• 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 Korean Society for Industrial and Applied Mathematics
• /
• v.20 no.3
• /
• pp.175-202
• /
• 2016

Ultrasound imaging is a widely used tool for visualizing human body's internal organs and quantifying clinical parameters. Due to its advantages such as safety, non-invasiveness, portability, low cost and real-time 2D/3D imaging, diagnostic ultrasound industry has steadily grown. Since the technology advancements such as digital beam-forming, Doppler ultrasound, real-time 3D imaging and automated diagnosis techniques, there are still a lot of demands for image quality improvement, faster and accurate imaging, 3D color Doppler imaging and advanced functional imaging modes. In order to satisfy those demands, mathematics should be used properly and effectively in ultrasound imaging. Mathematics has been used commonly as mathematical modelling, numerical solutions and visualization, combined with science and engineering. In this article, we describe a brief history of ultrasound imaging, its basic principle, its applications in obstetrics/gynecology, cardiology and radiology, domestic-industrial products, contributions of mathematics and challenging issues in ultrasound imaging.

• Korean Journal of Radiology
• /
• v.23 no.3
• /
• pp.308-321
• /
• 2022

Transabdominal ultrasound (TAUS) is useful in all aspects of lesion screening, monitoring activity, or treating/diagnosing any related complications of inflammatory bowel disease. Its ability to screen or diagnose complications is almost the same as that of other methods, such as CT or MRI. Moreover, its noninvasiveness makes it a first-line examination method. A TAUS image depicting ulcerative colitis will show large intestinal wall thickening that is continuous from the rectum, which is mainly due to mucosal layer thickening, while for Crohn's disease, a TAUS image is characterized by a diversity in the areas affected, distribution, and layer structure. Indicators of activity monitoring include wall thickness, wall structure, and vascular tests that use Doppler ultrasound or contrast agents. While all of these have been reported to be useful, at this time, no single parameter has been established as superior to others; therefore, a comprehensive evaluation of these parameters is justified. In addition, evaluating the elasticity of lesions using elastography is particularly useful for distinguishing between fibrous and inflammatory stenoses. However, the lack of objectivity is the biggest drawback of using ultrasound. Standardizing and popularizing the ultrasound process will be necessary, including scanning methods, equipment settings, and image analysis.

• Physical Therapy Rehabilitation Science
• /
• v.10 no.1
• /
• pp.82-89
• /
• 2021

Purpose: This study is to investigate the muscle activity based on real-time visual feedback training methods by rehabilitative ultrasound image in elderly and correlation between Heckmatt scale grade, muscle tone and thickness. Design: Cross-sectional study: Pilot study Methods: 6 elderly participated in the study with 2 conditions. Under the condition of rehabilitation ultrasound imaging equipment, all subjects performed voluntary maximal muscle contraction of the quadriceps 3 times using visual feedback based on Rehabilitative Ultrasound Imaging 1.0 (RUSI 1.0). Under the condition of only ultrasound images, all subjects performed voluntary maximal muscle contraction of the quadriceps 3 times using ultrasound image-based visual feedback. The muscle thickness and tone of the quadriceps were measured and the grades were classified by Heckmatt scale and all variables were comparative analyzed. Results: Heckmatt scale grade showed a negative correlation with muscle thickness at relaxation (p<0.05), and a negative correlation with the difference value obtained by subtracting muscle thickness at relaxation from muscle thickness at contraction in ultrasound image condition (p<0.05). The muscle tone during relaxation showed a negative correlation with the muscle thickness during relaxation (p<0.05). Conclusion: In the case of voluntary maximum muscle contraction of the quadriceps muscle in the elderly, it can be seen that the muscle thickness is getting larger when the RUSI 1.0-based visual feedback is provided than with only ultrasound image provided. And the lower Heckmatt scale grade is, the thicker the muscle is, and the lower the muscle tone is.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.655-657
• /
• 2021

It is challenging to find breast ultrasound image training dataset to develop an accurate machine learning model due to various regulations, personal information issues, and expensiveness of acquiring the images. However, studies targeting transfer learning for ultrasound breast cancer images classification have not been able to achieve high performance compared to radiologists. Here, we propose an improved transfer learning model for ultrasound breast cancer classification using publicly available dataset. We argue that with a proper combination of ImageNet pre-trained model and optimizer, a better performing model for ultrasound breast cancer image classification can be achieved. The proposed model provided a preliminary test accuracy of 99.5%. With more experiments involving various hyperparameters, the model is expected to achieve higher performance when subjected to new instances.

• Journal of the Korean Society of Radiology
• /
• v.15 no.5
• /
• pp.621-628
• /
• 2021

Prior studies on frequency-related image quality analysis of intravascular ultrasound catheters are lacking both in Korea and abroad. Therefore, this study was conducted to prepare a standard for measuring the image quality using the program and to suggest a measuring method to researchers related to the quality analysis of intravascular ultrasound images. For the target, the vessel lumen size is 3.0 - 4.0 mm. Before using intravascular ultrasound, thoroughly clean the ultrasound catheter so that no air or foreign substances enter it. Normal vascular images and lesion vascular images of sufficiently dilated images were used. As a standard image acquisition method, the image of the end-systolic section, which has the best evaluation of vascular lesions when using intravascular ultrasound, was acquired retrospectively through the DCAS PACS program to set the standard. When setting the measurement method criteria, we proposed a standard setting method that corresponds to the concentric and eccentric circles of normal and lesion vessels. By applying this criterion, we proposed a method for measuring the lumen and lateral cavities of normal and lesion vessels of interest and background area. In conclusion, if the image quality of intravascular ultrasonography is measured through the method devised by these researchers, consistent quality measurement is possible regardless of the type of intravascular ultrasound catheter. Therefore, it is thought that it can be applied as a guideline for the actual image quality measurement method in the study related to intravascular ultrasound image quality.

• Proceedings of the KOSOMBE Conference
• /
• v.1998 no.11
• /
• pp.70-71
• /
• 1998

In this paper, We proposed fast ultrasound image compression based on characteristics of ultrasound images. In the proposed method, wavelet transform is performed for non-zero coefficients selectively. It codes zero-tree symbols using conditional pdf (probability density function) as orientation of bands. It normalizes wavelet coefficients with threshold of each wavelet band and encodes those using a uniform quantizer. Experimental results show that the proposed method is the proposed method is superior in PSNR to LuraTech's method by about 1.0 dB, to JPEG by about 5.0 dB for $640\times480$ 24bits color ultrasound image.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.89-90
• /
• 2019

본 논문에서는 ultrasound image Right Parasagittal Liver에 edge detection을 적용한 후, 특징점 검출 알고리즘인 Scale Invarient Feature Transfom(SIFT)를 이용하여 특징점의 위치를 살펴보도록 한다. edge detection 알고리즘으로는 Canny edge detection과 Prewitt edge detection을 적용하기로 한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.313-314
• /
• 2019

본 논문에서는 특징점 검출 알고리즘을 적용하여 ultrasound image에서 특징점을 검출하는 것과 object dectection을 위한 keypoints가 object에 올바르게 위치하는지를 검증하는 실험을 진행한다. 특징점 검출을 위한 알고리즘으로는 Scale Invariant Feature Transform(SIFT)과 Harris corner detection 을 적용하여 검증한다.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.8 s.173
• /
• pp.182-191
• /
• 2005

It is very important to obtain a high quality of bone image for an accurate ultrasonic measurement of bone mineral density. In this study, we suggested a technique to acquire an optimal image by adapting an acoustic lens and a properly selected ultrasonic probe. Also, we have applied an image processing algorithm with which automatically makes a decision of brightness and contrast of image by generating threshold level, a composition of ultrasonic data, an elimination of noise using modified median filter, and a real time interpolation. We could confirm much improved resolution of bone image with acoustic lens attached to the ultrasonic probe and with the image processing algorithm suggested in this study. Therefore, it became possible to precisely diagnose the osteoprosis using ultrasonic imaging technique.