• 한국재난정보학회 논문집
• /
• 제14권1호
• /
• pp.28-35
• /
• 2018

본 연구에서는 재난현장 또는 일상에서 발생할 수 있는 다수사상자의 중증도 분류를 신속하고 정확하게 수행하기 위한 시스템을 설계하여 구현하였으며, 중증도 분류 알고리즘의 정확도뿐만 아니라 사용자 편의성 등 현장의 요구사항을 적극 반영하였다. 개발된 e-Triage System은 IoT개념을 활용하여 다양한 중증도 분류 알고리즘을 적용하였으며, 기존의 중증도 분류표의 단점을 극복하기 위하여 NFC 모듈 등 전자적 요소를 반영한 e-Triage Tag를 구현하였다. 앱으로 구현된 중증도 분류 알고리즘을 사용하여 신속하고 정확한 환자의 평가가 가능함을 입증하였고, 시인성을 위해 전자 중증도 분류 결과를 4가지 LED램프로 표출하였으며, 2차 분류를 통해 RTS 점수를 FND(Flexible Numeric Display)로 표출하였다.

• Korean Journal of Radiology
• /
• 제23권10호
• /
• pp.1009-1018
• /
• 2022

Objective: This study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment. Materials and Methods: This retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI). Results: Of 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity. Conclusion: This study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.

• 대한세포병리학회지
• /
• 제17권2호
• /
• pp.99-107
• /
• 2006

In the investigation of superficial lymphadenopathy of unknown cause, fine needle aspiration (FNA) cytology plays an invaluable role. It enables the differentiation of benign lymphadenopathy from lymphoid and non-lymphoid malignancies, obviating the need for open biopsy, and allowing the triage of patients. Cytopathologists should be familiar with the typical FNA patterns of benign lymphadenopathy, and recognize and differentiate among categories. In a minority of cases of benign lymphadenopathy, FNA can render a specific diagnosis. Benign lymphadenopathies are generally categorized into reactive lymphoid hyperplasia (RLH), inflammatory or infectious processes, and benign lymphoproliferative disorders. RLH characteristically presents with a heterogeneous and polymorphous smear composed of normal cellular constituents of lymph nodes, in contrast with the homogeneous or monomorphic smear of most lymphomas. The caveat is that various malignant disorders may also present with polymorphous populations. It is also important to recognize thatbenign lymphoid smears may sometimes contain atypical cells that raise the suspicion of malignancy. Clinical information should always be the integral part of the diagnostic criteria in FNA of lymphadenopathy. If there is any doubt about the benign nature of the smear, it is prudent to suggest biopsy and ancillary studies.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권14호
• /
• pp.5879-5882
• /
• 2014

High-risk (HR) human papillomavirus (HPV) testing is important in cervical cancer screening for triage colposcopy. The objective of the study was to evaluate the prevalence of HR HPV infection with different cervical cytological features among women undergoing health examination. A total of 2,897 women were retrospectively evaluated between May 2011 to December 2011. DNA was extracted from residual specimens collected during routine liquid-based cytology tests at the National Cancer Institute. Overall, HR HPV prevalence was 9.3% including 1.6% of HPV-16 and 0.4% of HPV-18. Of all 270 HPV positive samples, 211 (78.1% were HR-HPV non 16/18; 47 (17.4%) were HPV-16 and 12 (4.4%) were HPV-18. The prevalence of HPV infection was similar in all age groups, although a higher rate was observed in women age 31-40 years. Among women with normal cytology, HR HPV positive were found in 6.7%. In abnormal cytology, HR HPV were found 46.7% in atypical squamous cells (ASC), 54.8% in low-grade squamous intraepithelial lesions (LSIL) and 80.0% in high-grade squamous intraepithelial lesions (HSIL). HPV-16 was detected in 8.6%, 6.4% and 12.0% of ASC, LSIL and HSIL, respectively. The results of this study provide baseline information on the HPV type distribution, which may be useful for clinicians to decide who should be monitored or treated more aggressively.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권9호
• /
• pp.3997-4003
• /
• 2014

Background: Infection with certain human papillomavirus (HPV) genotypes is the most important risk factor related with cervical cancer. The objective of the present study was to investigate the prevalence of HPV infection, the distribution of HPV genotypes and HPV E6/E7 oncogene mRNA expression in Turkish women with different cervical cytological findings in Mersin province, Southern Turkey. Materials and Methods: A total of 476 cytological samples belonging to women with normal and abnormal cervical Pap smears were enrolled in the study. For the detection and genotyping assay, a PCR/direct cycle sequencing approach was used. E6/E7 mRNA expression of HPV-16, 18, 31, 33, and 45 was determined by type-specific real-time NASBA assay (NucliSENS EasyQ$^{(R)}$HPV v1.1). Results: Of the 476 samples, 106 (22.3%) were found to be positive for HPV DNA by PCR. The presence of HPV was significantly more common (p<0.001) in HSIL (6/8, 75%) when compared with LSIL (6/14, 42.9%), ASC-US (22/74, 29.7%) and normal cytology (72/380, 18.9%). The most prevalent genotypes were, in descending order of frequency, HPV genotype 66 (22.6%), 16 (20.8%), 6 (14.2%), 31 (11.3%), 53 (5.7%), and 83 (4.7%). HPV E6/E7 oncogene mRNA positivity (12/476, 2.5%) was lower than DNA positivity (38/476, 7.9%). Conclusions: Our data present a wide distribution of HPV genotypes in the analyzed population. HPV genotypes 66, 16, 6, 31, 53 and 83 were the predominant types and most of them were potential carcinogenic types. Because of the differences between HPV E6/E7 mRNA and DNA positivity, further studies are required to test the role of mRNA testing in the triage of women with abnormal cervical cytology or follow up of HPV DNA positive and cytology negative. These epidemiological data will be important to determine the future impact of vaccination on HPV infected women in our region.