A5089915992- Electrical and Bioimpedance Tomography
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Geophysical and Geoelectrical Methods
- Dental Radiography and Imaging
- Radiation Dose and Imaging
- Microwave Imaging and Scattering Analysis
- Non-Destructive Testing Techniques
- Numerical methods in inverse problems
- Medical Image Segmentation Techniques
- Forensic Anthropology and Bioarchaeology Studies
- Advanced Vision and Imaging
- Orthodontics and Dentofacial Orthopedics
- Ultrasonics and Acoustic Wave Propagation
- Advanced Numerical Methods in Computational Mathematics
- AI in cancer detection
- Microfluidic and Bio-sensing Technologies
- Electromagnetic Scattering and Analysis
- Brain Tumor Detection and Classification
- Quantum Dots Synthesis And Properties
- Advanced MRI Techniques and Applications
- Dental Implant Techniques and Outcomes
- Hemodynamic Monitoring and Therapy
- Image Retrieval and Classification Techniques
- Flow Measurement and Analysis
National Institute for Mathematical Sciences
2015-2025
Korea Advanced Institute of Science and Technology
2006-2010
Arizona State University
2009
Retinal swelling due to the accumulation of fluid is associated with most vision-threatening retinal diseases. Optical coherence tomography (OCT) current standard care in assessing presence and quantity image-guided treatment management. Deep learning methods have made their impact across medical imaging, many OCT analysis been proposed. However, it currently not clear how successful they are interpreting on OCT, which lack standardized benchmarks. To address this, we organized a challenge...
This paper presents a new approach to automatic three-dimensional (3D) cephalometric annotation for diagnosis, surgical planning, and treatment evaluation. There has long been considerable demand automated landmarking, since manual landmarking requires time experience as well objectivity scrupulous error avoidance. Due the inherent limitation of two-dimensional (2D) cephalometry 3D nature simulation, there is trend away from current 2D cephalometry. Deep learning approaches seem highly...
Abstract The lengthy time needed for manual landmarking has delayed the widespread adoption of three-dimensional (3D) cephalometry. We here propose an automatic 3D cephalometric annotation system based on multi-stage deep reinforcement learning (DRL) and volume-rendered imaging. This considers geometrical characteristics landmarks simulates sequential decision process underlying human professional patterns. It consists mainly constructing appropriate two-dimensional cutaway or model view,...
Abstract Background In X‐ray computed tomography (CT), metal‐induced beam hardening artifacts arise from the complex interactions between polychromatic beams and metallic objects, leading to degraded image quality impeding accurate diagnosis. A previously proposed correction (MBHC) method provides a theoretical framework for addressing nonlinear through mathematical analysis, with its effectiveness demonstrated by numerical simulations phantom experiments. However, in practical applications,...
Abstract We solve elliptic interface problems using a discontinuous Galerkin (DG) method, for which discontinuities in the solution and its normal derivatives are prescribed on an inside domain. Standard ways to with finite element methods consist enforcing discontinuity of space. Here, we show that DG method provides natural framework enforce both weakly formulation, provided triangulation domain is fitted interface. The resulting discretization leads symmetric system can be efficiently...
The topological derivative-based non-iterative imaging algorithm has demonstrated its applicability in limited-aperture inverse scattering problems. However, this been confirmed through many experimental simulation results, and the reason behind not satisfactorily explained. In paper, we identify mathematical structure certain properties of derivatives for two-dimensional crack-like thin penetrable electromagnetic inhomogeneities that are completely embedded a homogeneous material. To end,...
The aims of this study were to determine the predictive value decision support analysis for shock wave lithotripsy (SWL) success rate and analyze data obtained from patients who underwent SWL assess factors influencing outcome by using machine learning methods. We retrospectively reviewed medical records 358 urinary stone (kidney upper-ureter stone) between 2015 2018 evaluated possible prognostic features, including patient population characteristics, characteristics on a non-contrast,...
To evaluate the diagnostic performance of a deep learning algorithm for automated detection developmental dysplasia hip (DDH) on anteroposterior (AP) radiographs.
Abstract Purpose Dental cone‐beam computed tomography (CBCT) has been increasingly used for dental and maxillofacial imaging. However, the presence of metallic inserts, such as implants, crowns, braces, violates CT model assumption, which leads to severe metal artifacts in reconstructed CBCT image, resulting degradation diagnostic performance. In this study, we deep learning reduce artifacts. Methods The artifacts, appearing streaks shadows, are nonlocal highly associated with various...
Magnetic resonance electrical impedance tomography (MREIT) is a new bio-imaging modality providing cross-sectional conductivity images from measurements of internal magnetic flux densities produced by externally injected currents. Recent experimental results postmortem and in vivo imaging the canine brain demonstrated its feasibility showing with meaningful contrast among different tissues. MREIT image reconstructions involve series data processing steps such as k-space handling, phase...
Automatic annotation for three-dimensional (3D) cephalometric analysis has been limited by computational complexity and computing performance. The purpose of this study was to evaluate the accuracy our newly-developed automatic 3D system using a deep learning algorithm. Our model mainly consisted convolutional neural network image data resampling. Discrepancies between referenced predicted coordinate values in three axes distance were calculated yield prediction errors 3.26, 3.18, 4.81 mm...
Magnetic resonance electrical impedance tomography (MREIT) attempts to provide conductivity images of an electrically conducting object with a high spatial resolution. When we inject current into the object, it produces internal distributions density <b xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">J</b> and magnetic flux xmlns:xlink="http://www.w3.org/1999/xlink">B</b> =( <i xmlns:xlink="http://www.w3.org/1999/xlink">Bx</i> ,...
In magnetic resonance electrical impedance tomography, among several conductivity image reconstruction algorithms, the harmonic <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</i> <sub xmlns:xlink="http://www.w3.org/1999/xlink">z</sub> algorithm has been successfully applied to data from phantoms and animals. The is, however, sensitive measurement noise in data. Especially, vivo animal human experiments where injection current amplitudes are...
The goal of magnetic resonance electrical impedance tomography (MREIT) is to produce a tomographic image conductivity distribution inside an electrically conducting object. Injecting current into the object, we measure z-component Bz induced flux density using MRI scanner. Based on relation between and measured data, may reconstruct cross-sectional images distribution. In two-dimensional imaging slice, can see that changes along equipotential lines are determined by data. Since themselves...
Our purpose in this study is to evaluate the clinical feasibility of deep-learning techniques for F-18 florbetaben (FBB) positron emission tomography (PET) image reconstruction using data acquired a short time. We reconstructed raw FBB PET 294 patients 20 and 2 min into standard-time scanning (PET20m) short-time (PET2m) images. generated PET-like (sPET20m) from PET2m network. did qualitative quantitative analyses assess whether sPET20m images were available applications. In our internal...
Objectives To evaluate standard dose-like computed tomography (CT) images generated by a deep learning method, trained using unpaired low-dose CT (LDCT) and standard-dose (SDCT) images. Materials methods LDCT (80 kVp, 100 mAs, n = 83) SDCT (120 200 42) were divided into training (42 42 SDCT) validation (41 LDCT) sets. A generative adversarial network framework was used to train datasets. The method virtual (VIs) from the original (OIs). test proposed 262 33) collected another scanner...
Conductivity imaging based on the current-injection MRI technique has been developed in magnetic resonance electrical impedance tomography. Current injected through a pair of surface electrodes induces flux density distribution inside an object, which results additional field inhomogeneity. We can extract phase changes related to current injection and obtain image induced density. Without rotating object bore, we measure only one component B(z) B = (B(x), B(y), B(z)). Based relation between...
Vortex flow imaging is a relatively new medical method for the dynamic visualization of intracardiac blood flow, potentially useful index cardiac dysfunction. A reconstruction proposed here to quantify distribution velocity fields inside left ventricle from color images compiled ultrasound measurements. In this paper, 2D incompressible Navier-Stokes equation with mass source term utilize measurable data in plane along moving boundary condition. The model reflects out-of-plane flows on...
Abstract Owing to recent advances in thoracic electrical impedance tomography (EIT), a patient’s hemodynamic function can be noninvasively and continuously estimated real-time by surveilling cardiac volume signal (CVS) associated with stroke output. In clinical applications, however, CVS is often of low quality, mainly because the deliberate movements or inevitable motions during interventions. This study aims develop quality indexing method that assesses influence motion artifacts on...
Magnetic resonance electrical impedance tomography (MREIT) is a new medical imaging modality visualizing static conductivity images of electrically conducting subjects. Recently, MREIT has rapidly progressed in its theory, algorithm, and experiment technique now reached to the stage vivo animal experiments. In this paper, we present software, named CoReHA 2.0 standing for second version reconstructor using harmonic algorithms, facilitate reconstruction image. This software offers various...