• Journal of radiological science and technology
• /
• v.45 no.2
• /
• pp.151-158
• /
• 2022

The Cardiac Gated Blood Pool (GBP) scintigram, a nuclear medicine imaging, calculates the left ventricular Ejection Fraction (EF) by segmenting the left ventricle from the heart. However, in order to accurately segment the substructure of the heart, specialized knowledge of cardiac anatomy is required, and depending on the expert's processing, there may be a problem in which the left ventricular EF is calculated differently. In this study, using the DeepLabV3 architecture, GBP images were trained on 93 training data with a ResNet-50 backbone. Afterwards, the trained model was applied to 23 separate test sets of GBP to evaluate the reproducibility of the region of interest and left ventricular EF. Pixel accuracy, dice coefficient, and IoU for the region of interest were 99.32±0.20, 94.65±1.45, 89.89±2.62(%) at the diastolic phase, and 99.26±0.34, 90.16±4.19, and 82.33±6.69(%) at the systolic phase, respectively. Left ventricular EF was calculated to be an average of 60.37±7.32% in the ROI set by humans and 58.68±7.22% in the ROI set by the deep learning segmentation model. (p<0.05) The automated segmentation method using deep learning presented in this study similarly predicts the average human-set ROI and left ventricular EF when a random GBP image is an input. If the automatic segmentation method is developed and applied to the functional examination method that needs to set ROI in the field of cardiac scintigram in nuclear medicine in the future, it is expected to greatly contribute to improving the efficiency and accuracy of processing and analysis by nuclear medicine specialists.

• Journal of Korean Foot and Ankle Society
• /
• v.7 no.2
• /
• pp.263-268
• /
• 2003

Tarsal coalition is a congenital failure of segmentation resulting in fibrous, cartilaginous, or bony union between tarsal bones. Although single tarsal coalitions are common, dual tarsal coalitions are a rare occurrence. We repport of unilateral and bilateral dual calcaneonavicular and talocalcaneal coalitions.

• Journal of the Korea Convergence Society
• /
• v.3 no.4
• /
• pp.15-21
• /
• 2012

Image segmentation for object to extract data from ultrasound acquired is an essential preprocessing step for the effective diagnosis. Various image segmentation methods have been studied. In this study, interactive image segmentation method by graph cut algorithm is proposed to develop a variety of applications of vascular ultrasound imaging and diagnostics. General imaging and vascular ultrasound imaging segmentation by entering constrain condition such as foreground and background. In the future it will be able to develop new ultrasound diagnostics.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.12
• /
• pp.3001-3008
• /
• 2013

To diagnose the cardiac valve abnormalities using analysis of phonocardiogram, first of all, accurate detection of S1, S2 components is needed for heart sound segmentation. In this paper, a new method that uses the third moment characteristics of an envelope of the PCG is proposed for accurate detection of S1 and S2 components of the heart sound with cardiac murmurs. The envelope of the PCG is obtained from the short-time energy profile, and its third moment profile with slope information is used for accurate time gating of the S1, S2 components. Experimental results have shown that the proposed method is superior to the conventional second moment method for detection of S1 and S2 regions from the heart sound signals with cardiac murmurs.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.51-58
• /
• 2023

In this paper, we propose an organ segmentation technique for the automatic extraction of medical diagnostic indicators from X-ray images. In order to calculate diagnostic indicators of heart disease and spinal disease such as VHS(vertebral heart scale) and Cobb angle, it is necessary to accurately segment the thoracic spine, carina, and heart in a chest X-ray image. A deep neural network model in which the high-resolution representation of the image for each layer and the structure converted into a low-resolution feature map are connected in parallel was adopted. This structure enables the relative position information in the image to be effectively reflected in the segmentation process. It is shown that learning performance can be improved by combining the OCR module, in which pixel information and object information are mutually interacted in a multi-step process, and the channel attention module, which allows each channel of the network to be reflected as different weight values. In addition, a method of augmenting learning data is presented in order to provide robust performance against changes in the position, shape, and size of the subject in the X-ray image. The effectiveness of the proposed theory was evaluated through an experiment using 145 human chest X-ray images and 118 animal X-ray images.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.119-122
• /
• 1997

In this paper, we represented the variation of heart cavity area in the space domain by 3-d rendering. We arranged the 2-d sequence of ultrasonic image acquired in the time domain as volumetric data, and extracted heart cavity region from 3-d data. For the segmentation of 3-d volume data, we extracted the cavity region using the method of expanding the cavity region that is same statistical property. By shading which is using light and object normal vector, we visualized the volume data on image plane.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.517-520
• /
• 1999

In this paper, we propose a non-invasive method to estimate blood velocity from the real medical images. To measure the magnitude and direction components associated with the blood velocity, we apply the optical flow analysis algorithm. It is demonstrated that the accuracy of the blood velocity estimate could possibly be increased by segmenting the optical flow region. We call this the Region Optical Flow(ROF) algorithm. We carried out some preliminary experiments using the aorta medical images, and corresponding regional optical flow diagrams are provided.

• Korean Journal of Radiology
• /
• v.20 no.1
• /
• pp.102-113
• /
• 2019

Objective: To assess the accuracy and potential bias of computed tomography (CT) ventricular volumetry using semiautomatic three-dimensional (3D) threshold-based segmentation in repaired tetralogy of Fallot, and to compare them to those of two-dimensional (2D) magnetic resonance imaging (MRI). Materials and Methods: This retrospective study evaluated 32 patients with repaired tetralogy of Fallot who had undergone both cardiac CT and MRI within 3 years. For ventricular volumetry, semiautomatic 3D threshold-based segmentation was used in CT, while a manual simplified contouring 2D method was used in MRI. The indexed ventricular volumes were compared between CT and MRI. The indexed ventricular stroke volumes were compared with the indexed arterial stroke volumes measured using phase-contrast MRI. The mean differences and degrees of agreement in the indexed ventricular and stroke volumes were evaluated using Bland-Altman analysis. Results: The indexed end-systolic (ES) volumes showed no significant difference between CT and MRI (p > 0.05), while the indexed end-diastolic (ED) volumes were significantly larger on CT than on MRI (93.6 ± 17.5 mL/m² vs. 87.3 ± 15.5 mL/m² for the left ventricle [p < 0.001] and 177.2 ± 39.5 mL/m² vs. 161.7 ± 33.1 mL/m² for the right ventricle [p < 0.001], respectively). The mean differences between CT and MRI were smaller for the indexed ES volumes (2.0-2.5 mL/m²) than for the indexed ED volumes (6.3-15.5 mL/m²). CT overestimated the stroke volumes by 14-16%. With phase-contrast MRI as a reference, CT (7.2-14.3 mL/m²) showed greater mean differences in the indexed stroke volumes than did MRI (0.8-3.3 mL/m²; p < 0.005). Conclusion: Compared to 2D MRI, CT ventricular volumetry using semiautomatic 3D threshold-based segmentation provides comparable ES volumes, but overestimates the ED and stroke volumes in patients with repaired tetralogy of Fallot.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.215-222
• /
• 2006

People health improvement is becoming new subject through the combining with the oriental medicine diagnosis theory and IT technology. To do this, firstly, it needs sicked data that supply the visualization, objectification and quantification method. Especially, if an ocular inspection can be more objective and visual expression in oriental medicine, it seems to offer the biggest opportunity in diagnosis field. In this study, I propose a diagnosis to check the symptoms of heart diagnosis. Our research aim is on the visualization of diagnosis using image processing system which it can be actual analysis about the symptom of heart. To catch up this study, through the color support assistance by face image processing, I devide the face area and analyze the face form and also extract face characteristic point in heart disease diagnosis using oriental medicine based on an ocular inspection method. I would like to prove the usefulness of the method that proposed by an experiment.

• Korean Journal of Radiology
• /
• v.21 no.6
• /
• pp.717-725
• /
• 2020

Objective: To assess left ventricular remodeling patterns using cardiac computed tomography (CT) in children with congenital heart disease and correlate these patterns with their clinical course. Materials and Methods: Left ventricular volume and myocardial mass were quantified in 17 children with congenital heart disease who underwent initial and follow-up end-systolic cardiac CT studies with a mean follow-up duration of 8.4 ± 9.7 months. Based on changes in the indexed left ventricular myocardial mass (LVMi) and left ventricular mass-volume ratio (LVMVR), left ventricular remodeling between the two serial cardiac CT examinations was categorized into one of four patterns: pattern 1, increased LVMi and increased LVMVR; pattern 2, decreased LVMi and decreased LVMVR; pattern 3, increased LVMi and decreased LVMVR; and pattern 4, decreased LVMi and increased LVMVR. Left ventricular remodeling patterns were correlated with unfavorable clinical courses. Results: Baseline LVMi and LVMVR were 65.1 ± 37.9 g/m² and 4.0 ± 3.2 g/mL, respectively. LVMi increased in 10 patients and decreased in seven patients. LVMVR increased in seven patients and decreased in 10 patients. Pattern 1 was observed in seven patients, pattern 2 in seven, and pattern 3 in three patients. Unfavorable events were observed in 29% (2/7) of patients with pattern 1 and 67% (2/3) of patients with pattern 3, but no such events occurred in pattern 2 during the follow-up period (4.4 ± 2.7 years). Conclusion: Left ventricular remodeling patterns can be characterized using cardiac CT in children with congenital heart disease and may be used to predict their clinical course.