A5029468817- Glioma Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- Cancer, Lipids, and Metabolism
- Computational Drug Discovery Methods
- Ferroptosis and cancer prognosis
- MicroRNA in disease regulation
- Sarcoma Diagnosis and Treatment
- Brain Metastases and Treatment
- Atmospheric aerosols and clouds
- Atmospheric and Environmental Gas Dynamics
- Gaussian Processes and Bayesian Inference
- Artificial Intelligence in Healthcare
- Meningioma and schwannoma management
- Air Quality Monitoring and Forecasting
- Domain Adaptation and Few-Shot Learning
- Colorectal and Anal Carcinomas
- Recommender Systems and Techniques
- Atmospheric chemistry and aerosols
- Anomaly Detection Techniques and Applications
- Pituitary Gland Disorders and Treatments
- Geophysics and Gravity Measurements
- Advanced Neuroimaging Techniques and Applications
- Gene expression and cancer classification
- Advanced Causal Inference Techniques
Yonsei University
2021-2024
Severance Hospital
2022
To propose a novel recursive partitioning analysis (RPA) classification model in patients with IDH-wildtype glioblastomas that incorporates the recently expanded conception of extent resection (EOR) terms both supramaximal and total resections. This multicenter cohort study included developmental 622 from single institution (Severance Hospital) validation cohorts 536 three institutions (Seoul National University Hospital, Asan Medical Center, Heidelberg Hospital). All completed standard...
Abstract There is a growing need to develop novel strategies for the diagnosis of schizophrenia using neuroimaging biomarkers. We investigated robustness diagnostic model radiomic features from T1-weighted and diffusion tensor images corpus callosum (CC). A total 165 participants [86 79 healthy controls (HCs)] were allocated training ( N = 115) test 50) sets. Radiomic CC subregions extracted T1-weighted, apparent coefficient (ADC), fractional anisotropy (FA) 1605). Following feature...
Abstract Context Early identification of the response prolactinoma patients to dopamine agonists (DA) is crucial in treatment planning. Objective To develop a radiomics model using an ensemble machine learning classifier with conventional magnetic resonance images (MRIs) predict DA patients. Design Retrospective study. Setting Severance Hospital, Seoul, Korea. Patients A total 177 who underwent baseline MRI (109 responders and 68 nonresponders) were allocated training (n = 141) test 36)...
To comprehensively investigate prognostic factors, including clinical and molecular factors treatment modalities, in adult glioma patients with leptomeningeal metastases (LM).
Lower-grade gliomas of histologic grades 2 and 3 follow heterogenous clinical outcomes, which necessitates risk stratification. This study aimed to evaluate whether diffusion-weighted perfusion-weighted MRI radiomics allow overall survival (OS) prediction in patients with lower-grade investigate its prognostic value.
Abstract. This study presents advancements in the processing of satellite remote sensing data, focusing mainly on Aerosol Optical Depth (AOD) retrievals from Geostationary Environment Monitoring Spectrometer (GEMS). The transformation Level 2 (L2) which includes atmospheric state retrievals, into higher-quality 3 (L3) data is crucial sensing. Our contributions lie two novel improvements to algorithm. First, we improve inverse distance weighting algorithm by incorporating quality flag...
To evaluate the performance of MRI-derived radiomic risk score (RRS) and PD-L1 expression to predict overall survival (OS) progression-free (PFS) patients with recurrent head neck squamous cell carcinoma receiving nivolumab therapy.
The large-scale pre-trained neural network has achieved notable success in enhancing performance for downstream tasks. Another promising approach generalization is Bayesian Neural Network (BNN), which integrates methods into architectures, offering advantages such as Model averaging (BMA) and uncertainty quantification. Despite these benefits, transfer learning BNNs not been widely investigated shows limited improvement. We hypothesize that this issue arises from the inability to find flat...
Abstract. This study presents advancements in the processing of satellite remote sensing data, focusing mainly on aerosol optical depth (AOD) retrievals from Geostationary Environment Monitoring Spectrometer (GEMS). The transformation Level-2 (L2) which includes atmospheric-state retrievals, into higher-quality Level-3 (L3) data is crucial sensing. Our contributions lie two novel improvements to algorithm. First, we improve inverse-distance-weighting algorithm by incorporating quality flag...
<p>Supplementary figure 1</p>
<p>Supplementary figure 2</p>
<p>Supplementary figure 3</p>
<div>AbstractPurpose:<p>To propose a novel recursive partitioning analysis (RPA) classification model in patients with IDH-wildtype glioblastomas that incorporates the recently expanded conception of extent resection (EOR) terms both supramaximal and total resections.</p>Experimental Design:<p>This multicenter cohort study included developmental 622 from single institution (Severance Hospital) validation cohorts 536 three institutions (Seoul National University...
<p>Supplementary Data</p>
최근 재활 치료 영역에도 딥러닝, 인공지능, 빅데이터 기술 등을 적용한 스마트 관련 개발이 활발하게 진행되고 있다. 본 논문에서는 그래프 구조를 보다 효과적으로 반영하는 신경망을 사용하여 환자개인별 특성에 맞는 개인맞춤형 운동 추천 알고리즘 기술을 제안한다. 의료법에 의해 실제 환자 데이터 사용이 불가능한 관계로 연구에서는 무릎 질환 환자의 속성 데이터를 생성하고, 다양한 프로그램을 선정하여 교차 검증을 통해 환자-운동 간의 경험 데이터셋을 생성한다. 각 사용자에 대한 모든 아이템 예측 선호도중 가장 높은 N개의 아이템을 추천하는 Top-N 시스템 시나리오에서 정밀도, 재현율, nDCG를 척도로 제안 방법의 성능을 검증한다. 생성된 데이터셋 사용시 논문에서 제안하는 방법이 기존의 알고리즘에 비해 정확도 측면에서 더욱 우수함을 보인다.
Abstract Purpose Lower-grade gliomas of histologic grade 2 and 3 follow heterogenous clinical outcomes, which necessitates risk stratification. This study aimed to evaluate whether diffusion-weighted perfusion-weighted MRI radiomics allow overall survival (OS) prediction in patients with lower-grade investigate its prognostic value. Methods In this retrospective study, radiomic features were extracted from apparent diffusion coefficient, relative cerebral blood volume map, Ktrans map...
Abstract Purpose Lower-grade gliomas of histologic grade 2 and 3 follow heterogenous clinical outcomes, which necessitates risk stratification. This study aimed to evaluate whether diffusion-weighted perfusion-weighted MRI radiomics allow overall survival (OS) prediction in patients with lower-grade investigate its prognostic value. Methods In this retrospective study, radiomic features were extracted from apparent diffusion coefficient, relative cerebral blood volume map, Ktrans map...