Research Interests:
Understanding of standardized uptake value (SUV) of 2-deoxy-2-[18F]fluoro-d-glucose positron emission tomography (FDG-PET) depends on the background accumulations of glucose because the SUV often varies the status of patients. The purpose... more
Understanding of standardized uptake value (SUV) of 2-deoxy-2-[18F]fluoro-d-glucose positron emission tomography (FDG-PET) depends on the background accumulations of glucose because the SUV often varies the status of patients. The purpose of this study was to develop a new method for quantitative analysis of SUV of FDG-PET scan images. The method included an anatomical standardization and a statistical comparison with normal cases by using Z-score that are often used in SPM or 3D-SSP approach for brain function analysis. Our scheme consisted of two approaches, which included the construction of a normal model and the determination of the SUV scores as Z-score index for measuring the abnormality of an FDG-PET scan image. To construct the normal torso model, all of the normal images were registered into one shape, which indicated the normal range of SUV at all voxels. The image deformation process consisted of a whole body rigid registration of shoulder to bladder region and liver reg...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Engineering, Computer Science, Artificial Intelligence, Image Processing, Image segmentation, and 11 moreRegion growing, Medical Imaging and Image Processing, Human Body, Segmentation, Thresholding, High Resolution, Spatial resolution, Soft Tissue, Region Segmentation, Computer Aided Diagnosis, and Torso
Research Interests:
Research Interests:
Hepatic-vessel trees are the key structures in the liver. Knowledge of the hepatic-vessel tree is required because it provides information for liver lesion detection in the computer-aided diagnosis (CAD) system. However, hepatic vessels... more
Hepatic-vessel trees are the key structures in the liver. Knowledge of the hepatic-vessel tree is required because it provides information for liver lesion detection in the computer-aided diagnosis (CAD) system. However, hepatic vessels cannot easily be distinguished from other liver tissues in plain CT images. Automated segmentation of hepatic vessels in plain (non-contrast) CT images is a challenging issue. In this paper, an approach to automatic segmentation of hepatic vessels is proposed. The approach consists of two processing steps: enhancement of hepatic vessels and hepatic-vessel extractions. Enhancement of the vessels was performed with two techniques: (1) histogram transformation based on a Gaussian function; (2) multi-scale line filtering based on eigenvalues of a Hessian matrix. After the enhancement of the vessels, candidates of hepatic vessels were extracted by a thresholding method. Small connected regions in the final results were considered as false positives and we...
Research Interests: Computer Science, Algorithms, Medicine, Humans, Liver, and 15 moreSegmentation, Thresholding, Vessel Segmentation, Time Factors, Reproducibility of Results, Ground Truth, Sensitivity and Specificity, Normal Distribution, Computer Aided Diagnosis, Contrast Media, Radiological Physics and Technology, False Positive, Hepatic Veins, Hessian matrix, and Automatic segmentation
The detection of asymptomatic lacunar infarcts on magnetic resonance (MR) images are important tasks for radiologists to ensure the prevention of sever cerebral infarction. However, their accurate identification is often difficult task.... more
The detection of asymptomatic lacunar infarcts on magnetic resonance (MR) images are important tasks for radiologists to ensure the prevention of sever cerebral infarction. However, their accurate identification is often difficult task. Therefore, the purpose of this study is to develop a computer-aided diagnosis scheme for the detection of lacunar infarcts. Our database consisted of 1,143 T1- and 1,143 T2-weighted images obtained from 132 patients. We first segmented the cerebral region in the T1- weighted image by using a region growing technique. For identifying the initial lacunar infarcts candidates, white top-hat transform and multiple-phase binarization were then applied to the T2- weighted image. For eliminating false positives (FPs), we determined 12 features, i.e., the locations x and y, density differences in the T1- and T2- weighted images, nodular components (NC), and nodular & linear components (NLC) from a scale 1 to 4. The NCs and NLCs were obtained using filter bank...
Research Interests: Computer Science, Algorithms, Artificial Intelligence, Magnetic Resonance Imaging, Medicine, and 15 moreBrain, Humans, Female, Male, Magnetic Resonance, Conference Proceedings, Aged, Middle Aged, Image Enhancement, Adult, Filter Bank, Computer Aided Diagnosis, Cerebral Infarction, Magnetic resonance image, and False Positive
Research Interests:
Research Interests:
The shapes of the inner organs are important information for medical image analysis. Statistical shape modeling provides a way of quantifying and measuring shape variations of the inner organs in different patients. In this study, we... more
The shapes of the inner organs are important information for medical image analysis. Statistical shape modeling provides a way of quantifying and measuring shape variations of the inner organs in different patients. In this study, we developed a universal scheme that can be used for building the statistical shape models for different inner organs efficiently. This scheme combines the traditional point distribution modeling with a group-wise optimization method based on a measure called minimum description length to provide a practical means for 3D organ shape modeling. In experiments, the proposed scheme was applied to the building of five statistical shape models for hearts, livers, spleens, and right and left kidneys by use of 50 cases of 3D torso CT images. The performance of these models was evaluated by three measures: model compactness, model generalization, and model specificity. The experimental results showed that the constructed shape models have good "compactness&quo...
Research Interests:
Research Interests:
Research Interests: Design, Computer Aided Design, Body, Tomography, Automation, and 3 moreVolume, Accuracy, and Digestive System
Research Interests:
Research Interests: Cardiology, Ultrasound, Medicine, Humans, Internal Medicine, and 12 moreFemale, Male, Aged, Acute Coronary Syndrome, Myocardial Infarction, Public health systems and services research, Angina pectoris, Coronary Artery Disease, Vulnerable Plaque', cross sectional area, Cardiovascular medicine and haematology, and Coronary Vessels
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Magnetic Resonance Imaging, Nuclear medicine, Medicine, Humans, Liver Cirrhosis, and 15 moreLiver, Neuroradiology, Male, Liver Fibrosis, Fibrosis, Energy Analysis, Clinical Sciences, Aged, Middle Aged, Adult, Hepatic Fibrosis, chronic hepatitis C, Area Under Curve, Elastography, and Elasticity Imaging Techniques
Research Interests:
Research Interests:
BACKGROUND We introduce an ensemble learning approach that can be used to solve organ localization problems. Location of an inner organ in a CT image is the basic information that is required for medical image analysis such as image... more
BACKGROUND We introduce an ensemble learning approach that can be used to solve organ localization problems. Location of an inner organ in a CT image is the basic information that is required for medical image analysis such as image segmentation, lesion detection, content-based image retrieval, and anatomical annotation. The proposed approach can be used to generate a fast and practical organ-localization scheme automatically from a small number of training samples that include both original images and target locations. EVALUATION A database containing 660 patient cases (male, 344; female, 316; age range, 29–92 years) of 3D volumetric CT scans were used in the experiment. These 3D CT scans were generated by LightSpeed Ultra16, GE Healthcare; and Brilliance 64, Philips Medical Systems. All CT scans were obtained using a common protocol (120 kV/Auto mA) and covered the entire human torso region. Each 3D CT scan had approximately 800–1200 axial CT slices with an isotropic spatial resol...