down position. The average DLP value of the CT chest arm up examination was 275 $mGy{\cdot}cm$. The average DLP value of the CT chest arm down examination was 312.46 $mGy{\cdot}cm$. In the retrospective study with same patient, The average DLP value of the CT chest examination arm up vigorously was 267.5 $mGy{\cdot}cm$. The average DLP value of the CT chest arm down examination was 307.5 $mGy{\cdot}cm$. Chest CT scan without raising arm created linear artifact due to the lack of X-ray photons which is the thickest part of the human body of shoulder area. In conclusion, arm positioning patients' arms above the shoulders at CT of the chest increases image quality and substantially reduces effective radiation dose.

• 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.

• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.547-554
• /
• 2021

In order to quickly and accurately diagnose pneumonia on a chest X-ray image, different batch sizes of 4, 8, 16, and 32 were applied to the same Xception deep learning model, and modeling was performed 3 times, respectively. As a result of the performance evaluation of deep learning modeling, in the case of modeling to which batch size 32 was applied, the results of accuracy, loss function value, mean square error, and learning time per epoch showed the best results. And in the accuracy evaluation of the Test Metric, the modeling applied with batch size 8 showed the best results, and the precision evaluation showed excellent results in all batch sizes. In the recall evaluation, modeling applied with batch size 16 showed the best results, and for F1-score, modeling applied with batch size 16 showed the best results. And the AUC score evaluation was the same for all batch sizes. Based on these results, deep learning modeling with batch size 32 showed high accuracy, stable artificial neural network learning, and excellent speed. It is thought that accurate and rapid lesion detection will be possible if a batch size of 32 is applied in an automatic diagnosis study for feature extraction and classification of pneumonia in chest X-ray images using deep learning in the future.

• Journal of the Korean Society of Radiology
• /
• v.16 no.5
• /
• pp.595-602
• /
• 2022

This study tried to suggest the most efficient learning rate for accurate and efficient automatic diagnosis of medical images for chest X-ray pneumonia images using deep learning. After setting the learning rates to 0.1, 0.01, 0.001, and 0.0001 in the Inception V3 deep learning model, respectively, deep learning modeling was performed three times. And the average accuracy and loss function value of verification modeling, and the metric of test modeling were set as performance evaluation indicators, and the performance was compared and evaluated with the average value of three times of the results obtained as a result of performing deep learning modeling. As a result of performance evaluation for deep learning verification modeling performance evaluation and test modeling metric, modeling with a learning rate of 0.001 showed the highest accuracy and excellent performance. For this reason, in this paper, it is recommended to apply a learning rate of 0.001 when classifying the presence or absence of pneumonia on chest X-ray images using a deep learning model. In addition, it was judged that when deep learning modeling through the application of the learning rate presented in this paper could play an auxiliary role in the classification of the presence or absence of pneumonia on chest X-ray images. In the future, if the study of classification for diagnosis and classification of pneumonia using deep learning continues, the contents of this thesis research can be used as basic data, and furthermore, it is expected that it will be helpful in selecting an efficient learning rate in classifying medical images using artificial intelligence.

• Journal of the Korean Society of Radiology
• /
• v.5 no.6
• /
• pp.421-426
• /
• 2011

This research was accomplished to assess dose effects on image quality at computed radiography (CR). The ultimate target of the research was finding optimized exposure that provides necessary image quality for the clinical chest diagnosis. Modulation transfer function (MTF), normalized noise power spectrum (NNPS), and Noise equivalent quanta (NEQ) corresponding to the different doses were measured for the assessment of image quality. The preparation of "edge test device" used in MTF measurement and experimental geometry setup were followed by the recommendations of International Electrotechnical Commission (IEC). The experimental results show the necessary image quality can be achieved even at a half of the automatic exposure control (AEC) setting dose for chest diagnosis. It means that the patient exposure can be reduced dramatically by using optimized dose.