http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김광기,우성호,이경민 대한신경과학회 2005 대한신경과학회지 Vol.23 No.1
Background: Graphesthesia is the ability to recognize letters or symbols via somatic sensation. We employed functional MRI to determine neurological substrates underlying this ability. We also designed a behavioral experiment to examine the relationship between graphesthesia and working memory. Methods: Images were acquired in a 1.5T scanner from ten right-handed normal subjects while tactile stimulation was applied for either graphesthesia or simple sensation. Additional eight right-handed normal observers participated in the behavioral experiment where they performed a visuo-spatial or a verbal working memory task, simultaneously with graphesthesia. Overall performance times were measured to detect interference in the dual-task situations. Results: Comparison between graphesthesia and simple sensory stimulation revealed activations at bilateral prefrontal, parietal and superior temporal cortices, regardless of the hand stimulated. The right parietal operculum was activated for both hand conditions, while the corresponding area in the left hemisphere was activated by right-hand stimulation only, suggesting a right-hemisphere dominance for graphesthesia. From the behavioral experiments, we observed that the visuo-spatial task, but not the verbal task, interfered with graphaesthesia. Conclusions: Taken together, these results suggest that the brain areas underlying the visuo-spatial sub-system of working memory are involved in graphesthesia and that some cognitive processes underlying graphesthesia are right-lateralized.
Detection and Weak Segmentation of Masses in Gray-Scale Breast Mammogram Images Using Deep Learning
김광기,김영재 연세대학교의과대학 2022 Yonsei medical journal Vol.63 No.-
Purpose: In this paper, we propose deep-learning methodology with which to enhance the mass differentiation performance of convolutional neural network (CNN)-based architecture. Materials and Methods: We differentiated breast mass lesions from gray-scale X-ray mammography images based on regions of interest (ROIs). Our dataset comprised breast mammogram images for 150 cases of malignant masses from which we extracted the mass ROI, and we composed a CNN-based deep learning model trained on this dataset to identify ROI mass lesions. The test dataset was created by shifting some of the training data images. Thus, although both datasets were different, they retained a deep structural similarity. We then applied our trained deep-learning model to detect masses on 8-bit mammogram images containing malignant masses. The input images were preprocessed by applying a scaling parameter of intensity before being used to train the CNN model for mass differentiation. Results: The highest area under the receiver operating characteristic curve was 0.897 (Î 20). Conclusion: Our results indicated that the proposed patch-wise detection method can be utilized as a mass detection and segmentation tool.