• Journal of the Korean Society of Radiology
• /
• v.13 no.7
• /
• pp.1015-1024
• /
• 2019

In the medical field, X-rays are essential in the diagnosis and treatment of diseases, and the use of X-rays continues to increase with the development of imaging technology, but X-rays have the disadvantage of radiation exposure. Although lead protection tools are used in clinical practice to protect against radiation exposure, lead is classified as a heavy metal and can cause harmful reactions such as lead poisoning. Therefore, the purpose of this study is to investigate the usefulness of the shield fabricated using materials of FDM (Fused Deposition Modeling) 3D printer. In order to confirm the filament's line attenuation factor, phantoms were fabricated using PLA, XT-CF20, Wood, Glow and Brass, and CT scan was performed. And the shielding sheet of 100 × 100 × 2 mm size was modeled, the dose and shielding rate was measured by using a diagnostic X-ray generator and irradiation dose meter, and the shielding rate with lead protection tools. As a result of the experiment, the CT number of the brass was measured to be the highest, and the shielding sheet was manufactured by using the brass. As a result of confirming with the diagnostic X-ray generator, the shielding rate was increased in the shielding sheet having a thickness of 6 mm upon X-ray irradiation under the condition of 100 kV and 40 mAs. It measured by 90% or more, and confirmed that the shielding rate is higher than apron 0.25 mmPb. As a result of this study, it was confirmed that the shield fabricated by 3D printing technology showed high shielding rate in the diagnostic X-ray region. there was.

• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.903-906
• /
• 2021

인공지능 기술 발전으로, 의료영상 분야에서도 딥러닝 기반 질병 진단 연구가 활발히 진행되고 있다. 딥러닝 모델 개발 시, 학습 데이터 품질은 모델의 성능과 신뢰성에 매우 큰 영향을 미친다. 그러나 의료 분야의 경우 도메인 지식에 대한 진입 장벽이 높아 개발자가 학습에 사용되는 의료영상 데이터의 품질을 평가하기 어렵다. 이로 인해, 많은 의료영상 분야에서는 각 분야의 특성(질병의 종류, 관찰 아나토미 등)에 따른 영상 품질 평가 방법을 제시해왔다. 그러나 기존의 방법은 특정 질병에 초점이 맞춰져, 일반화된 품질 평가 기준을 제시하고 있지 않다. 따라서 본 논문에서는 대부분의 흉부 질환을 진단하기 위한 흉부 X선 영상의 품질을 평가할 수 있는 기준을 제안한다. 우선, 흉부 X선 영상을 대상으로 관찰된 영역인 심장, 횡격막, 견갑골, 폐 등을 분할하여, 3D 히스토그램을 기반으로 각 영역별 통계적인 정밀 품질 평가 기준을 제안한다. 본 연구에서는 JSRT, Chest 14의 오픈 데이터셋을 활용하여 적용 실험을 수행하였으며, 민감도는 97.6%, 특이도는 92.8%의 우수한 성능을 확인하였다.

• Journal of the Korean Society of Radiology
• /
• v.81 no.6
• /
• pp.1334-1347
• /
• 2020

Coronavirus disease (COVID-19) has threatened public health as a global pandemic. Chest CT and radiography are crucial in managing COVID-19 in addition to reverse transcription-polymerase chain reaction, which is the gold standard for COVID-19 diagnosis. This is a review of the current status of the use of chest CT and radiography in COVID-19 diagnosis and management and anㄷ introduction of early representative studies on the application of artificial intelligence to chest CT and radiography. The authors also share their experiences to provide insights into the future value of artificial intelligence.

• Journal of radiological science and technology
• /
• v.30 no.1
• /
• pp.7-12
• /
• 2007

This study examined present conditions of upper-gastrointestinal X-ray fluoroscopy and patient skin dose. The authors elected 21 equipments to check the X-ray equipment and exposure factor of fluoroscopy & spot exposure in university hospitals, hospitals, and clinics where perform upper-gastrointestinal X-ray fluoroscopy more than five times every day in Incheon areas. The amount of patient's skin dose during upper-gastrointestinal X-ray fluoroscopy was measured by ionization chamber.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.762-763
• /
• 2010

The X-ray device used for medical treatment is classified into fixed type that is used by installing at the location with the stable power supply and mobile type that can be taken by moving the X-ray device to the location where a patient is. Mobile X-ray device which is typically used in the mobile type of X-ray can be used very usefully beyond the space restriction. However, due to its difficulty to generate high-voltage, it is mainly applied to take hand and foot shootings which only need low output power. In this study, by designing and producing the large volume of mobile X-ray device which doesn't have the limitations on diagnostic areas of the body, the operating characteristics of device according to the loading change was identified.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.409-412
• /
• 2011

본 논문에서는 흉부 X선 영상으로부터 폐 종류 음영을 검출하기 위한 필터를 예측해서 바람직하게 평가하기 위한 방법을 제안한다. 더욱이 그 평가방법을 이용해서 이전부터 제안한 다중해상도 라플라시안-가우시안 필터의 평가를 행한다. 전문의의 진단보조 혹은 종합자동진단시스템의 구성요소로서 필터가 행하는 역할을 고려한 후에 필터가 만족해야할 조건 및 그 조건을 만족한 경우에 있어서 몇가지 성능평가 척도를 명확히 한다. 제안한 평가방법을 통해서 다중해상도 필터가 단일해상도 필터에 비해 높은 성능을 갖게됨을 명확히 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.614-617
• /
• 2022

인공지능의 발전으로 의료영상 분야에서 딥러닝 기반 질병 진단 연구가 활발하다. 그러나 모델 개발 시 학습 데이터의 개수와 품질은 매우 중요한데, 의료 분야 특성상 접근 가능한 데이터셋이 적으며 오픈 데이터셋은 서로 다른 기관에서 배포되거나 웹상에서 수집된 것으로 진단에 적합한 품질을 기대하기 어렵다. 또한, 기존 연구는 데이터셋이 학습에 적합한지에 대한 품질검증 없이 사용한다. 따라서 본 논문에서는 임상에서 사용하는 화질 평가 요소에 근거를 두고 영역별 화소값 분석을 통한 흉부 X선 영상 품질 평가 기법을 제안한다. 오픈 데이터셋 JSRT, Chest14와 국내 A 병원 데이터셋 AUH에 제안한 기법을 적용한 결과 민감도 91.5%, 특이도 96.1%의 우수한 성능을 확인하였다.

• Journal of radiological science and technology
• /
• v.8 no.1
• /
• pp.87-105
• /
• 1985

• Journal of radiological science and technology
• /
• v.8 no.1
• /
• pp.77-85
• /
• 1985