http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Clinical Implication and Risk Factors for Malignancy of Atypical Gastric Gland during Forceps Biopsy
( Min Seong Kim ),( Sang Gyun Kim ),( Hyunsoo Chung ),( Jung Kim ),( Hyoungju Hong ),( Hee Jong Lee ),( Hyun Ju Kim ),( Min A Kim ),( Woo Ho Kim ),( Hyun Chae Jung ) 대한간학회 2018 Gut and Liver Vol.12 No.5
Background/Aims: Although forceps biopsy is performed for suspicious gastric tumors during endoscopy, it is difficult to determine treatment strategies for atypical gastric glands due to uncertainty of the diagnosis. The aim of this study was to investigate clinical implications and risk factors for predicting malignancy in atypical gastric glands during forceps biopsy. Methods: We retrospectively reviewed medical records of 252 patients with a diagnosis of atypical gastric gland during forceps biopsy. Predictors of malignancy were analyzed using initial endoscopic findings and clinical data. Results: The final diagnosis for 252 consecutive patients was gastric cancer in 189 (75%), adenoma in 26 (10.3%), and gastritis in 37 (14.7%). In the multivariate analysis, lesion sizes of more than 10 mm (odds ratio [OR], 3.021; 95% confidence interval [CI], 1.480 to 6.165; p=0.002), depressed morphology (OR, 3.181; 95% CI, 1.579 to 6.406, p=0.001), and surface nodularity (OR, 3.432; 95% CI, 1.667 to 7.064, p=0.001) were significant risk factors for malignancy. Conclusions: Further evaluation and treatment should be considered for atypical gastric gland during forceps biopsy if there is a largesized (>10 mm) lesion, depressed morphology, or surface nodularity. (Gut Liver 2018;12:523-529)
Self-Attention을 적용한 문장 임베딩으로부터 이미지 생성 연구
유경호(Kyungho Yu),노주현(Juhyeon No),홍택은(Taekeun Hong),김형주(Hyoungju Kim),김판구(Pankoo Kim) 한국스마트미디어학회 2021 스마트미디어저널 Vol.10 No.1
사람이 어떤 문장을 보고 그 문장에 대해 이해하는 것은 문장 안에서 주요한 단어를 이미지로 연상시켜 그 문장에 대해 이해한다. 이러한 연상과정을 컴퓨터가 할 수 있도록 하는 것을 text-to-image라고 한다. 기존 딥 러닝 기반 text-to-image 모델은 Convolutional Neural Network(CNN)-Long Short Term Memory(LSTM), bi-directional LSTM을 사용하여 텍스트의 특징을 추출하고, GAN에 입력으로 하여 이미지를 생성한다. 기존 text-to-image 모델은 텍스트 특징 추출에서 기본적인 임베딩을 사용하였으며, 여러 모듈을 사용하여 이미지를 생성하므로 학습 시간이 오래 걸린다. 따라서 본 연구에서는 자연어 처리 분야에서 성능 향상을 보인 어텐션 메커니즘(Attention Mechanism)을 문장 임베딩에 사용하여 특징을 추출하고, 추출된 특징을 GAN에 입력하여 이미지를 생성하는 방법을 제안한다. 실험 결과 기존 연구에서 사용되는 모델보다 inception score가 높았으며 육안으로 판단하였을 때 입력된 문장에서 특징을 잘 표현하는 이미지를 생성하였다. 또한, 긴 문장이 입력되었을 때에도 문장을 잘 표현하는 이미지를 생성하였다. When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.
Clinical efficacy of endoscopic ultrasonography for decision of treatment strategy of gastric cancer
Kim, Jung,Kim, Sang Gyun,Chung, Hyunsoo,Lim, Joo Hyun,Choi, Ji Min,Park, Jae Yong,Yang, Hyo-Joon,Han, Seung Jun,Oh, Sooyeon,Kim, Min Seong,Kim, Hyun Ju,Hong, Hyoungju,Lee, Hee Jong,Kim, Jue Lie,Lee, E Springer-Verlag 2018 Surgical endoscopy Vol.32 No.9