A5004946653- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- MRI in cancer diagnosis
- Chronic Obstructive Pulmonary Disease (COPD) Research
- COVID-19 diagnosis using AI
- Anatomy and Medical Technology
- Advanced MRI Techniques and Applications
- Medical Imaging Techniques and Applications
- Dental Radiography and Imaging
- Advanced X-ray and CT Imaging
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Orthodontics and Dentofacial Orthopedics
- Surgical Simulation and Training
- Cardiac Imaging and Diagnostics
- Medical Imaging and Analysis
- Advanced Neuroimaging Techniques and Applications
- Medical Image Segmentation Techniques
- Glioma Diagnosis and Treatment
- Colorectal Cancer Screening and Detection
- Cardiac Valve Diseases and Treatments
- Respiratory Support and Mechanisms
- Atomic and Subatomic Physics Research
- Coronary Interventions and Diagnostics
- Climate Change and Health Impacts
Asan Medical Center
2016-2025
University of Ulsan
2016-2025
Ulsan College
2016-2025
Ansan University
2024
Korea University
2009-2024
Kyungpook National University Hospital
2023-2024
Ulsan University Hospital
2010-2024
Convergence
2016-2023
Seoul National University
2004-2023
Research Institute of Radiology
2007-2023
The artificial neural network (ANN), one of the machine learning (ML) algorithms, inspired by human brain system, was developed connecting layers with neurons. However, due to low computing power and insufficient learnable data, ANN has suffered from overfitting vanishing gradient problems for training deep networks. advancement graphics processing units availability large data acquisition, outperforms or other ML capabilities in computer vision speech recognition tasks. These potentials are...
Background and Purpose— We aimed to investigate the ability of machine learning (ML) techniques analyzing diffusion-weighted imaging (DWI) fluid-attenuated inversion recovery (FLAIR) magnetic resonance identify patients within recommended time window for thrombolysis. Methods— analyzed DWI FLAIR images consecutive with acute ischemic stroke 24 hours clear symptom onset by applying automatic image processing approaches. These processes included infarct segmentation, DWI, registration feature...
Objective: This study was conducted to explore differences in cortical thickness between subjects with bipolar disorder and healthy comparison using surface‐based analysis. Methods: Brain magnetic resonance images were acquired from 25 21 subjects. Cortical analysis the Freesurfer application. Group thickness, defined by distance gray/white boundary pial surface, assessed statistical difference maps. Results: Subjects exhibited significantly decreased left cingulate cortex, middle frontal...
Abstract Purpose To evaluate whether measurement of apparent diffusion coefficient (ADC) and pure ( D ) can help to characterize solid pancreatic masses. Materials Methods Diffusion‐weighted MR imaging was performed in both a patient group n = 71; cancer [ 47], mass‐forming pancreatitis 13], pseudopapillary neoplasm 6], neuroendocrine tumor 5]) normal control 11) by applying three b‐factors 0, 500, 1000 sec/mm 2 . ADC 500 , (ADC using b ), perfusion fraction f 1‐ exp [‐500 × – )]) pancreas,...
Abstract Purpose To investigate the feasibility of diffusion‐weighted imaging (DWI) in differentiation metastatic from nonmetastatic lymph nodes. Materials and Methods In 125 patients who underwent node dissection for uterine cervical cancer, DWI was performed at b value 0 1000 s/mm 2 . By referring to surgical maps pelvic nodes, apparent diffusion coefficient (ADC) compared receiver‐operating‐characteristics analysis evaluate diagnostic performance ADC differentiating Results The were...
Institutional review board approval and written informed consent were obtained. Although xenon (Xe) ventilation CT has been introduced as a potential method with which to depict regional ventilation, quantification of Xe enhancement limited by the variability lung attenuation caused different volumes between scans. The purpose this study was assess feasibility dual-energy technique. Dual-energy performed in 12 subjects after inhalation. With use technique, component could be extracted...
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...
To prospectively evaluate the reproducibility of apparent diffusion coefficient (ADC) measurement in malignant hepatic tumors and to examine influence imaging methods, lesion location, size on ADC measurement.The institutional review board approved study protocol, informed consent was obtained. Forty-nine patients underwent both breath-hold respiratory-triggered diffusion-weighted (DW) magnetic resonance a 1.5-T system twice. Two independent readers measured largest tumor for each patient...
Purpose: To develop a semiautomated computer-aided diagnosis (cad) system for thyroid cancer using two-dimensional ultrasound images that can be used to yield second opinion in the clinic differentiate malignant and benign lesions. Methods: A total of 118 included axial longitudinal from patients with biopsy-confirmed (n = 30) 29) nodules were collected. Thyroid cad software was developed extract quantitative features these based on nodule segmentation which adaptive diffusion flow active...
To compare the influence of triggering methods for diffusion-weighted imaging (DWI) on apparent diffusion coefficient (ADC) and intravoxel incoherent motion (IVIM) parameters in liver, as well regional variability measurement repeatability.In this institutional review board-approved prospective study, 12 healthy volunteers (six women, six men; mean age, 30 years) underwent 1.5-T DWI liver by using nine b values twice with free breathing (FB) without (mean acquisition time ± standard...
Most mortalities from liver disease and cancer worldwide are attributable to hepatitis B virus (HBV) C virus. Despite remarkable advances in the treatment of HBV over past decades, limited population‐level data available regarding its impact on burden cancer. Mortality were obtained national death certificate database Korea, an HBV‐endemic country, between 1999 2013, analyzed by Joinpoint analysis. For disease, number annual deaths decreased 62.3% (95% confidence interval [CI], 62.0‐62.6),...
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)...