• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.754-756
• /
• 2005

본 논문은 연속 초음파 영상에서 움직임 보상 시간 필터를 적용하여 영상의 품질을 향상시키는 방법을 제안한다. 비선형 광학 흐름 추정 방법을 이용하여 화소 단위의 움직임을 추정하고, 이를 바탕으로 시간적 재귀 필터링을 적용한다 화소 단위 움직임 벡터의 양이 작을 경우 필터링을 크게 하고, 움직임 벡터의 양이 클 경우 필터링을 작게 적용한다. 그 결과 프로브에 의한 전역적 움직임과 측정 대상물에 의한 국부적 움직임으로 발생되는 블러 현상을 극소화하고 잡음을 감소시켜 영상의 품질을 향상시켰다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.556-558
• /
• 2019

기존 초음파 지방간 분석은 Hepatorenal sonographic index(HI)를 사용하여 지방간을 진단하여 왔다. 이러한 HI 기법에서는 Hepato(간)과 Renal(신장), 두 부분의 영상데이터를 비교 활용하였다면, 본 논문에서는 신장의 영상데이터만을 이용하여, 이의 통계적 특징 벡터만을 활용하여 지방간을 진단을 함으로서 기존의 HI기반 분석대비 편리성과 정확도를 개선코자 Kidney Index(KI) 기반의 분석 기법을 제안한다. 본 논문에서 제안된 KI는 정상간과 지방간을 가진 실제 환자의 초음파 사진(정상간, 지방간 각 30명)을 학습 데이터를 구성하고, 이들 데이터군으로부터 특징 벡터들을 선별하여 머신러닝 기법 중 서포트 벡터 머신(Support Vector Machine)을 통해 학습시켜, 제안된 알고리즘의 유효성을 입증하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.792-795
• /
• 2013

본 연구에서는 조영증강 의료 초음파 영상에서 조영제의 도달시간(arrival time)과 전이시간(transit time)에 관한 정보를 영상화하는 과정에서 정보의 왜곡을 개선하는 방법론을 제시한다. 간 질환 진단을 위한 파라미터 영상에서 병변 형태의 왜곡은 호흡에 의한 흔들림 현상과 노이즈의 영향에 기인한다. 본 논문에서는 이를 개선하는 방법으로서 MRF(Markov Random Field) 모델을 적용한 최적화 기법을 제안한다. 이를 위하여 Gibbs 샘플러를 적용하기 위한 에너지 함수를 정의하고 이를 기반으로 하는 영상개선 알고리즘을 구현하였다. 제안된 이론은 실제 의료진단 데이터에 적용함으로써 그 유용성을 평가하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.232-235
• /
• 2013

간 질환 진단을 위한 의료 초음파 동영상에서 호흡으로 인한 영상의 흔들림 현상은 전이시간(transit time) 요소와 같은 진단 파라미터의 신뢰도를 저하시킬 뿐만 아니라, 정확한 병변 형태의 추출을 어렵게 한다. 본 연구에서는 호흡 주기를 자동으로 감지하고 이를 기반으로 ROI 를 추적하는 방법과 프레임 샘플링을 통하여 TIC(Time-Intensity Curve) 형태의 왜곡을 보정하는 방법을 고찰한다. 세부적으로 동적 가중치와 모멘텀 요소를 고려한 추적 기법을 제시하고 유용성을 평가한다. 또한 호흡주기와 프레임간 유사도(similarity)를 기반으로 한 영상 샘플링 기법을 제안하고 이로부터 신호의 왜곡을 보정할 수 있음을 보인다.

• Clinical Pain
• /
• v.18 no.1
• /
• pp.44-47
• /
• 2019

Lying on the side while falling asleep deeply after drinking or taking a sleeping pill can cause compressive neuropathy. We report a 70-year-old male patient of medial cord of left brachial plexus injury (BPI) after deep sleep. The mechanism of the injury might be compression and stretching of brachial plexus. The electrodiagnostic study was performed and the medial cord lesion of BPI was suggested. The ultrasonography image of compression site revealed the nerve swelling of medial cord of brachial plexus and median nerve at the mid-arm level. Pharmacologic treatment including oral prednisolone and exercise training were prescribed. On 6 months after initial visit, neurologic symptom and pain were improved but mild sequelae was remained.

• Transactions on Electrical and Electronic Materials
• /
• v.17 no.6
• /
• pp.375-379
• /
• 2016

Increasing fat tissue of obese people, increases the rate of cardiovascular disease, diabetes, metabolic syndromes and dyslipidemia. An increase in the focal tissue of pancreas is a known risk factor of these diseases. Although there exists sufficient research on the diagnosis and treatment of pancreatic cancer, studies have been done on fatty pancreas. In this study, based on ultrasound imaging and using a texture characteristic of GLCM, fatty pancreas was divided into three categories: mild, moderate and severe. We compared and analyzed the three groups was by Pancreatic ultrasonography and body characteristics, serological tests, pressure and the degree of arteriosclerosis, against normal control group. The following parameters of control and test groups were measured: WC (waist circumference),BMI (body mass index), TC (total cholesterol), TG (triglyceride), HDL-C (High-density lipoprotein cholesterol) and LDL-C (Low-density lipoprotein cholesterol), SBP (systolic blood pressure), BST (Blood Sugar Test) and aortic PWV (pulse wave velocity). We observed the values correspondingly increasing fat deposition. However, ABI (Ankle Brachial pressure index) stenosis and HDL-C levels decreased with increasing fat deposit (p <0.05); a drop in these parameters are known to be harmful to the human body. The difference in texture characteristics between normal control group and pancreatic fatty group (mild, moderate, and severe) was statistically confirmed. Ultrasound imaging of pancreatic steatosis categorized the disease as mild, moderate and severe based on the characteristic texture. In conclusion, we observed on increase in metabolic syndrome, dyslipidemia, and arteriosclerosis, proportional to the degree of pancreatic fat deposition. The escalation of these diseases was confirmed and was directly related with predictors of cardiovascular diseases.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.2
• /
• pp.70-77
• /
• 2019

Breast ultrasound readings are very important to diagnose early breast cancer. In Ultrasonic inspection, it shows a significant difference in image quality depending on the ultrasonic equipment, and there is a large difference in diagnosis depending on the experience and skill of the inspector. Therefore, objective criteria are needed for accurate diagnosis and treatment. In this study, we analyzed texture characteristics by applying GLCM (Gray Level Co-occurrence Matrix) algorithm and extracted characteristic parameters and diagnosed breast cancer using neural network classifier. Breast ultrasound images were classified into normal, benign and malignant tumors and six texture parameters were extracted. Fourteen cases of normal, malignant and benign tumor diagnosed by mammography were studied by using the extracted six parameters and learning by multi - layer perceptron neural network back propagation learning method. As a result of classification using 51 normal images, 62 benign tumor images, and 74 malignant tumor images of the learned model, the classification rate was 95.2%.

• The Journal of Korean Physical Therapy
• /
• v.26 no.5
• /
• pp.324-330
• /
• 2014

Purpose: The aim of the current study was to compare the muscle architecture of lower extremity using rehabilitative ultrasound imaging (RUSI) in young adults in Seoul and Hanoi. Methods: The study design was a comparative study of muscle cross-sectional area of lower extremity. Sixty healthy young subjects (Seoul group: 30, Hanoi group: 30) participated in this study. Real-time B-mode RUSI with a 7.5MHz linear transducer was used for measurement of cross-sectional area, pennation angle, and muscle thickness of the rectus femoris, tibialis anterior, and medial gastrocnemius muscles. Independent t-test was used for statistical analysis. Results: Significant difference in cross sectional area of rectus femoris was observed between Korean young adults and Hanoi young adults (p<0.01). Muscle thickness and pennation angle of tibialis anterior in Korean young adults were greater than in Hanoi young adults (p<0.01). In addition, the muscle thickness and pennation angle of the medial part of gastrocnemius muscle were greater in Korean young adults than in Hanoi young adults (p<0.01). In addition, in the results for gender, men had larger muscle architectures than women in both groups (p<0.01). Conclusion: This study, using RUSI, showed significant difference in muscle architectures of lower extremity in a diverse group of young adults RUSI.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.901-904
• /
• 2007

Nowadays, in many fields of medical treatment, we can make an observation and a diagnosis of inward disease without using a surgical operation. As one of them, ultra-sound diagnosis system can be available widely in its cost and size compared with other medical instruments. This system also make it possible for us to see the inner parts of the body in real time harmlessly for a long time. So it can be utilized to inspect the movement of heart or fetus and to diagnose an internal disease of the soft tissues. Ultra-sound images can be generated by the reflexive and scattered wave through the pulse generator and so in ultrasound images there exist inherently many affective noised signals. In this paper, we are to take an noise-restrained image and to extract a more affective regions of the images.

• Journal of Biomedical Engineering Research
• /
• v.31 no.4
• /
• pp.285-291
• /
• 2010

Recently, advance on various modalities of diagnosing, prostate volume estimation became possible not only by the existing two-dimension medical images data but also by the three-dimensional medical images data. In this study, magnetic resonance image (MRI), computer tomography (CT) and ultrasound (US) were employed to evaluate prostate phantom volume measurements for estimation, comparison and analysis. For the prostate phantoms aimed at estimating the volume, total of 17 models were developed by using devils-tongue jelly and changing each of the 5ml of capacity from 20ml to 100ml. For the volume estimation through 2D US, the calculation of the diameter with C9-5Mhz transducer was conducted by ellipsoid formula. For the volume estimation through 3D US, the Qlab software (Philips Medical) was used to calculate the volume data estimated by 3D9-3Mhz transducer. Moreover, the images by 16 channels CT and 1.5 Tesla MRI were added by the method of continuous cross-section addition and each of imaginary prostate model's volume was yielded. In the statistical analysis for comparing the availability of volume estimation, the correlation coefficient (r) was more than 0.9 for all indicating that there were highly correlated, and there were not statistically significant difference between each of the correlation coefficient (p=0.001). Therefore, the estimation of prostate phantom volume using three-dimensional modalities of diagnosing was quite closed to the actual estimation.