• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.248-251
• /
• 1995

Nowadays, the internal images of a human body can be easily provided by the ultrasound imaging, the X-ray CT, or the MRI device, among which the ultrasound imaging device has good resolution for soft tissues of a human body compared with the other devices. Furthermore, the use of ultrasound imaging devices will increase in future especially in the obstetrics, territory, since it does not give harm to the human body. Although several techniques have been investigated until now in order to extract organs from ultrasound images, very few of them have achieved satisfactory results because of low contrast and high noise nature of images. This paper proposes a technique for automatic extraction of the gall bladder area from ultrasound images. The proposed technique first extracts a small reliable area of a gall bladder from an ultrasound image employing smoothing, binarization, expanding and shrinking, and labeling, and then expands the area referring to the binarized version of the original image. The technique is examined its performance by real ultrasound images of a gall bladder and satisfactory results are obtained. Some problems to be solved are discussed finally.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.357-358
• /
• 2007

Contrast enhancement in the field of ultrasound imaging contributes to improve the accuracy of medical diagnosis by enhancing the visibility of ultrasound images. This paper proposes a contrast enhancement method that improves the contrast of ultrasound images both globally and locally by fusing global and adaptive contrast enhancement methods. Experimental results show that our approach yields more competitive results than the existing global and adaptive contrast enhancement methods in enhancing the visibility of ultrasound images.

• Journal of Biomedical Engineering Research
• /
• v.17 no.4
• /
• pp.433-442
• /
• 1996

Since one texture property(i.e coarseness, orientation, regularity, granularity) for ultrasound liver ages was not sufficient enough to classify the characteristics of livers, we used multi texture vectors tracted from ultrasound liver images and a statistical classifier. Multi texture vectors are selected among the feature vectors of the normal liver, fat liver and cirrhosis images which have a good separability in those ultrasound liver images. The statistical classifier uses multi texture vectors as input vectors and classifies ultrasound liver images for each multi texture vector by the Bayes decision rule. Then the decision of the liver disease is made by choosing the maximum value from the averages of a posteriori probability for each multi texture vector In our simulation, we obtained higtler correct ratio than that of other methods using single feature vector, for the test set the correct ratio is 94% in the normal liver, 84% in the fat liver and 86% in the cirrhosis liver.

• Physical Therapy Korea
• /
• v.13 no.1
• /
• pp.47-53
• /
• 2006

Since ultrasound has different reflections depending on components of organization, analysis of ultrasound images of skeletal muscle can offer both quantitative and qualitative reports as concerns skeletal muscle structure. This study is focused on the ultrasound method for evaluating the structural characteristics of skeletal muscle and also conducted to examine its practicality. After obtaining images of the elbow flexors from an ultrasound image device with 88 normal subjects whose ages were between twenty and seventy years old (44 men and 44 women), muscular density and white area index (WAI) which indicated structural characteristics of skeletal muscle were analyzed with gray scale analysis. The study examined correlations between subject's age and items which obtained from measuring ultrasound images and the differences in relations to sex and age. Muscular density and WAI had a high correlation with age and were significantly increased in men and women with greater age. The quantitative evaluation method of skeletal muscle structure which analyzed the ultrasound images has high practicality because it is a non-invasive method which complements physical therapy diagnosis and research methods and promotes functionality evaluation.

• Journal of Biomedical Engineering Research
• /
• v.37 no.1
• /
• pp.31-38
• /
• 2016

For the patients with bladder dysfunction, measurement of urine volume inside the bladder is very critical to avoid bladder failure. In measuring urine volume inside a bladder, low-resolution 3D ultrasound images are widely used. However, urine volume estimation from 3D ultrasound images is prone to big errors and inconsistency because of low spatial resolution and low signal-to-noise ratio of ultrasound images. We developed a new robust volume estimation algorithm which is not computationally expensive. We tested the algorithm on a lab-built ultrasound bladder phantom and volunteers. The average error rate of the human bladder volume estimation was 5.9% which was better than the commercial machine.

• Journal of Biomedical Engineering Research
• /
• v.28 no.2
• /
• pp.294-299
• /
• 2007

For efficient and accurate diagnosis of ultrasound images, appropriate time gain compensation(TGC) and dynamic range(DR) control of ultrasound echo signals are important. TGC is used for compensating the attenuation of ultrasound echo signals along the depth, and DR controls the image contrast. In recent ultrasound systems, these two factors are automatically set by a system and/or manually adjusted by an operator to obtain the desired image quality on the screen. In this paper, we propose an algorithm to find the optimized parameter values far TGC and DR automatically. In TGC optimization, we determine the degree of attenuation compensation along the depth by dividing an image into vertical strips and reliably estimating the attenuation characteristic of ultrasound signals. For DR optimization, we define a novel cost function by properly using the characteristics of ultrasound images. We obtain experimental results by applying the proposed algorithm to a real ultrasound(US) imaging system. The results verify that the proposed algorithm automatically sets values of TGC and DR in real-time such that the subjective quality of the enhanced ultrasound images may be sufficiently high for efficient and accurate diagnosis.

• Biomedical Engineering Letters
• /
• v.8 no.4
• /
• pp.355-364
• /
• 2018

When focusing using an ultrasonic transducer array, a main lobe is formed in the focal region of an ultrasound field, but side lobes also arise around the focal region due to the leakage. Since the side lobes cannot be completely eliminated in the focusing process, they are responsible for subsequent ultrasound image quality degradation. To improve ultrasound image quality, a signal processing strategy to reduce side lobes is definitely in demand. To this end, quantitative determination of main and side lobes is necessary. We propose a theoretically and actually error-free method of exactly discriminating and separately computing the main lobe and side lobe parts in ultrasound image by computer simulation. We refer to images constructed using the main and side lobe signals as the main and side lobe images, respectively. Since the main and side lobe images exactly represent their main and side lobe components, respectively, they can be used to evaluate ultrasound image quality. Defining the average brightness of the main and side lobe images, the conventional to side lobe image ratio, and the main to side lobe image ratio as image quality metrics, we can evaluate image characteristics in speckle images. The proposed method is also applied in assessing the performance of side lobe suppression filtering. We show that the proposed method may greatly aid in the evaluation of medical ultrasonic images using computer simulations, albeit lacking the use of actual experimental data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.134-136
• /
• 2021

Research related to early diagnosis of breast cancer using artificial intelligence algorithms has been actively conducted in recent years. Although various algorithms that classify breast cancer based on a few publicly available ultrasound breast cancer images have been published, these methods show various limitations such as, processing speed and accuracy suitable for the user's purpose. To solve this problem, in this paper, we propose a multi-stage transfer learning where ResNet model trained on ImageNet is transfer learned to microscopic cancer cell line images, which was again transfer learned to classify ultrasound breast cancer images as benign and malignant. The images for the experiment consisted of 250 breast cancer ultrasound images including benign and malignant images and 27,200 cancer cell line images. The proposed multi-stage transfer learning algorithm showed more than 96% accuracy when classifying ultrasound breast cancer images, and is expected to show higher utilization and accuracy through the addition of more cancer cell lines and real-time image processing in the future.

• Journal of the Korean Society of Radiology
• /
• v.9 no.5
• /
• pp.263-267
• /
• 2015

In this paper, a method was proposed for objective and scientific judgment on disease conditions that is currently relied on subjective judgment of ultrasound practitioners. In the proposed method, mean squared errors (MSE) in ultrasound images for follow-up of HCC patients were obtained and the Peak Signal to Noise Ratio(PSNR) of the ultrasound images was analyzed. According to the results of analysis, MSE and PSNR values changed over time. This is attributable to changes in ultrasound images resulting from increases in utrasonic echoes following the progression of HCC. The results of the present study can be used as a method for scientific and objective judgment in ultrasonic scan instead of current subjective judgment by practitioners.

• Journal of Korean Neurosurgical Society
• /
• v.66 no.2
• /
• pp.172-182
• /
• 2023

Objective : The blood-brain barrier (BBB) is an obstacle for molecules to pass through from blood to the brain. Focused ultrasound is a new method which temporarily opens the BBB, which makes pharmaceutical delivery or removal of neurodegenerative proteins possible. This study was demonstrated to review our BBB opening procedure with magnetic resonance guided images and find specific patterns in the BBB opening. Methods : In this study, we reviewed the procedures and results of two clinical studies on BBB opening using focused ultrasound regarding its safety and clinical efficacy. Magnetic resonance images were also reviewed to discover any specific findings. Results : Two clinical trials showed clinical benefits. All clinical trials demonstrated safe BBB opening, with no specific side effects. Magnetic resonance imaging showed temporary T1 contrast enhancement in the sonication area, verifying the BBB opening. Several low-signal intensity spots were observed in the T2 susceptibility-weighted angiography images, which were also reversible and temporary. Although these spots can be considered as microbleeding, evidence suggests these are not ordinary microbleeding but an indicator for adequate BBB opening. Conclusion : Magnetic resonance images proved safe and efficient BBB opening in humans, using focused ultrasound.