• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2E
• /
• pp.72-78
• /
• 2009

Heart sound segmentation into its components, S1, systole, S2 and diastole is the first step of analysis and the most important part in the automatic diagnosis of heart sounds. Conventionally, the Shannon energy envelope peak detection method has been popularly used due to its superior performance in locating S1 and S2. Recently, the HMM has been shown to be quite suitable in modeling the heart sound signal and its use in segmenting the heart sound signal has been suggested with some success. In this paper, we compared the two methods for heart sound segmentation using a common database. Experimental tests carried out on the 4 different types of heart sound signals showed that the segmentation accuracy relative to the manual segmentation was 97.4% in the HMM based method which was larger than 91.5% in the peak detection method.

• International journal of advanced smart convergence
• /
• v.7 no.2
• /
• pp.1-6
• /
• 2018

In this paper, we propose an automatic left ventricle segmentation method in computed tomography angiography (CTA) using separating energy function. First, we smooth the images by applying anisotropic diffusion filter to remove noise. Secondly, the volume of interest (VOI) is detected by using k-means clustering. Thirdly, we divide the left and right heart with split energy function. Finally, we extract only left ventricle from left and right heart with optimizing cost function including orientation term.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.1
• /
• pp.32-43
• /
• 2009

In this paper, we improve the performance of cardiac disorder classification by continuous heart sound signals using automatic segmentation and extreme learning machine (ELM). The accuracy of the conventional cardiac disorder classification systems degrades because murmurs and click sounds contained in the abnormal heart sound signals cause incorrect or missing starting points of the first (S1) and the second heart pulses (S2) in the automatic segmentation stage, In order to reduce the performance degradation due to segmentation errors, we find the positions of the S1 and S2 pulses, modify them using the time difference of S1 or S2, and extract a single period of heart sound signals. We then obtain a feature vector consisting of the mel-scaled filter bank energy coefficients and the envelope of uniform-sized sub-segments from the single-period heart sound signals. To classify the heart disorders, we use ELM with a single hidden layer. In cardiac disorder classification experiments with 9 cardiac disorder categories, the proposed method shows the classification accuracy of 81.6% and achieves the highest classification accuracy among ELM, multi-layer perceptron (MLP), support vector machine (SVM), and hidden Markov model (HMM).

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.4
• /
• pp.144-152
• /
• 2007

Conventional research works on the classification of the heart sound signal have been done mainly with the artificial neural networks. But the analysis results on the statistical characteristic of the heart sound signal have shown that the HMM is suitable for modeling the heart sound signal. In this paper, we model the various heart sound signals representing different heart diseases with the HMM and find that the classification rate is much affected by the clustering of the heart sound signal. Also, the heart sound signal acquired in real environments is a continuous signal without any specified starting and ending points of time. Hence, for the classification based on the HMM, the continuous cyclic heart sound signal needs to be manually segmented to obtain isolated cycles of the signal. As the manual segmentation will incur the errors in the segmentation and will not be adequate for real time processing, we propose a variant of the ergodic HMM which does not need segmentation procedures. Simulation results show that the proposed method successfully classifies continuous heart sounds with high accuracy.

• International Journal of Internet, Broadcasting and Communication
• /
• v.9 no.4
• /
• pp.19-24
• /
• 2017

In this paper, we propose an automatic segmentation method of left and right heart in computed tomography angiography (CTA) using separating energy function. First, we smooth the images by applying anisotropic diffusion filter to remove noise. Then, the volume of interest (VOI) is detected by using k-means clustering. Finally, we extract the left and right heart with separating energy function which we proposed to split the heart. We tested our method in ten CT images and they were obtained from a different patient. For the evaluation of the computational performance of the proposed method, we measured the total processing time. The average of total processing time, from first step to third step, was $14.39{\pm}1.17s$. We expect for our method to be used in cardiac diagnosis for cardiologist.

• Journal of International Society for Simulation Surgery
• /
• v.1 no.1
• /
• pp.37-40
• /
• 2014

Purpose For living donor liver transplantation, liver segmentation is difficult due to the variability of its shape across patients and similarity of the density of neighbor organs such as heart, stomach, kidney, and spleen. In this paper, we propose an automatic segmentation of the liver using multi-planar anatomy and deformable surface model in portal phase of abdominal contrast-enhanced CT images. Method Our method is composed of four main steps. First, the optimal liver volume is extracted by positional information of pelvis and rib and by separating lungs and heart from CT images. Second, anisotropic diffusing filtering and adaptive thresholding are used to segment the initial liver volume. Third, morphological opening and connected component labeling are applied to multiple planes for removing neighbor organs. Finally, deformable surface model and probability summation map are performed to refine a posterior liver surface and missing left robe in previous step. Results All experimental datasets were acquired on ten living donors using a SIEMENS CT system. Each image had a matrix size of $512{\times}512$ pixels with in-plane resolutions ranging from 0.54 to 0.70 mm. The slice spacing was 2.0 mm and the number of images per scan ranged from 136 to 229. For accuracy evaluation, the average symmetric surface distance (ASD) and the volume overlap error (VE) between automatic segmentation and manual segmentation by two radiologists are calculated. The ASD was $0.26{\pm}0.12mm$ for manual1 versus automatic and $0.24{\pm}0.09mm$ for manual2 versus automatic while that of inter-radiologists was $0.23{\pm}0.05mm$. The VE was $0.86{\pm}0.45%$ for manual1 versus automatic and $0.73{\pm}0.33%$ for manaual2 versus automatic while that of inter-radiologist was $0.76{\pm}0.21%$. Conclusion Our method can be used for the liver volumetry for the pre-surgery planning of living donor liver transplantation.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.2
• /
• pp.37-44
• /
• 2020

In this paper, we proposed that a fully automatic multi-class whole heart segmentation algorithm using deep learning. The proposed method is based on U-Net architecture which consist of recurrent convolutional block, residual multi-dilated convolutional block. The evaluation was accomplished by comparing automated analysis results of the test dataset to the manual assessment. We obtained the average DSC of 96.88%, precision of 95.60%, and recall of 97.00% with CT images. We were able to observe and analyze after visualizing segmented images using three-dimensional volume rendering method. Our experiment results show that proposed method effectively performed to segment in various heart structures. We expected that our method can help doctors and radiologist to make image reading and clinical decision.

• Korean Journal of Radiology
• /
• v.22 no.10
• /
• pp.1597-1608
• /
• 2021

Cardiovascular computed tomography (CT) is among the most active fields with ongoing technical innovation related to image acquisition and analysis. Artificial intelligence can be incorporated into various clinical applications of cardiovascular CT, including imaging of the heart valves and coronary arteries, as well as imaging to evaluate myocardial function and congenital heart disease. This review summarizes the latest research on the application of deep learning to cardiovascular CT. The areas covered range from image quality improvement to automatic analysis of CT images, including methods such as calcium scoring, image segmentation, and coronary artery evaluation.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.2
• /
• pp.196-204
• /
• 2016

World Health Organization reported that heart-related diseases such as coronary artery stenoses show the highest occurrence rate which may cause heart attack. Using Computed Tomography angiography images will allow radiologists to detect and have intervention by creating 3D roadmapping of the vessels. However, it is often complex and difficult do reconstruct 3D vessel which causes very large amount of time and previous researches were studied to segment vessels more accurate automatically. Therefore, in this paper, Region Competition, Geodesic Active Contour (GAC), Multi-atlas based segmentation and Active Shape Model algorithms were applied to segment aortic root from CTA images and the results were analyzed by using mean Hausdorff distance, volume to volume measure, computational time, user-interaction and coronary ostium detection rate. As a result, Extracted 3D aortic model using GAC showed the highest accuracy but also showed highest user-interaction results. Therefore, it is important to improve automatic segmentation algorithm in future

• Journal of KIISE:Software and Applications
• /
• v.33 no.4
• /
• pp.418-426
• /
• 2006

This paper proposes a robust and efficient segmentation method for a cardiac ultrasound image taken from a probe inserted into the heart in surgery. The method consists of three steps: initial boundary extraction, whole boundary modification using confidence competition, and local boundary modification using the rolling spoke method. Firstly, the initial boundary is extracted with threshold regions along the global spokes emitted from the center of an ultrasound probe. Secondly, high confidence boundary edges are detected along the global spokes by competing among initial boundary candidate and new candidates achieved by edge and appearance information. finally, the boundary is modified by rolling local spokes along concave regions that are difficult to extract using the global spokes. The proposed method produces promising segmentation results for the ultrasound cardiac images acquired during surgery.