• 대한방사선기술학회지:방사선기술과학
• /
• 제43권5호
• /
• pp.397-404
• /
• 2020

Coronavirus disease(COVID-19) is highly infectious disease that directly affects the lungs. To observe the clinical findings from these lungs, the Chest Radiography(CXR) can be used in a fast manner. However, the diagnostic performance via CXR needs to be improved, since the identifying these findings are highly time-consuming and prone to human error. Therefore, Artificial Intelligence(AI) based tool may be useful to aid the diagnosis of COVID-19 via CXR. In this study, we explored various Deep learning(DL) approach to classify COVID-19, other viral pneumonia and normal. For the original dataset and lung-segmented dataset, the pre-trained AlexNet, SqueezeNet, ResNet18, DenseNet201 were transfer-trained and validated for 3 class - COVID-19, viral pneumonia, normal. In the results, AlexNet showed the highest mean accuracy of 99.15±2.69% and fastest training time of 1.61±0.56 min among 4 pre-trained neural networks. In this study, we demonstrated the performance of 4 pre-trained neural networks in COVID-19 diagnosis with CXR images. Further, we plotted the class activation map(CAM) of each network and demonstrated that the lung-segmentation pre-processing improve the performance of COVID-19 classifier with CXR images by excluding background features.

• 한국전자통신학회논문지
• /
• 제15권3호
• /
• pp.611-616
• /
• 2020

본 논문은 대도시에서의 COVID-19 바이러스 확산을 막기 위해, 대한민국 서울의 감염 상황에 대한 클러스터 분석을 통한 링크드 데이터 기반 시맨틱 진단 및 추적 시스템을 제안한다. 본 논문은 크게 3개의 섹션으로 구성되어 있는데, 클러스터 분석을 위해 서울의 감염자 정보를 수집하고, 중요한 감염 환자 속성을 추출하여 랜덤 포레스트를 기반으로 한 진단 모델을 구축하고, 그리고 링크드 데이터를 기반으로 한 추적 시스템을 설계하고 구현한다. 실험 결과 진단 모델의 정확도가 80% 이상으로 나타났으며, 더군다나 본 논문에서 제안한 추적 시스템은 기존 시스템들보다 더 유연하고 개방적이며 시맨틱 쿼리도 지원한다.

• Journal of Medicine and Life Science
• /
• 제17권2호
• /
• pp.33-40
• /
• 2020

Coronavirus disease 2019 (COVID-19) is a respiratory tract infection caused by a newly emergent coronavirus, that was first recognized in Wuhan, China, in December 2019. Genetic sequencing of the virus suggests that it is a beta coronavirus closely linked to the SARS virus. This disease has non-specific symptoms such as fever, dry cough, sore throat, and gastrointestinal symptoms. This virus can transmit via aerosol and need to droplet precaution to prevent spreading in public areas. Most people with COVID-19 develop only mild or uncomplicated illness. However, about 20% patients require hospitalization, oxygen supply, and intensive care. There is no currently effective treatment available for COVID-19 unresponsive to supportive care. This is review about the recently published epidemiologic, and clinical features, diagnosis, treatment and prevention of COVID-19.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.149-158
• /
• 2022

The pandemic of Covid-19 (Coronavirus Disease 19) has devastated the world, affected millions of people, and disrupted the world economy. The cause of the Covid19 epidemic has been identified as a new variant known as Severe Acute Respiratory Syndrome Coronavirus 2(SARS-CoV2). It motives irritation of a small air sac referred to as the alveoli. The alveoli make up most of the tissue in the lungs and fill the sac with mucus. Most human beings with Covid19 usually do no longer improve pneumonia. However, chest x-rays of seriously unwell sufferers can be a useful device for medical doctors in diagnosing Covid19-both CT and X-ray exhibit usual patterns of frosted glass (GGO) and consolidation. The introduction of deep getting to know and brand new imaging helps radiologists and medical practitioners discover these unnatural patterns and pick out Covid19-infected chest x-rays. This venture makes use of a new deep studying structure proposed to diagnose Covid19 by the use of chest X-rays. The suggested model in this work aims to predict and forecast the patients at risk and identify the primary COVID-19 risk variables

• Korean Journal of Radiology
• /
• 제21권8호
• /
• pp.1018-1023
• /
• 2020

The coronavirus disease (COVID-19) outbreak has reached global pandemic status as announced by the World Health Organization, which currently recommends reverse transcription polymerase chain reaction (RT-PCR) as the standard diagnostic tool. However, although the RT-PCR test results may be found negative, there are cases that are found positive for COVID-19 pneumonia on computed tomography (CT) scan. CT is also useful in assessing the severity of COVID-19 pneumonia. When clinicians desire a CT scan of a patient with COVID-19 to monitor treatment response, a safe method for patient transport is necessary. To address the engagement of medical resources necessary to transport a patient with COVID-19, our institution has implemented the use of mobile CT. Therefore, we report two cases of COVID-19 pneumonia evaluated by using mobile cone-beam CT. Although mobile cone-beam CT had some limitations regarding its image quality such as scatter noise, motion and streak artifacts, and limited field of view compared with conventional multi-detector CT, both cases had acceptable image quality to establish the diagnosis of COVID-19 pneumonia. We report the usefulness of mobile cone-beam CT in patients with COVID-19 pneumonia.

• 대한임상검사과학회지
• /
• 제52권3호
• /
• pp.284-295
• /
• 2020

2019년 12월, 중국 후베이성 우한시에서 COVID-19환자가 처음으로 보고되었다. 그 이후 국내에서 신종 코로나 바이러스에 의해 야기된 중증 급성 호흡기 증후군 환자가 급격하게 증가하였다. 이러한 새로운 변종 바이러스는 기침, 인후통, 비루, 호흡곤란, 폐렴 및 기타 폐질환을 유발한다. 중증 급성 호흡기 증후군 코로나 바이러스 2는 RNA바이러스로, 실시간 역전사효소 중합효소 연쇄반응을 통한 분자진단 검사가 COVID-19의 진단에 폭 넓게 사용되고 있다. 국내 질병관리본부와 식품의약품 안전처의 긴급 사용 허가 승인에 따라, 건강한 사람과 COVID-19 환자로부터 검체를 채취하여 진단검사의학적인 방법을 통해 진단을 수행하고 있다. 기존에 출판된 많은 문헌 고찰을 통해, 본 연구에서는 역학, 증상 및 질병관리본부의 승인을 받은 현재의 검사실 내 COVID-19 분자 진단 방법, 분자 진단 검사와 혈청학적 진단의 차이, 임상 검체 가이드라인 등을 다시 한 번 확인하고자 하였다. 추가적으로 본 연구를 통해 국내 의료기관 내 의료종사자 및 임상병리사들의 병원 감염을 예방하고자 생물학적 안전에 관한 가이드라인을 확인하였다. 국내 임상병리사들의 경험과 그로부터 얻은 교훈을 통해 국내외 COVID-19 팬데믹 상황으로부터 국민의 안전을 지킬 수 있는 단초를 제공할 수 있을 것이라 사료된다.

• The Korean Journal of Pain
• /
• 제35권4호
• /
• pp.458-467
• /
• 2022

Background: Few studies have investigated unspecified or idiopathic pain associated with COIVD-19. This study aimed to provide the incidence rates of unspecified pain and idiopathic pain in patients with COVID-19 for 90 days after COVID-19 diagnosis. Methods: A propensity score matched cohort was used, including all patients with COVID-19 in South Korea, and analyzed their electronic medical records. The control group consisted of those who had not had tests for COVID-19 at all. Unspecified pain diagnoses consisted of diagnoses related to pain included in the ICD-10 Chapter XVIII. Idiopathic pain disorders included fibromyalgia, temporomandibular joint disorders, headaches, chronic prostatitis, complex regional pain syndrome, atypical facial pain, irritable bowel syndrome, and interstitial cystitis. Results: After matching, the number of participants in each group was 7,911. For most unspecified pain, the incidences were higher in the COVID-19 group (11.7%; 95% confidence interval [CI], 11.0-12.5) than in the control group (6.5%; 95% CI, 6.0-7.1). For idiopathic pain, only the headaches had a significantly higher incidence in the COVID-19 group (6.6%; 95% CI, 6.1-7.2) than in the control group (3.7%; 95% CI, 3.3-4.1). However, using a different control group that included only patients who visited a hospital at least once for any reasons, the incidences of most unspecified and idiopathic pain were higher in the control group than in the COVID-19 group. Conclusions: Patients with COVID-19 might be at a higher risk of experiencing unspecified pain in the acute phase or after recovery compared with individuals who had not had tests for COVID-19.

• Parasites, Hosts and Diseases
• /
• 제59권4호
• /
• pp.399-402
• /
• 2021

The COVID-19 pandemic continues to be a major health problem worldwide. Timely diagnosis of co-infections mimicking COVID-19, such as malaria, might be challenging particularly in non-endemic areas. We report the first case of COVID-19 and Plasmodium ovale malaria co-infection from our region aiming to highligt the importance of travel history and prophylaxis in malaria management in the context of pandemic. The galloping sound can sometimes be a harbinger of zebra besides the horse.

• Korean Journal of Radiology
• /
• 제21권5호
• /
• pp.537-540
• /
• 2020

Recently, some global cases of 2019 novel coronavirus (COVID-19) pneumonia have been caused by second- or third-generation transmission of the viral infection, resulting in no traceable epidemiological history. Owing to the complications of COVID-19 pneumonia, the first symptom and imaging features of patients can be very atypical and early diagnosis of COVID-19 infections remains a challenge. It would aid radiologists and clinicians to be aware of the early atypical symptom and imaging features of the disease and contribute to the prevention of infected patients being missed.

• Korean Journal of Radiology
• /
• 제21권7호
• /
• pp.851-858
• /
• 2020

Coronavirus disease 2019 (COVID-19) is a new infectious disease rapidly spreading around the world, raising global public health concerns. Radiological examinations play a crucial role in the early diagnosis and follow-up of COVID-19. Cross infection among patients and radiographers can occur in radiology departments due to the close and frequent contact of radiographers with confirmed or potentially infected patients in a relatively confined room during radiological workflow. This article outlines our experience in the emergency management procedure and infection control of the radiology department during the COVID-19 outbreak.