Bo Kyu Kim
Korea University · 医学
研究室紹介
Professor Bo Kyu Kim's research lab specializes in advanced neuroimaging techniques and artificial intelligence applications in cerebrovascular disease. The lab focuses on optimizing MRI sequences—such as DWI, PETRA-MRA, and time-resolved MRA—for improved diagnosis and follow-up of intracranial aneurysms and acute ischemic stroke. A key research direction involves leveraging deep learning, including CycleGAN and DNN-based reconstruction, to enhance image quality and enable synthetic imaging for faster, more accurate stroke assessment. The lab also investigates quantitative imaging biomarkers, such as infarct volume on CTP, to predict clinical outcomes after endovascular thrombectomy.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15According to our preliminary results, contrast staining might be differentiated from hemorrhagic transformation using an immediate postinterventional DWI protocol including gradient recalled-echo sequences. It might be possible to expedite establishment of postinterventional medical treatment strategy.
BACKGROUND: The optimal magnetic resonance angiography (MRA) sequence for assessing the aneurysm occlusion state or in-stent flow after endovascular coiling is not well established. OBJECTIVE: To evaluate the diagnostic performance of pointwise encoding time reduction with radial acquisition (PETRA)-MRA in patients who underwent endovascular coiling relative to that of time-of-flight (TOF)-MRA and contrast-enhanced (CE)-MRA. METHODS: We evaluated the aneurysm occlusion state using digital subtra
BACKGROUND: Pointwise encoding time reduction with radial acquisition (PETRA) magnetic resonance angiography (MRA) is useful for evaluating intracranial aneurysm recurrence, but the problem of severe background noise and low peripheral signal-to-noise ratio (SNR) remain. Deep learning could reduce noise using high- and low-quality images. PURPOSE: To develop a cycle-consistent generative adversarial network (cycleGAN)-based deep learning model to generate synthetic TOF (synTOF) using PETRA. STUD
A CycleGAN-based deep learning model was developed to generate synthetic TOF from time-resolved MRA. Synthetic TOF can potentially assist in the detection of large-vessel occlusion in stroke centers using time-resolved MRA.
Purpose: The purpose of this study is to improve the qualitative and quantitative image quality of the time-resolved angiography with interleaved stochastic trajectories technique (4D-TWIST-MRA) using deep neural network (DNN)-based MR image reconstruction software. Materials and Methods: A total of 520 consecutive patients underwent 4D-TWIST-MRA for ischemic stroke or intracranial vessel stenosis evaluation. Four-dimensional DNN-reconstructed MRA (4D-DNR) was generated using commercially availa
Background/Objectives: This study aimed to evaluate the incidence, risk factors, clinical implications, and rescue maneuvers of technical complications related to embolic protection devices (EPDs) during carotid artery stenting (CAS). Materials and Methods: We retrospectively reviewed all patients who had undergone CAS with EPDs between April 2018 and March 2024. The incidence and types of technical complication associated with EPDs were assessed. Clinical, angiographical, and procedural factors
Background Arterial pulsatility is one of the driving forces of glymphatic flow. Objectives To evaluate the feasibility of the pulsatility index (PI) of cortical arteries in the centrum semiovale (PI CSO ) as a novel non-invasive imaging biomarker for Alzheimer’s disease (AD) in the context of glymphatic function. Design Retrospective cross-sectional study. Setting Single tertiary academic center equipped with both 3.0 T MRI systems. Participants A total of 160 individuals were enrolled: 50 heal
Background/Objectives: The cavernous sinus air sign, historically linked to trauma or venous sinus thrombosis, has recently been reported in association with retrograde venous air embolism, often without clinical significance. Despite this, its exact prevalence, etiology, and clinical relevance remain unclear. This study aims to systematically evaluate the incidence of the cavernous sinus air sign in patients undergoing CT angiography (CTA) and to assess its potential clinical implications. Meth
Background and Purpose: This study aimed to identify the imaging characteristics and discriminate the etiology of acute internal carotid artery occlusion (ICAO) on computed tomography angiography (CTA) in patients with acute ischemic stroke. Materials and Methods: We retrospectively evaluated consecutive patients who underwent endovascular thrombectomy for acute ICAO. Contrast filling of the extracranial ICA in preprocedural CTA was considered apparent ICAO. Non-contrast filling of the extracran