http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
자궁경부 영상에서의 라디오믹스 기반 판독 불가 영상 분류 알고리즘 연구
김고은,김영재,주웅,남계현,김수녕,김광기,Kim, Go Eun,Kim, Young Jae,Ju, Woong,Nam, Kyehyun,Kim, Soonyung,Kim, Kwang Gi 대한의용생체공학회 2021 의공학회지 Vol.42 No.5
Recently, artificial intelligence for diagnosis system of obstetric diseases have been actively studied. Artificial intelligence diagnostic assist systems, which support medical diagnosis benefits of efficiency and accuracy, may experience problems of poor learning accuracy and reliability when inappropriate images are the model's input data. For this reason, before learning, We proposed an algorithm to exclude unread cervical imaging. 2,000 images of read cervical imaging and 257 images of unread cervical imaging were used for this study. Experiments were conducted based on the statistical method Radiomics to extract feature values of the entire images for classification of unread images from the entire images and to obtain a range of read threshold values. The degree to which brightness, blur, and cervical regions were photographed adequately in the image was determined as classification indicators. We compared the classification performance by learning read cervical imaging classified by the algorithm proposed in this paper and unread cervical imaging for deep learning classification model. We evaluate the classification accuracy for unread Cervical imaging of the algorithm by comparing the performance. Images for the algorithm showed higher accuracy of 91.6% on average. It is expected that the algorithm proposed in this paper will improve reliability by effectively excluding unread cervical imaging and ultimately reducing errors in artificial intelligence diagnosis.
평활화 알고리즘에 따른 자궁경부 분류 모델의 성능 비교 연구
김윤지,박예랑,김영재,주웅,남계현,김광기,Kim, Youn Ji,Park, Ye Rang,Kim, Young Jae,Ju, Woong,Nam, Kyehyun,Kim, Kwang Gi 대한의용생체공학회 2021 의공학회지 Vol.42 No.3
We developed a model to classify the absence of cervical cancer using deep learning from the cervical image to which the histogram equalization algorithm was applied, and to compare the performance of each model. A total of 4259 images were used for this study, of which 1852 images were normal and 2407 were abnormal. And this paper applied Image Sharpening(IS), Histogram Equalization(HE), and Contrast Limited Adaptive Histogram Equalization(CLAHE) to the original image. Peak Signal-to-Noise Ratio(PSNR) and Structural Similarity index for Measuring image quality(SSIM) were used to assess the quality of images objectively. As a result of assessment, IS showed 81.75dB of PSNR and 0.96 of SSIM, showing the best image quality. CLAHE and HE showed the PSNR of 62.67dB and 62.60dB respectively, while SSIM of CLAHE was shown as 0.86, which is closer to 1 than HE of 0.75. Using ResNet-50 model with transfer learning, digital image-processed images are classified into normal and abnormal each. In conclusion, the classification accuracy of each model is as follows. 90.77% for IS, which shows the highest, 90.26% for CLAHE and 87.60% for HE. As this study shows, applying proper digital image processing which is for cervical images to Computer Aided Diagnosis(CAD) can help both screening and diagnosing.
이수윤 ( Soo Yoon Lee ),주웅 ( Woong Ju ) 대한산부인과학회 2009 Obstetrics & Gynecology Science Vol.52 No.9
경계성 난소종양 치료로는 철저한 외과적 병기설정 이후 정기적인 추적 관찰을 하는 방법이 행해지고 있다. 최근의 경향은 예후가 양호할 것으로 예측되는 젊은 여성 환자들에게 보존적 방법의 치료를 시행하는 것인데, 이러한 보존적 치료의 안전성이 완전히 확립된 것은 아니다. 본 종설은 최근에 발표된 연구들을 중심으로 경계성 난소종양의 치료에 대한 최신 지견을 고찰 해 본다. 재발 위험을 가늠하기 위해 외과적 병기설정은 필수적인데, 가임력을 보존하는 수술의 경우라도 자궁절제술과 반대측 난소절제술을 제외한 적절한 외과적 병기설정은 필요하다. 1기 환자의 경우 가임력을 보존하는 수술을 시행할 수 있으며, 그 이상 진행된 환자에게는 근치적 수술이 필요하다. 수술 후 보조화학요법이나 복강경하 병기설정의 역할은 현재까지 확실하지 않다. The mainstream in management of borderline ovarian tumor has been thorough surgical staging and close observation. Recent trends prefer conservative management especially for the young, reproductive aged women due to the good prognosis profile and wide use of laparoscopy, although the safety for oncologic outcome of conservative treatment has not been fully established. The present article updates published literatures respecting management of borderline ovarian tumor. A proper staging procedure is necessary for all the patients to estimate the risk of recurrence. Fertility-sparing surgery is a tolerable option in young patients with stage I disease. Patients with advanced-stage disease or who are finished childbearing are treated with radical surgery. The roles of adjuvant chemotherapy or laparoscopic staging are not definite up to now.
공공보건의료인력 임상교육효과 평가: 지역거점공공병원 간호사 대상
신윤희 ( Yoonhee Shin ),박관준 ( Kwanjun Park ),변은경 ( Eunkyung Byun ),이동원 ( Dongwon Lee ),주웅 ( Woong Ju ) 한국보건행정학회 2016 보건행정학회지 Vol.26 No.4
Background: The purpose of this study is to evaluate the outcomes of clinical education program for nurses in regional public hospital, utilizing the Kirkpatrick`s model. Methods: Kirkpatrik`s 4-level model was applied to this study. Trainees were asked to fill out questionnaires in the middle and at the end of the program. Also administrators of excellent trainees were asked to fill out the questionnaires regarding nursing management performance after 1-2 months from the end of the training course. Results: All trainees had positive reactions to the clinical education program. Not only the results of individual level (satisfaction and achievement scores, academic achievement scores, practical application rate, and educational transition factors) but also the scores of organization level (nursing management performance scores) are improved. Conclusion: By showing a correlation between the effectiveness factors we need to verify the relationship between these factors in a future study. In addition, development of quantitative and qualitative performance indicators are needed. To establish a long-term education system, it is required to applying the excellent trainee`s successful experiences.