A5077441011- Radiomics and Machine Learning in Medical Imaging
- Hepatocellular Carcinoma Treatment and Prognosis
- Liver Disease Diagnosis and Treatment
- Radiation Dose and Imaging
- Pancreatic and Hepatic Oncology Research
- MRI in cancer diagnosis
- Advanced Radiotherapy Techniques
- Renal cell carcinoma treatment
- Bladder and Urothelial Cancer Treatments
- Gallbladder and Bile Duct Disorders
- Sarcoma Diagnosis and Treatment
- Urinary and Genital Oncology Studies
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Colorectal Cancer Surgical Treatments
- Advanced X-ray and CT Imaging
- Advanced MRI Techniques and Applications
- Pancreatitis Pathology and Treatment
- Photoacoustic and Ultrasonic Imaging
- Metastasis and carcinoma case studies
- Topic Modeling
- Hepatitis B Virus Studies
- Neuroendocrine Tumor Research Advances
- Medical Imaging Techniques and Applications
- Liver Diseases and Immunity
- Ultrasound in Clinical Applications
Korea University
2018-2025
ORCID
2023
Korea University Medical Center
2022
Background/Objectives: This study compared the image quality of conventional multiplexed sensitivity-encoding diffusion-weighted imaging (MUSE-DWI) and deep learning MUSE-DWI with that vendor-specific (DL) reconstruction applied to bladder MRI. Methods: retrospective included 57 patients a visible mass. DWI images were reconstructed using vendor-provided DL algorithm (AIRTM Recon DL; GE Healthcare)—a CNN-based reduces noise enhances quality—applied here as prototype for MUSE-DWI. Two...
Background/Objectives: The accurate preoperative prediction of lymph node (LN) metastasis is essential to optimizing surgical management in renal pelvis urothelial carcinoma (RPUC) and ureteral (UUC). This study evaluates the predictive value computed tomography (CT) findings detecting LN determining primary metastatic location based on tumor site. Methods: retrospective included 48 RPUC 97 UUC patients who underwent surgery with dissection (LND) between 2005 2023. Preoperative CT images...
Background The 2017 international consensus guidelines for intraductal papillary mucinous neoplasm (IPMN) of the pancreas are widely used. Purpose To evaluate interobserver agreement and diagnostic performance MRI assessment in predicting malignant potential IPMN according to radiologists' experience. Materials Methods This multicenter retrospective study included 100 patients with pathologically proven pancreatic (77 surgery, 23 biopsy) who underwent contrast-enhanced between 2016 2021....
We aimed to compare the capabilities of two leading large language models (LLMs), GPT-4 and Gemini, in analyzing serial radiology reports, highlight oncological issues that require further clinical attention.
This study aimed to assess the diagnostic feasibility of radiomics analysis based on magnetic resonance (MR)-proton density fat fraction (PDFF) for grading hepatic steatosis in patients with suspected non-alcoholic fatty liver disease (NAFLD).This retrospective included 106 NAFLD who underwent a parenchymal biopsy. MR-PDFF and MR spectroscopy were performed all using 3.0-T scanner. Following whole-volume segmentation images, 833 radiomic features analyzed commercial program. Radiologic...
<strong>Objectives:</strong> To determine the performance of virtual monoenergetic images (VMIs) portal venous phase (PVP) compared with pancreatic-phase image for pancreatic ductal adenocarcinoma (PDAC) evaluation. <strong>Materials and methods:</strong> This retrospective study enrolled 64 patients PDAC who underwent CT dual-layer spectral between February 2018 January 2020. A polychromatic VMIs at 40 (VMI<sub>40</sub>), 55 (VMI<sub>55</sub>), 70 keV (VMI<sub>70</sub>) PVP were generated....
The aim of the study was to investigate diagnostic feasibility radiomics analysis using magnetic resonance elastography (MRE) assess hepatic fibrosis in patients with nonalcoholic fatty liver disease (NAFLD).One hundred suspected NAFLD were retrospectively enrolled. All underwent a parenchymal biopsy. Magnetic performed 3.0-T scanner. After multislice segmentation MRE images, 834 radiomic features analyzed commercial program. Radiologic features, such as median and mean values regions...
To explore whether high- and low-grade clear cell renal carcinomas (ccRCC) can be distinguished using radiomics features extracted from magnetic resonance imaging.In this retrospective study, 154 patients with pathologically proven ccRCC underwent contrast-enhanced 3 T imaging were assigned to the development (n = 122) test 32) cohorts in a temporal-split setup. A total of 834 whole-tumor volumes sequences: T2-weighted (T2WI), diffusion-weighted imaging, T1-weighted imaging. random forest...
Gastrointestinal tract involvement in undifferentiated pleomorphic sarcoma (UPS) is extremely rare.To the authors' knowledge, only 21 cases of primary small bowel UPS have been reported literature available English.Reported CT findings nonspecific, and MRI one case.The present article describes a case involving 72-year-old male with histologically confirmed arising from ileum, focusing on both magnetic resonance enterography findings.On CT, was noted as heterogeneously enhanced mass without...
Background: In conventional ultrasonography, the ultrasound image is not labeled with information on location or orientation of transducer. There also no parts body under examination. Objectives: This study aimed to investigate efficacy navigation-loaded including real-time transducer and inspection site, compared ultrasound. Patients Methods: After obtaining approval from institutional review board, 29 healthy adult volunteers were prospectively enrolled in this study. One gastrointestinal...
Abstract Background: To investigate the usefulness of body navigation-loaded ultrasound including a real time transducer location and inspection site compared with conventional images. Methods: Under approval institutional review board, we prospectively enrolled total 29 healthy adult volunteers. One gastrointestinal radiologist performed abdominal simultaneously using Ultrasound Navigation Image Convergence System developed by researchers. Subsequently, an equivalent image set was prepared....
Abstract Background: To investigate the diagnostic performance of radiomics analysis using magnetic resonance elastography (MRE) toward assessing hepatic fibrosis in patients with nonalcoholic fatty liver disease (NAFLD). Methods: A total 100 suspected NAFLD were retrospectively enrolled. All underwent a parenchymal biopsy. MRE was performed 3.0-T scanner. Following three-dimensional (3D) segmentation images, 834 radiomic features analyzed commercial program. Radiologic features, such as...