• 대한기관식도과학회지
• /
• 제6권2호
• /
• pp.159-163
• /
• 2000

The patient with findings of diffuse infiltrative lung on chest X-ray has various causes; therefore, the prognosis is different and the treatment should be changed according to the cause. We are trying to identify the meaning of operative lung biopsy and to 11nd a more accurate and effective procedure. We reviewed 46 medical records of patients with the findings of diffuse infiltrative lung on chest X-ray who had undergone operative lung biopsy or biopsies for 8 years. The open lung biopsy were done in 22 cases(47.8%) and thoracoscopic lung biopsy in 24 cases(52.2%). There is no significant difference in the rate of diagnosis(p=0.452) and the incidence of complications(p=0.155) between these groups. The number of cases with more than two biopsies are 9(19.6%) and that of one biopsy are 37(80.4%). There are no statistical difference in the rate of diagnosis(p=0.928) and the incidence of complications(p=0.125). The postoperative complications occurred in 8 cases,7 cases of air leak more than 7 days and 1 case of respiratory insufficiency. In the diagnosis and treatment of the patients with findings of infiltrative lung on chest X-ray, the operative lung biopsy is the very necessary course, and shows satisfactory rate of diagnosis with negligible complications.

• International Journal of Computer Science & Network Security
• /
• 제24권7호
• /
• pp.170-176
• /
• 2024

Since the World Health Organization (WHO) has declared COVID-19 as pandemic, many researchers have started working on developing vaccine and developing AI systems to detect COVID-19 patient using Chest X-ray images. The purpose of this work is to improve the performance of pre-trained Deep convolution neural nets (DCNNs) on Chest X-ray images dataset specially COVID-19 which is developed by collecting from different sources such as GitHub, Kaggle. To improve the performance of Deep CNNs, data augmentation is used in this study. The COVID-19 dataset collected from GitHub was containing 257 images while the other two classes normal and pneumonia were having more than 500 images each class. There were two issues whike training DCNN model on this dataset, one is unbalanced and second is the data is very less. In order to handle these both issues, we performed data augmentation such as rotation, flipping to increase and balance the dataset. After data augmentation each class contains 510 images. Results show that augmentation on Chest X-ray images helps in improving accuracy. The accuracy before and after augmentation produced by our proposed architecture is 96.8% and 98.4% respectively.

• 한국방사선학회논문지
• /
• 제12권7호
• /
• pp.827-832
• /
• 2018

대규모 데이터에 기반한 실제 사용 조건의 장기유효선량 분석 연구는 부족하다. 본 연구에서는 국내 324개 의료기관에서 사용하는 흉부 X건 검사의 노출조건에 대해 전산모사를 이용한 장기선량을 계산하고 평가하였다. 실험결과, 저에너지 파라미터 대역에서 유효선량은 0.024 mSv이고 비장, 부신, 폐 순으로 높았다. 고에너지 노출파라미터 대역에서 유효선량은 0.123 mSv이고 신장, 비장, 부신 순으로 높게 나왔다. Park의 연구에서 제안한 화질과 피폭을 고려한 최적의 조건을 사용했을 때 유효선량은 0.017 mSv 로 나타났다. 사용 에너지가 높아질수록 장기 전체의 유효선량이 높아지고 그 중 신장이 가장 크게 증가하였다. 연구결과는 흉부X선 검사 시 참고자료가 되고 환자 피폭저감에 도움을 줄 것이다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제13권1호
• /
• pp.19-24
• /
• 1990

In appilcation of wide latitude HR-C film to chest x-ray examination, former x-ray diagnosis area is larger and diagnostic information has great deal of promotion. HR-C film is compare to former x-ray film is larger latitude and density level is small, reading is very easily. Especially, high estimate that is in characteristic curve linearity of toe part is good, contrast of low density made good shape and not good describe to overlap is diagnostic information increase mediastinum portion etc.

• Journal of Chest Surgery
• /
• 제26권8호
• /
• pp.654-660
• /
• 1993

The incidence of pulmonary leiomyosarcoma is very rare as a primary lung tumor. Usually, pulmonary leiomyosarcoma arise from the smooth muscle present in the bronchi or blood vessles. We had experienced two cases of primary pulmonary leiomyosarcoma. The first case was 28-year old male patient who had been in good health until admission, when he experienced an episode of dyspnea and sudden hemoptysis. The chest X-ray film revealed a large round tumor mass in left lower lobe measuring 6.5x9.5x5.3cm in dimension. On physical examination,the patient was friction rub and rales on the left lower chest and postoperative course was smooth and non-eventful. Emergency left lower lobectomy was performed due to repeated hemoptysis. Chemotheraphy was done postoperatively as an adjuvant therapy.The second case was 52-year-old man who had been well prior to admission, when recently he noticed a abrupt growing tendency of old pulmonary coin lesion in right lower lobe on routine physical examination. Since 1968, small round mass was gradually enlarged very slowly, during recent one year interval, the tumor mass was enlarged abruptly as twice in size on chest X-ray. Bronchoscopic examination revealed no specipic findings. Right lower lobectomy was performed and pathologic examination was answered as primary leiomyosarcoma without lymph node metastasis. Postoperative course was smooth, except local wound infection.

• 지능정보연구
• /
• 제28권4호
• /
• pp.27-40
• /
• 2022

최근 많은 발전을 이룬 의료 인공지능은 의사가 진단과 결정을 내리는 데 도움을 주는 등 중요한 역할을 수행하고 있다. 특히, 흉부 엑스레이 분야는 접근성 및 흉부질환 탐지에 유용함과 최근 COVID-19 상황이 도래함에 따라 많은 관심을 받고 있다. 그러나, 데이터의 수가 많음에도 레이블이 있는 데이터의 수가 부족하므로 효과적인 인공지능 모델을 만드는데 한계가 있다. 이러한 문제를 완화하는 방안으로 연합학습을 흉부 엑스레이 데이터에 적용한 연구가 등장했지만, 여전히 다음과 같은 문제를 내포하고 있다. 1) Non-IID 환경에서 발생할 수 있는 문제를 고려하지 않았다. 2) 연합학습 환경에서도 여전히 클라이언트의 레이블이 있는 데이터가 부족하다. 우리는 자기지도학습 모델을 연합학습의 Global 모델로 사용함으로써 위와 같은 문제를 해결하는 방법을 제안한다. 이를 위해 흉부 엑스레이 데이터를 사용한 연합학습에 알맞은 자기지도학습 방법론을 실험적으로 탐색하며, 자기지도학습 모델을 연합학습에 사용함으로써 얻을 수 있는 장점을 검증한다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권1호
• /
• pp.51-58
• /
• 2023

본 논문에서는 X-ray 영상에서 의료 진단지표를 자동으로 추출하기 위한 조직분할 기법을 제안한다. 척추질환이나 심장질환에 대한 진단지표로서, 흉추-심장 비율이나 콥 각도 등의 지표를 산출하기 위해서는 흉부 X-ray 영상으로부터 흉추, 용골 및 심장의 영역을 정확하게 분할하는 과정이 필요하다. 본 연구에서는 이를 위하여 계층별로 영상의 고해상도의 표현과 저해상도의 특징지도로 변환되는 구조가 병렬적으로 연결되는 형태의 심층신경망 모델을 채택하였다. 이러한 구조는 영상에서 세부 조직의 상대적인 위치정보가 분할 과정에 효과적으로 반영될 수 있게 한다. 또한 픽셀 정보와 객체 정보가 다단계의 과정으로 상호 작용되는 OCR 모듈과, 네트워크의 각 채널이 서로 다른 가중치 값으로 반영되도록 하는 채널 어텐션 모듈을 결합하여 학습 성능을 개선할 수 있음을 보인다. 부수적으로 X-ray 영상에서 피사체의 위치 변화, 형태의 변형 및 크기 변이 등에도 강인한 성능을 제공하기 위하여 학습데이터를 증강하는 방법을 제시하였다. 총 145개의 인체 흉부 X-ray 영상과, 총 118개의 동물 X-ray 영상을 사용한 실험을 통하여 제안된 이론의 타당성을 평가하였다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.794-798
• /
• 2009

We introduce an implementation of plug-ins on PLUTO. These plug-ins discriminate inflammatory nodules from other types of nodules in chest X-ray CT images. The PLUTO is a common platform for computer-aided diagnosis systems on Microsoft Windows series and it is easy to add new functions as plug-ins. We coded two plug-ins. One of the them calculates features based on medical knowledge. The other plug-in calculates parameters to classify the type of nodules, and it also classifies nodules into inflammatory nodules and others using SVM. These plug-ins are coded using MIST library which is produced at Nagoya University, Japan. In our previous study, the MIST library was parallelized, so that we can utilize a number of CPUs to calculate features and SVM learning/classifying depending on the amount of computation. Using these plug-ins, it became easy to extract features to discriminate inflammatory nodules from other types of nodules and to change parameters for feature extraction and SVM learning/classifying with GUI interface. The accuracy of the classifying result is 100% with 78 solid nodules which contains 43 inflammatory nodules and 35 other type of nodules.

• 대한방사선기술학회지:방사선기술과학
• /
• 제45권3호
• /
• pp.205-211
• /
• 2022

This study aimed to provide basic data for 3D printing in the medical health field by developing upper wear fixation device (UWFD), an auxiliary device for shortening chest AP examination time on emergency room beds and non-contact with patients. The standard of hooks was modeled according to the bed frame using the Autodesk Fusion 360. It was printed with Form2 (Formlabs, Somerville, MA, USA), as SLA (stereo lithography apparatus) method, and was washed and hardened using Form Wash and Form Cure. The completed UWFD conducted an online survey on 4 items of stability, convenience, availability, preference and general characteristics. The total stability average was 3.93±0.80, the total convenience average was 3.93±0.68, the total availability average was 4.01±0.89, and the total preference average was 3.80±1.08. This study was significant in suggesting improvements in the general X-ray examination process in the emergency room by designing and making aids to easily fixing the patient's top to the frame of the emergency bed while meeting promptness and non-contact with the patient.

• Clinical and Experimental Pediatrics
• /
• 제58권3호
• /
• 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.