김태훈 교수
Tae Hoon Kim
연세대학교 흉부외과 · 의학
연구실 소개
김태훈 교수의 연구실은 의료 영상 진단과 생체 이미징 기술의 정밀화를 목표로 하며, 특히 폐암, 심장 질환, 피부암 등 주요 질환의 조기 진단을 위한 고해상도 영상 분석과 머신러닝 기반 진단 모델 개발에 주력하고 있습니다. 또한, 생체 조직의 구조적 변화를 정량적으로 평가하기 위한 MRI 기반 T1 매핑 기법과 생체 적합성 있는 자외선 차단 재료 개발 등 응용 의학 및 생체재료 분야의 융합 연구도 진행하고 있습니다. 최근에는 사이버보안 분야에서의 양자 머신러닝 기반 위협 탐지 기술 개발까지 연구 영역을 확장하고 있습니다.
연구 현황
연구 성과 추이
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
주요 논문
15Findings of this study suggest that pleomorphic carcinomas of the lung preferentially manifest as large peripheral lung neoplasms with a central low-attenuation area and frequently invade the pleura and chest wall.
A two-phase reconstruction method on cardiac MDCT is relatively simple and can provide an objective standard for reconstructing the appropriate image sets for end-diastole and end-systole without the need to review serial preview images.
The adverse effects of UV (ultraviolet) radiation on polymeric materials and organic constituents can damage the molecular structure of human skin and polymeric materials, resulting in their degradation. Therefore, additives or reagents for UV-shielding must be used in related applications, including polymer compounds and skin cosmetics. Bio-based polymers have shown great potential as alternatives to conventional metallic and organic materials (e.g., TiO2 and ZnO) in various applications; there
Skin cancer is common and deadly, hence a correct diagnosis at an early age is essential. Effective therapy depends on precise classification of the several skin cancer forms, each with special traits. Because dermoscopy and other sophisticated imaging methods produce detailed lesion images, early detection has been enhanced. It's still difficult to analyze the images to differentiate benign from malignant tumors, though. Better predictive modeling methods are needed since the diagnostic procedu
In the field of cybersecurity, hackers often enter computer systems despite current security measures, owing to the huge amount of network traffic that makes intruder identification difficult. Differentiating between authorized traffic and abnormal data produced by Distributed Denial of Service (DDoS) attackers is still a major difficulty. This research provides a unique technique that uses Quantum Machine Learning (QML) to improve security protocols for secure communication between two parties.
BACKGROUND: Post-contrast T1 mapping by modified Look-Locker inversion recovery (MOLLI) sequence has been introduced as a promising means to assess an expansion of the extra-cellular space. However, T1 value in the myocardium can be affected by scanning time after bolus contrast injection. In this study, we investigated the changes of the T1 values according to multiple slicing over scanning time at 15 minutes after contrast injection and usefulness of blood T1 correction. METHODS: Eighteen repe
대표 연구 분야
김태훈 교수의 연구를 Nubint에서 더 깊이 살펴보세요
이 연구실의 논문을 앱에서 열어 AI와 함께 읽고, 핵심을 요약하고, 내 글에 인용하세요.