A5100767784- Glioma Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- Advanced MRI Techniques and Applications
- Brain Metastases and Treatment
- Cerebrovascular and Carotid Artery Diseases
- Medical Imaging Techniques and Applications
- Intracranial Aneurysms: Treatment and Complications
- Meningioma and schwannoma management
- Advanced Neuroimaging Techniques and Applications
- CNS Lymphoma Diagnosis and Treatment
- Lanthanide and Transition Metal Complexes
- Acute Ischemic Stroke Management
- Advanced X-ray and CT Imaging
- Indian and Buddhist Studies
- Parkinson's Disease Mechanisms and Treatments
- Brain Tumor Detection and Classification
- Neurological disorders and treatments
- Liver Disease and Transplantation
- Pituitary Gland Disorders and Treatments
- Vascular Malformations Diagnosis and Treatment
- Functional Brain Connectivity Studies
- Lung Cancer Research Studies
- Congenital Heart Disease Studies
- Lymphoma Diagnosis and Treatment
Asan Medical Center
2016-2025
University of Ulsan
2016-2025
Ulsan College
2016-2025
Chosun University
2024
Samsung Medical Center
2024
Sungkyunkwan University
2024
Yonsei University
2024
Bucheon University
2024
Soonchunhyang University Hospital
2024
University of Southern California
2024
Pseudoprogression is a diagnostic challenge in early posttreatment glioblastoma. We therefore developed and validated radiomics model using multiparametric MRI to differentiate pseudoprogression from tumor progression patients with glioblastoma.The was the enlarging contrast-enhancing portions of 61 glioblastomas within 3 months after standard treatment 6472 radiomic features being obtained contrast-enhanced T1-weighted imaging, fluid-attenuated inversion recovery apparent diffusion...
Purpose To develop and validate a deep learning system (DLS) for staging liver fibrosis by using CT images in the liver. Materials Methods DLS CT-based of was created development data set that included portal venous phase 7461 patients with pathologically confirmed fibrosis. The diagnostic performance evaluated separate test sets 891 patients. influence patient characteristics techniques on accuracy logistic regression analysis. In subset 421 patients, compared radiologist's assessment,...
Purpose To test the predictive value of skewness and kurtosis changes normalized cerebral blood volume (nCBV) during early treatment period for differentiating tumor progression from pseudoprogression in patients with newly diagnosed glioblastomas. Materials Methods The institutional review board approved this retrospective study. authors assessed 135 glioblastomas who underwent concurrent chemotherapy radiation therapy (CCRT) after surgical resection. Patients developed new or enlarged...
Radiomics is a rapidly growing field in neuro-oncology, but studies have been limited to conventional MRI, and external validation critically lacking. We evaluated technical feasibility, diagnostic performance, generalizability of diffusion radiomics model for identifying atypical primary central nervous system lymphoma (PCNSL) mimicking glioblastoma.
Pseudoprogression is a treatment-related reaction with an increase in contrast-enhancing lesion size, followed by subsequent improvement. Differentiating tumor recurrence from pseudoprogression remains problem neuro-oncology.To validate the added value of arterial spin labeling (ASL), compared dynamic susceptibility contrast (DSC) perfusion magnetic resonance imaging (MRI) alone, distinguishing early progression patients newly diagnosed glioblastoma multiforme (GBM).We retrospectively...
To compare the added value of dynamic contrast material-enhanced ( CE enhanced ) DCE magnetic resonance (MR) imaging with that susceptibility DSC MR combination T1-weighted and diffusion-weighted DW diffusion weighted for predicting recurrent glioblastoma.This retrospective study was approved by institutional review board, requirement informed patient consent waived. images, images in 169 patients pathologically or clinicoradiologically diagnosed glioblastoma (n = 87) radiation necrosis 82)...
Purpose To correlate and compare diagnostic performance with amide proton transfer (APT) imaging as a tumor proliferation index that magnetic resonance (MR) spectroscopy in subgroups of patients pre- posttreatment glioma. Materials Methods This retrospective study was approved by the institutional review board. In 40 pretreatment glioma 25 glioma, correlation between APT asymmetry choline-to-creatine choline-to-N-acetylaspartate ratios corresponding voxels interest determined, 90% histogram...
Background Achieving high-spatial-resolution pituitary MRI is challenging because of the trade-off between image noise and spatial resolution. Deep learning–based reconstruction enables denoising with sharp edges reduced artifacts, which improves quality thin-slice MRI. Purpose To assess diagnostic performance 1-mm slice thickness deep (DLR) (hereafter, MRI+DLR) compared 3-mm MRI) for identifying residual tumor cavernous sinus invasion in evaluation postoperative adenoma. Materials Methods...
Abstract We aimed to establish a high-performing and robust classification strategy, using magnetic resonance imaging (MRI), along with combinations of feature extraction selection in human machine learning radiomics or deep features by employing small dataset. Using diffusion contrast-enhanced T1-weighted MR images obtained from patients glioblastomas primary central nervous system lymphomas, task was assigned combination radiomic (1) supervised after (2) multilayer perceptron (MLP)...
Abstract We evaluated the diagnostic performance and generalizability of traditional machine learning deep models for distinguishing glioblastoma from single brain metastasis using radiomics. The training external validation cohorts comprised 166 (109 glioblastomas 57 metastases) 82 (50 32 patients, respectively. Two-hundred-and-sixty-five radiomic features were extracted semiautomatically segmented regions on contrast-enhancing peritumoral T2 hyperintense masks used as input data. For each...
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...
<h3>BACKGROUND AND PURPOSE:</h3> Dynamic contrast-enhanced T1-weighted perfusion MR imaging is much less susceptible to artifacts, and its high spatial resolution allows accurate characterization of the vascular microenvironment lesion. The purpose this study was test predictive value initial final area under time signal-intensity curves ratio derived from dynamic differentiate pseudoprogression early tumor progression in patients with glioblastomas. <h3>MATERIALS METHODS:</h3> Seventy-nine...
To determine whether the ratio of initial area under time-signal intensity curve (AUC) (IAUC) to final AUC--or AUCR--derived from dynamic contrast material-enhanced magnetic resonance (MR) imaging can be an biomarker for distinguishing recurrent glioblastoma multiforme (GBM) radiation necrosis and compare diagnostic accuracy AUCR with commonly used model-free contrast-enhanced MR parameters.The institutional review board approved this retrospective study waived informed consent requirement....
<h3>BACKGROUND AND PURPOSE:</h3> Intravoxel incoherent motion can simultaneously measure diffusion and perfusion characteristics. Our aim was to determine whether the parameters derived from intravoxel could act as imaging biomarkers for distinguishing recurrent tumor treatment effect in patients with glioblastoma. <h3>MATERIALS METHODS:</h3> Fifty-one pathologically confirmed (<i>n</i> = 31) or 20) were assessed by means of MR imaging. The histogram cutoffs 90th percentiles normalized CBV...
To determine the utility of intravoxel incoherent motion (IVIM)-derived perfusion and diffusion parameters for differentiation atypical primary central nervous system lymphoma (PCNSL) from glioblastoma in patients who do not have acquired immunodeficiency syndrome.The institutional review board approved this retrospective study waived informed consent requirement. Sixty with either pathologic analysis-confirmed PCNSLs (n = 19) or glioblastomas 41) were assessed by using maximum IVIM-derived...