Sae-Kwang Lee
Korea University · Medicine
About the Lab
Professor Sae-Kwang Lee's research lab specializes in neuroimaging and artificial intelligence applications in neurological disorders, with a focus on stroke, aphasia, depression, and cerebellar ataxia. The lab integrates advanced neuroimaging techniques—such as diffusion tensor imaging (DTI), structural MRI, and fMRI—with machine learning and explainable AI to predict clinical outcomes and uncover neural mechanisms. Key research directions include identifying biomarkers for language and motor recovery post-stroke, analyzing structural brain changes in mood disorders, and developing interpretable models for clinical decision support. The lab emphasizes translational neuroscience, bridging neuroimaging findings with real-world clinical data to improve patient outcomes.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15This study investigated factors associated with aphasia severity at both 2 weeks and 3 months after stroke using demographic and clinical variables, brain diffusion tensor imaging (DTI) parameters, and lesion volume measurements. Patients with left hemisphere stroke were assessed at 2 weeks (n = 68) and at 3 months (n = 20) after stroke. Demographic, clinical, and neuroimaging data were collected; language functions were assessed using the Western Aphasia Battery. For neuroimaging, DTI parameter
OBJECTIVE: This study aimed to investigate the morphometric differences in the corpus callosum between patients with major depressive disorder (MDD) and healthy controls and analyze their relationship to gray matter changes. METHODS: Twenty female MDD patients and 21 healthy controls (HCs) were included in the study. To identify the difference in the regional gray matter concentration (GMC), VBM was performed with T1 magnetic resonance imaging. The shape analysis of the corpus callosum was proce
Swallowing disorders occur more frequently in older adults. However, the effects of the aging process on neural activation when swallowing are unclear. We aimed to identify neural regions activated during swallowing and evaluate changes in neural activation and neural networks with aging. Using a general linear model (GLM) and independent component (IC) analyses, blood oxygen level-dependent (BOLD) signals were observed in the lateral precentral gyrus, postcentral gyrus, anterior insular cortice
This study develops explainable artificial intelligence for predicting safe balance using hospital data, including clinical, neurophysiological, and diffusion tensor imaging properties. Retrospective data from 92 first-time stroke patients from January 2016 to June 2023 was analysed. The dependent variables were independent mobility scores, i.e., Berg Balance Scales with 0 (45 or below) vs. 1 (above 45) measured after three and six months, respectively. Twenty-nine predictors were included. Rand
BACKGROUND: The aim of this review is to highlight the new advance of predictive and explainable artificial intelligence for neuroimaging applications. METHODS: Data came from 30 original studies in PubMed with the following search terms: "neuroimaging" (title) together with "machine learning" (title) or "deep learning" (title). The 30 original studies were eligible according to the following criteria: the participants with the dependent variable of brain image or associated disease; the interve
Cerebellar mutism (CM) is a rare neurological condition characterized by lack of speech due to cerebellar lesions. CM is often reported in children. We describe a rare case of CM after spontaneous cerebellar hemorrhage. The patient showed mutism, irritability, decreased spontaneous movements and oropharyngeal apraxia. Diffusion tensor imaging revealed significant volume reduction of medial frontal projection fibers from the corpus callosum. In Tracts Constrained by UnderLying Anatomy (TRACULA) a
Acute ischemic stroke is the leading cause of morbidity and mortality worldwide. Recombinant tissue plasminogen activator (rtPA) is the only agent clinically approved by FDA for patients with acute ischemic stroke. However, delayed treatment of rtPA (e.g., more than 3 h after stroke onset) exacerbates ischemic brain damage by causing intracerebral hemorrhage and increasing neurotoxicity. In the present study, we investigated whether the neuroprotant otaplimastat reduced delayed rtPA treatment-ev
An ischemic cerebral stroke results from the interruption of blood flow to the brain, triggering rapid and complex cascades of excitotoxicity, oxidative stress, and inflammation. Current reperfusion therapies, including intravenous thrombolysis and mechanical thrombectomy, cause further brain injury due to reperfusion-induced cytotoxicity. To date, novel cytoprotective therapies that could address these challenges have yet to be developed, likely due to the limitations of targeting a single path
This retrospective study aimed to predict dexterity at 3 and 6 months post-stroke by integrating clinical, neurophysiological, and neuroimaging factors. We included 126 patients with first-ever, unilateral, and supratentorial stroke. Demographic, stroke characteristics, and initial clinical assessment variables [Mini-mental state examination and Fugl-Meyer Assessment Upper Extremity (FMA-UE)] were evaluated 2 weeks after stroke. Dexterity, measured using the Manual Function Test (MFT) hand subsc
BACKGROUND AND PURPOSE: Tinnitus is a condition in which individuals perceive sounds, such as ringing or buzzing, without any external source. Although the exact cause is not fully understood, recent studies have indicated the involvement of nonauditory brain structures, including the limbic system. We aimed to compare the volumes of specific brain structures between patients with tinnitus and controls. METHODS: Voxel-based morphometry and subfield volumetry were applied to analyze the brain str
현재 전세계적으로 이동통신 단말기의 발전은 빠른 속도 진행중이다. 기본적인 전화 통화이외에 다양한 멀티미디어 서비스 및 국제적 로밍이 가능한 3세대 이동통신으로 가고 있으며 이에 따라 더욱 생활 필수품이 될 것이다. 이처럼 많은 편리성을 제공해주는 이동통신 서비스에 있어 개인의 사생활 보호 및 안전한 데이터 전송은 필수적 요소이다. 3세대 이동통신 서비스를 제공하려는 비동기식, 동기식 진영 양쪽 모두 사용자의 인증 기능을 정의하고 있다. 이 인증기능은 자바카드 기반의 USIM, UIM application에 포함되어 제공될 것이다. 본 논문에서는 두방식의 인증 메커니즘과 키생성 메커니즘을 살펴보고 자바카드와 동일한 환경에서 구현한 내용과 테스트한 결과에 대하여 설명한다. 또 표준에서 불분명하게 정의되어 실제 Java card에서 구현시 발생할 수 있는 문제에 대하여 분석하였다.
Research Areas
Dive deeper into Sae-Kwang Lee's research on Nubint
Open this lab's papers in the app to read with AI, summarize, and cite in your writing.