Soo Yeol Lee
경희대학교 생체의공학과 · 공학
이 교수의 연구실은 의료 영상의 품질 향상과 정밀 진단을 목표로 하며, 특히 전자기파 영상법(예: EPT, CT)에서 발생하는 잡음과 금속 아티팩트 문제를 해결하는 데 중점을 두고 있습니다. 수용성 물리적 특성과 조직의 전기적 성질 간의 관계를 규명하는 데 기여한 바 있으며, 딥러닝 기반 분광 분석 및 생성적 적대 신경망(GAN)을 활용한 저선량 CT 영상 복원 기술 개발도 진행하고 있습니다. 특히 치과 영상에서의 금속 아티팩트 보정 및 고해상도 영상 복원 기술은 임상적 응용가능성이 매우 높습니다.
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
Human brain and phantom EP images suggest that water content is a dominating factor in determining the electrical properties of tissues. Despite possible literature inaccuracies, the proposed method offers EP maps that can provide complementary information to current approaches, to facilitate EPT scans in clinical applications. Magn Reson Med 77:1094-1103, 2017. © 2016 International Society for Magnetic Resonance in Medicine.
We examined fatigue-crack-growth behaviors of CoCrFeMnNi high-entropy alloys (HEAs) under as-fatigued and tensile-overloaded conditions using neutron-diffraction measurements coupled with diffraction peak-profile analyses. We applied both high-resolution transmission electron microscopy (HRTEM) and neutron-diffraction strain mapping for the complementary microstructure examinations. Immediately after a single tensile overload, the crack-growth-retardation period was obtained by enhancing the fat
Influences of chemical dilution and the number of weld layers on residual stresses in a multi-pass low-transformation-temperature (LTT) weld were investigated by finite element modelling and neutron diffraction. A coupled thermal-metallurgical-mechanical (TMM) model that took into account the chemical dilution effect was developed to simulate the complex LTT welding phenomena. The model was strictly validated by comparing the predictions with experimental measurements and the results found good
Abstract In this study, we propose a single‐layer multiple‐kernel‐based convolutional neural network (SLMK‐CNN) as an analysis tool for biological Raman spectra. We investigated the characteristics of SLMK‐CNN and then analyzed and classified the biological Raman spectra by optimizing the structure of SLMK‐CNN. We have found that the kernel size used in SLMMK‐CNN plays an important role in changing the characteristics of Raman spectra such as intensity and peak position. As a result, the kernel
The successful development of the image denoising techniques for low-dose computed tomography (LDCT) was largely owing to the public-domain availability of spatially-aligned high- and low-dose CT image pairs. Even though low-dose CT scans are also highly desired in dental imaging, public-domain databases of dental CT image pairs have not been established yet. In this paper, we propose a dental CT image denoising method based on the transfer learning of a generative adversarial network (GAN) from
