J. Kim

ORCID: 0000-0002-5440-4057
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced MRI Techniques and Applications
  • Osteoarthritis Treatment and Mechanisms
  • Lower Extremity Biomechanics and Pathologies
  • Total Knee Arthroplasty Outcomes
  • Knee injuries and reconstruction techniques
  • Cancer Diagnosis and Treatment
  • Chronic Obstructive Pulmonary Disease (COPD) Research
  • Radiomics and Machine Learning in Medical Imaging
  • Bone and Joint Diseases
  • Cancer Treatment and Pharmacology
  • Breast Cancer Treatment Studies
  • Photoacoustic and Ultrasonic Imaging
  • Orthopedic Infections and Treatments
  • Cardiovascular Function and Risk Factors
  • Advanced X-ray Imaging Techniques
  • Retinal Imaging and Analysis
  • Skin Protection and Aging
  • Sports injuries and prevention
  • Cancer Risks and Factors
  • Advanced Image Processing Techniques
  • Inhalation and Respiratory Drug Delivery
  • Analytical Chemistry and Sensors
  • melanin and skin pigmentation
  • Retinopathy of Prematurity Studies
  • MRI in cancer diagnosis

Cleveland Clinic
2004-2022

Cleveland Clinic Lerner College of Medicine
2020-2022

Chung Cheong University
2022

Arthritis Foundation
2021

Jeonbuk National University
2017

Inha University
2017

Chonbuk National University Hospital
2017

Jeonju University
2017

Here, we demonstrated the formation of active sites O<sub>2</sub><sup>−</sup> and O<sup>−</sup> on surface nanocube In<sub>2</sub>O<sub>3</sub>@RGO heterostructure, gas sensing mechanisms fluctuations in potential barrier height before after insertion acetone formaldehyde.

10.1039/c7ra05685k article EN cc-by-nc RSC Advances 2017-01-01

Purpose To develop an ultrafast and robust MR parameter mapping network using deep learning. Theory Methods We design a learning framework called SuperMAP that directly converts series of undersampled (both in k‐space parameter‐space) parameter‐weighted images into several quantitative maps, bypassing the conventional exponential fitting procedure. also present novel technique to simultaneously reconstruct T1rho T2 relaxation maps within single scan. Full data were acquired retrospectively...

10.1002/mrm.29411 article EN Magnetic Resonance in Medicine 2022-09-21

575 Background: Optimal choice of endocrine therapy for early-stage breast cancer differs with menopausal status. While amenorrhea is common during adjuvant chemotherapy, there currently no available test to establish when menopause permanent. The aim this study was determine the age cutoff after which resumption menses unlikely following chemotherapy and assess what additional risk factors may predict persistent at 5 years initiation chemotherapy. Methods: One hundred patients treated...

10.1200/jco.2009.27.15_suppl.575 article EN Journal of Clinical Oncology 2009-05-20

ACL injury is a major risk factor for post-traumatic osteoarthritis (PTOA), however mechanisms are not fully understood. In this work, we use radiomics from quantitative MRI imaging to associate subvisual changes in the infrapatellar fat pad (IPFP) both symptomatic and radiographic PTOA. was collected 113 patients at least 10 years post-ACLR. 1690 11 clinical features were extracted selected using gradient-boosted decision tree classifier model. A subset of texture-associated IPFP no...

10.58530/2023/4378 article EN Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition 2024-08-14

Deep learning methods have achieved superior reconstruction results in MRI reconstruction. Recently, denoising diffusion probabilistic models (DDPM) demonstrated great potential image-processing tasks. In this study, we combine and GRAPPA for highly accelerated 3D imaging. The method sequentially performs DDPM with specially designed sampling masks such that the benefits of model availability multi-channel data can be utilized jointly. Our demonstrate proposed achieve an acceleration factor...

10.58530/2023/4044 article EN Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition 2024-08-14

Motivation: Deep learning methods have achieved superior reconstruction in MR quantitative T1&amp;rho; imaging due to their ability learn the non-linearity relationship between undersampled k-space data and corresponding maps. Goal(s): In this study, we investigate use of DDPM for highly accelerated imaging. Approach: The learns image properties from fully acquired images during training without knowledge subsampling patterns used scans. This is advantageous most existing models that need be...

10.58530/2024/4555 article EN Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition 2024-11-26

The surface activated bonding (SAB) method generally has the advantage of high strength, low contact resistance, and microstructural stability at room temperature. In this study, Ti-Al laminates were produced by with aluminum titanium foils. Heat treatment was conducted temperature range from 200 to 550 °C in vacuum. strength measured a peel test, interfacial characteristics investigated observation. results showed that highest heat 400 °C, microstructure observation revealed laminate...

10.1166/jnn.2018.14992 article EN Journal of Nanoscience and Nanotechnology 2017-10-16

688 Background: The purpose of this study was to determine if pre-operative tumor characteristics can predict which patients are likely have residual infiltrating breast cancer (RIBC) after undergoing primary induction chemotherapy. Methods: Data were collected prospectively for 85 with locally advanced who underwent chemotherapy followed by surgery. Variables included age at diagnosis, hormone receptor status, taxane, and cTNM size, axillary node stage. Recursive partitioning analysis used...

10.1200/jco.2004.22.14_suppl.688 article EN Journal of Clinical Oncology 2004-07-15

Most parallel imaging methods require calibration data for reconstruction. Low-rank-based allow calibration-free reconstruction from randomly undersampled, multi-channel data. This abstract presents a novel method to combine multichannel blind deconvolution (MALBEC), method, and GRAPPA, calibration-based highly accelerated imaging. The sequentially performs MALBEC GRAPPA with specially designed sampling masks such that the benefits of low-rank structure availability can be utilized jointly....

10.58530/2022/3477 article EN Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition 2023-08-03

688 Background: The purpose of this study was to determine if pre-operative tumor characteristics can predict which patients are likely have residual infiltrating breast cancer (RIBC) after undergoing primary induction chemotherapy. Methods: Data were collected prospectively for 85 with locally advanced who underwent chemotherapy followed by surgery. Variables included age at diagnosis, hormone receptor status, taxane, and cTNM size, axillary node stage. Recursive partitioning analysis used...

10.1200/jco.2004.22.90140.688 article EN Journal of Clinical Oncology 2004-07-15
Coming Soon ...