A5087799197- Medical Image Segmentation Techniques
- Nutrition and Health in Aging
- Body Composition Measurement Techniques
- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- Liver Disease Diagnosis and Treatment
- Anatomy and Medical Technology
- Coronary Interventions and Diagnostics
- Robotics and Sensor-Based Localization
- Hip and Femur Fractures
- Radiation Dose and Imaging
- Organ Transplantation Techniques and Outcomes
- Advanced MRI Techniques and Applications
- Advanced Neural Network Applications
- Effects of Radiation Exposure
- 3D Shape Modeling and Analysis
- Frailty in Older Adults
- Image and Object Detection Techniques
- Soft Robotics and Applications
- Liver Disease and Transplantation
Soongsil University
2019-2023
Abstract As sarcopenia research has been gaining emphasis, the need for quantification of abdominal muscle on computed tomography (CT) is increasing. Thus, a fully automated system to select L3 slice and segment in an end-to-end manner demanded. We aimed develop deep learning model (DLM) with consideration anatomic variations cross-sectional areas (CSAs) fat. Our DLM, named L3SEG-net, was composed YOLOv3-based algorithm selecting convolutional network (FCN)-based segmentation. The developed...
Muscle quality is associated with fatty degeneration or infiltration of the muscle, which may be decreased muscle function and increased disability.The aim this study to evaluate feasibility automated quantitative measurements skeletal on computed tomography (CT) images assess normal-attenuation myosteatosis.We developed a web-based toolkit generate map by categorizing components. First, automatic segmentation total abdominal area (TAMA), visceral fat area, subcutaneous was performed using...
X-ray angiography is commonly used in the diagnosis and treatment of coronary artery disease with advantage visualization inside blood vessels real-time. However, it has several disadvantages that occur acquisition process, which causes inconvenience difficulty. Here, we propose a novel segmentation nonrigid registration method to provide useful real-time assistive images information. A convolutional neural network for arteries 2D acquired from various angles To compensate errors during 3D...
Although contrast-enhanced computed tomography (CT) is currently the most widely-used imaging modality for preoperative evaluation of potential living liver donors, radiation exposure remains a major concern. The present study aimed to determine relationship body mass index (BMI) and abdominal fat with effective dose received during CT scans as part pre-donation work-up in donors.This retrospective cross-sectional included 695 donors (mean age, 30.5±9.7 years; 445 men 250 women) who had...
In this paper, we propose a rapid rigid registration method for the fusion visualization of intraoperative 2D X-ray angiogram (XA) and preoperative 3D computed tomography angiography (CTA) images. First, perform cardiac cycle alignment patient's XA CTA images obtained from different apparatus. Subsequently, initial through space optimal boundary box. Finally, two are registered where distance between vascular structures is minimized by using local map, selective measure, optimization...
Objectives: Intraoperative navigation reduces the risk of major complications and increases likelihood optimal surgical outcomes. This paper presents an augmented reality (AR)-based simulation technique for ventriculostomy that visualizes brain deformations caused by movements a instrument in three-dimensional model. is achieved utilizing position-based dynamics (PBD) physical deformation method on preoperative image.Methods: An infrared camera-based AR environment aligns real-world space...
To improve1 the survival rate of hepatocellular carcinoma (HCC), early diagnosis and treatment are essential. Early HCC often involves comparing analyzing hundreds computed tomography (CT) images, which is a kind subjective judgment also time-consuming process. In this paper, we propose liver rigid registration method using vessel surface mesh to enable fast objective HCC. The proposed segmenting regions from abdominal CT generating meshes, performing based on Iterative Closest Point (ICP)...
This study presents a method for diagnosing fatty liver disease by using time-difference computed tomography (CT) images of the same patient to perform segmentation and rigid registration on regions, excluding vascular regions. The proposed comprises three main steps. First, region is segmented in precontrast phase, vessel regions are portal phase. Second, performed between align positions affected
<sec> <title>BACKGROUND</title> Muscle quality is associated with fatty degeneration or infiltration of the muscle, which may be decreased muscle function and increased disability. </sec> <title>OBJECTIVE</title> The aim this study to evaluate feasibility automated quantitative measurements skeletal on computed tomography (CT) images assess normal-attenuation myosteatosis. <title>METHODS</title> We developed a web-based toolkit generate map by categorizing components. First, automatic...
Abstract Background and aims: As sarcopenia research has been gaining emphasis, the need for quantification of abdominal muscle on computed tomography (CT) is increasing. Thus, a fully automated system to select L3 slice segment in an end-to-end manner demanded. We aimed develop deep learning model (DLM) with consideration anatomic variations cross-sectional areas (CSAs) fat. Methods: Our DLM, named L3SEG-net, was composed YOLOv3-based algorithm selecting convolutional network (FCN)-based...
<sec> <title>BACKGROUND</title> As sarcopenia research has been gaining emphasis, the need for quantification of abdominal muscle on computed tomography (CT) is increasing. Thus, a fully automated system to select L3 slice and segment in an end-to-end manner demanding. </sec> <title>OBJECTIVE</title> We aimed develop deep learning model (DLM) with consideration anatomic variations cross-sectional areas (CSAs) fat. <title>METHODS</title> Our DLM, named L3SEG-net, was composed YOLOv3-based...