http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김대겸(Daegyeom Kim),박재희(Jaehee Park),정병창(ByeongChang Jeong),한철(Cheol E. Han) 대한전자공학회 2020 대한전자공학회 학술대회 Vol.2020 No.8
An essential part of our brain is a complex structure of neural fibers connecting parts of the brain. This complex structure forms a brain network that has an important role in information communication between brain regions. Since the efficient information communication in the brain is associated with the higher intelligence and longer education duration, it is still in debate what aspect of brain networks is crucial in cognitive development. In this study, we analyzed the effects of the education duration on the information communication patterns using communicability that captures the total information flows through all possible communication pathways between brain regions, not only through the shortest path. We observed that the more-educated individuals have increased communicability in the left hemisphere, and decreased interhemispheric communicability, implying that the more specialization on the left hemisphere as education duration increases.
3D U-Net을 이용한 비등방성(non-isotropic) 의료 영상의 등방성(isotropic) 의료 영상으로의 변환기법 연구
김대겸(Daegyeom Kim),최명원(Myeoungwon Choi),김지현(Ji Hyun Kim),한철(Cheol E. Han) 대한전자공학회 2018 대한전자공학회 학술대회 Vol.2018 No.6
Fluid Attenuated Inversion Recovery (FLAIR) images are widely used for diagnostic and medical imaging studies related to brain diseases. However, FLAIR images are often inappropriate for research aims, since their spatial resolution in the z-axis is lower than the other two axes to reduce the acquisition time in most hospitals. Thus, conversion from non-isotropic FLAIR images to isotropic FLAIR images is quite useful. On the other hands, since the medical image is often required to be high-resolution, and thus the size of image is quite large. It causes memory space deficiency for analysis medical images using deep learning, which must be solved for medical image research. In this study, we employed and modified U-net that is widely used for super-resolution applications. We not only restored images that were not obtained, but also suggested a solution for memory deficiency for handling large-sized medical images.
이창석(Changseok Lee),김대겸(Daegyeom Kim),정병창(ByeongChang Jeong),이주영(Joo Young Lee),이현주(Hyun Ju Lee),한철(Cheol E. Han) 대한전자공학회 2020 대한전자공학회 학술대회 Vol.2020 No.8
Autism Spectrum Disorder (ASD) is a condition due to abnormal brain development, with problems mainly in language, and socialization skills. As a cause of these symptoms, inferior information integration function in patients with ASD was proposed. Instead, they exhibit superior local functional specialization. Recently, it is proposed that asymmetry of the brain network may be a key to explain the disease. In this study, we studied brain networks extracted from magnetic resonance (MR) images of normal and autistic children between the ages of 2 and 5 through network analysis. We found that the intra-hemispheric regional efficiency of the right hemisphere in ASD significantly larger than the one in the normal, while there was no difference in the left hemisphere, and the inter-hemispheric connections. Also, while the intra-hemispheric regional efficiency of the left hemisphere is significantly different from the one of the right hemisphere in the normal, in the ASD, they are significantly different each other. This captures that symmetry of regional efficiency in the ASD while asymmetry in the normal. The increased intra-hemispheric regional efficiency of the right hemisphere in the ASD is because of increased regional efficiency in the right Precuneus, middle temporal gyrus, and inferior temporal gyrus.
그래프 합성곱 신경망을 이용한 아밀로이드 단백질 확산 시뮬레이션 모델 개발
정병창(ByeongChang Jeong),김대겸(Daegyeom Kim),Marcus Kaiser,한철(Cheol E. Han) 대한전자공학회 2021 대한전자공학회 학술대회 Vol.2021 No.6
The Alzheimer’s Disease (AD) is a neuro-degenerative disease which impairs cognitive functions. One hypothesis of its development is the accumulation and spread of amyloid-β in the brain, leading neuronal cell deaths and consequent cognitive declines. Recent simulation studies focused on these processes to unveil their roles in disease progression through mathematical models. However, it is a challenging problem to estimate the model parameters for precise simulation due to their high model complexities. In this study, we employed graph convolutional neural network (GCN) to overcome this difficulty. GCN captures information flows between artificial neurons of the model through the given connectivity information, and its dynamics is similar to spreading of the toxic protein. We quantified the amount of its accumulation, and the connectivity between brain regions from various brain MR images of actual patients. Our GCN model well predicted the spread of the amyloid-β, showing high correlation with the real data.