http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
이언석,배서연 대한전기학회 2021 전기학회논문지 Vol.70 No.6
The condition of the capillaries is directly affected by inflammatory cells in the disease, resulting in abnormal changes in the occurrence of the disease. Capillary observations can identify not only the current condition of the disease but also the expected diseases, which is of great importance. Existing nail capillary examinations are difficult to obtain optimal images by light reflection by oil and are being conducted by the examiner’s supervision, so there are difficulties in objective diagnosis. Also, it is difficult for busy modern people to visit the hospital because they need expensive equipment. Thus, this study developed an imaging algorithm that produces observational devices that can be simply mounted and used in mobile devices and automatically divides capillaries from the background. This study allows users to obtain images without being constrained by space and to observe capillary conditions quickly through objective and intuitive data.
이언석,문초이,백유상,최민형 대한전기학회 2022 전기학회논문지 Vol.71 No.12
Psoriasis is a chronic recurrent disease formed by lesions such as erythema and scale. To evaluate the severity of psoriasis, the psoriasis area and severity index (PASI) score have been used in clinical trials and studies. This clinical indicator is subjective, so to overcome these shortcoming, various automatic psoriasis analysis methods based on deep learning have been studied. However, the limited number of data and psoriasis characteristic such as ambiguity of severity deteriorate model performance. One of the simple and powerful methods to overcome these problem is data augmentation. Data augmentation should be used according to data characteristics. Therefore, we analyzed and compared the classification results applied with five data augmentation methods, Geometric transformation, CutMix, Visual Corruptions, AutoAugment, RandAugment, and explored data augmentation method suitable for psoriasis severity classification. We used the EfficientNet B2 for psoriasis severity classification. As a result, when RandAugment or the combination of Geometric transform and Visual Corruptions were used, it showed the best classification performance with an accuracy of 87.5%. In addition, we confirmed the effect of data augmentation for improving model performance and the difference in performance according to single or multiple applications of the data augmentation methods. Through these results, our study can be applied to various studies as a data augmentation method suitable for psoriasis disease image.
이언석,김민기,하승한 한국융합학회 2012 한국융합학회논문지 Vol.3 No.4
초음파 영상 진단 장치에서 획득한 데이터로부터 진단 객체를 추출하기 위한 영상 분할은 질병의 효과적 인 진단을 위하여 필수적인 전처리 과정으로 인식되고 있으며, 지금까지 많은 분할 기법들이 연구되고 있다. 본 연 구에서는 혈관 초음파 영상의 다양한 응용 및 진단법 개발을 위하여 기초 전처리과정으로서 graph cut 알고리즘에 의한 상호적인 영상분할법을 제시한다. 일반영상 및 혈관 초음파 영상에 대하여 전경(foreground)과 배경 (background)의 제약조건을 주고 영상분할 처리하여, 원하는 object에 대한 분할 결과를 얻었다. 향후, 이러한 일련 의 처리 과정이 실시간으로 처리되면 새로운 초음파 진단법으로 발전시켜 나갈 수 있을 것으로 사료된다.