• Journal of the Korean Institute of Intelligent Systems
• /
• 제22권3호
• /
• pp.341-346
• /
• 2012

In rehabilitation where ultrasonographic diagnosis is not popular, it could be subjective by medical expert's experience. Thus, it is necessary to develop an objective automative procedure in ultrasonic image analysis. A disadvantage of existing automative analytic procedure in musculoskeletal system is to designate an incorrect muscle area when the figure of fascia is vague. In this study, we propose a new procedure to extract more accurate muscle area in abdomen ultrasonic image for that purpose. After removing unnecessary noise from input image, we apply End-in Search algorithm to enhance the contrast between fascia and muscle area. Then after extracting initial muscle area by Up-Down search, we trace the fascia area with a mask based on morphological and directional information. By this tracing of mask movements, we can emphasize the fascia area to extract more accurate muscle area in result. This new procedure is proven to be more effective than existing methods in experiment using convex ultrasound images that are used in real world rehabilitation diagnosis.

• Journal of the Korean Society of Radiology
• /
• 제17권3호
• /
• pp.385-392
• /
• 2023

Caroli's disease is a fibrocystic liver disease. Autosomal recessive disorder is characterized by congenital multiple dilatation of the bile duct. Computerized tomography, magnetic resonance imaging, cholangiography and ultrasound are among the methods for diagnosing caroli disease. Computerized tomography is essential for detecting and distinguishing fibroplastic liver disease and is useful for determining intrahepatic bile duct dilatation. However, awareness of the possible side effects of using contrast mediums is necessary. A typical method of magnetic resonance cholangiography is used for magnetic resonance imaging. A non-invasive examination can reduce the pain of the patient, and the anatomical structure of the bile pancreatic duct and the presence or absence of lesions can be easily and quickly observed. Biliary contrast is an effective diagnostic method that can directly visualize various cystic dilatations throughout the enlarged bile duct. However, since this procedure is also an invasive procedure, it is recommended not for diagnosis but for treatment purposes. Ultrasonography can confirm similar findings to computerized tomography. The hepatic artery root is difficult to prove with conventional grayscale ultrasound. However, it is of clinical value in that it can not only describe dilated bile ducts with vascular roots in the tube but also easily identify color Doppler signals in the tube. With the development of video diagnostics, early diagnosis has become possible through computerized tomography, magnetic resonance imaging, cholangiography, and ultrasound. In order to further contribute to the development of video diagnostics so that long-term prognosis can be improved after treatment through early diagnosis, we examined what aspects of each test's caroli disease appear.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• 제11권1호
• /
• pp.12-20
• /
• 2008

Purpose: Chronic pulmonary disease may be caused by aspiration of gastric contents secondary to gastroesophageal reflux. At present, there is no gold standard for documenting pulmonary aspiration. The purpose of this study was to investigate the usefulness of radionuclide scintigraphy in the detection of gastroesophageal reflux and pulmonary aspiration. Methods: Thirty-five patients with suspected aspiration pneumonia, and five normal control subjects, were included in the study. All subjects underwent gastroesophageal reflux scintigraphy after the ingestion of a $^{99m}Tc$-tin colloid mixture. Dynamic images to detect gastroesophageal reflux were obtained for 1 hour. Additional static images of the chest, to detect lung aspiration, were obtained at 6 and 24 hours after oral ingestion of the tin colloid. In addition to visual analysis, pulmonary aspiration was quantitated by counting the number of pixels labeled with radioactive isotope in the region of interest (ROI) of both lung fields. Aspiration index (AI) was obtained by subtracting the pixel counts of the background from the pixel counts of the ROI. Results: Among 35 patients with suspected aspiration pneumonia, 23 proved to have gastroesophageal reflux by scintigraphy. One patient showed definite pulmonary accumulation of activity by visual analysis of the 6-hour image. Thirty of 35 (85.7%) patients showed higher AI beyond the upper limit of AI in the healthy controls. When we compared the reflux group with the non-reflux group, there was a significantly higher AI at 6 hours in the reflux group (p<0.05). Conclusion: The results suggest that radionuclide scintigraphy is useful in detecting small pulmonary aspiration in patients with suspected aspiration pneumonia secondary to reflux.

• Journal of the Korean Society of Radiology
• /
• 제85권4호
• /
• pp.769-779
• /
• 2024

Purpose To determine the pros and cons of an artificial intelligence (AI) model developed to diagnose acute rib fractures in chest CT images of patients with chest trauma. Materials and Methods A total of 1209 chest CT images (acute rib fracture [n = 1159], normal [n = 50]) were selected among patients with chest trauma. Among 1159 acute rib fracture CT images, 9 were randomly selected for AI model training. 150 acute rib fracture CT images and 50 normal ones were tested, and the remaining 1000 acute rib fracture CT images was internally verified. We investigated the diagnostic accuracy and errors of AI model for the presence and location of acute rib fractures. Results Sensitivity, specificity, positive and negative predictive values, and accuracy for diagnosing acute rib fractures in chest CT images were 93.3%, 94%, 97.9%, 82.5%, and 95.6% respectively. However, the accuracy of the location of acute rib fractures was low at 76% (760/1000). The cause of error in the diagnosis of acute rib fracture seemed to be a result of considering the scapula or clavicle that were in the same position (66%) or some ribs that were not recognized (34%). Conclusion The AI model for diagnosing acute rib fractures showed high accuracy in detecting the presence of acute rib fractures, but diagnosis of the exact location of rib fractures was limited.

• Journal of the Korean Institute of Intelligent Systems
• /
• 제25권1호
• /
• pp.57-62
• /
• 2015

In this paper, we design fuzzy inference-based deterioration diagnosis system through different image for rapid as well as efficient diagnosis of electrical equipments. When the deterioration diagnosis of the electrical equipment starts, abnormal state of assigned area is detected by comparing with the temperature of the first normal state of the area. Deterioration state of detected area is diagnosed by using fuzzy inference algorithm. In the fuzzy inference algorithm, fuzzy rules are defined by If-then form and are described as look-up table. Both temperature and its ensuing variation are used as input variables. While triangular membership function is used for the fuzzy input variables of fuzzy rules, singleton membership function is used for the output variable of fuzzy rules. The final output is calculated by using the center of gravity of fuzzy inference method. Experimental data acquired from individual electrical equipments is used in order to evaluate the output performance of the proposed system.

• The Journal of Korean Orthopaedic Ultrasound Society
• /
• 제8권1호
• /
• pp.26-30
• /
• 2015

There are many traumatic foot and ankle problems in orthopaedic fields. Though it is not life-threatening problems, a delay in accurate diagnosis and treatments can danger limb function and therefore correct diagnosis can prevent long-term complications. Achilles tendon rupture is relatively common injury for active sports people. Ultrasonography is cost-effective, irradiation -free, effective for evaluation of soft tissues and dynamic analysis. It has been growing importance in Achilles tendon rupture. Ultrasonography is a diagnostic tool in Achilles tendon rupture. Physical examination and patient history is needed to diagnose Achilles tendon without image, but it is missed up by 20% in private clinic. Discontinuity of normal fibrillar architecture seen on an ultrasonographic image is diagnostic for Achilles tendon rupture, and can be accentuated by the performance of dorsi-flexion and plantar flexion, while observing in real time. And ultrasonography is a reliable method for serial observation after surgical treatment or conservative treatment.

• Proceedings of the Korean Information Science Society Conference
• /
• 한국정보과학회 2004년도 가을 학술발표논문집 Vol.31 No.2 (2)
• /
• pp.757-759
• /
• 2004

본 연구에서는 초음파 영상에서 간실질의 에코 명도를 비롯한 픽셀 정보분포를 분석하여 정량화 지방간 진단 파라미터를 구하기 위해 규준화 에코 명도 값 및 다수의 텍스쳐 파라미터 값을 추출하여 선형결합을 통해 지방간의 진행 정도와의 상관성을 연구하였다. 임상 지방간 지수와 본 연구의 추정 지방간 지표 값과의 선형 상관계수를 구하였다 신장대조 방법으로 추출한 규준화 에코 명도 및 회색도 픽셀분포의 텍스쳐 특성 파라미터를 계산하여 임상결과와 비교한 결과 임상 지방간 지수와 높은 상관성을 보임을 알 수 있었고, 지방간 진단의 보조사료로 유용함을 확인하였다. 계산된 지방간 지수와 임상결과 간의 선형상관계수는 0.84-0.93이다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• 제19권1호
• /
• pp.47-53
• /
• 2001

In this study, it is intended to measure the displacement of a bridge for the safety examination using Digital Close Range Photogrammetry(DCRP). The digital images which were obtained by a digital camera and a CCD camera in load cases was analyzed. In the same condition, the displacements were obtained respectively from sensor, precision level, and film-based images for comparison. As a result, it could be confirmed that the application of DCRP to the safety examination and the movement measurement of the bridge is possible.

• Proceedings of the Korea Society for Simulation Conference
• /
• 한국시뮬레이션학회 1999년도 춘계학술대회 논문집
• /
• pp.138-142
• /
• 1999

심장의 수축 및 이완기에서의 좌심실 벽 움직임은 허혈 및 심근경색증과 같은 심장질환에서 영상적 진단의 주요한 특징이다. 심장은 동적 기관으로써 진단을 위해서는 속도와 같은 4차원 파라미터의 추정이 필요하다. 본 논문에서는 심장의 좌심실 형태 및 움직임을 모델링하여 동적으로 가시화하는 방법을 제시한다. 본 논문에서는 좌심실을 Dynamic Gaussian Blob 모델로 근사화하였다. 이 모델은 가우시안 함수 기반 FEM 요소와 superellipsoid를 통합한 것으로 좌심실의 형태 및 벽의 움직임을 물리기반 방법에 의해 묘사할 수 있다. 즉, 일련의 영상들로부터 좌심실 벽에 대응되는 3차원 점들을 추출한 후 이 점들에 작용되는 힘에 의해 박동하는 좌심실의 움직임을 추적한다. 이와 같은 좌심실 벽 움직임 시뮬레이션은 심장 움직임에 이상이 있는 질환의 진단을 위한 빠르고 간편한 보조 도구로써 사용되어질 수 있다.

• Annual Conference of KIPS
• /
• 한국정보처리학회 2013년도 추계학술발표대회
• /
• pp.1309-1311
• /
• 2013

본 연구에서는 의료 진단키트의 자동판독 시스템에서, 통제되지 않은 조명 환경에서도 정확한 색상 판별을 위한 ROI 영역 추출 기법과 조명 보정 기법을 고찰한다. 3단계로 세분된 ROI 추출 과정은 조명변화에 적응적인 배경영상 정보를 유지하고, 노이즈 제거와 에지 추출 과정을 포함한다. 진단 결과의 정량적 판별에 중요 지표가 되는 색상정보가 조명의 영향의 의해 왜곡되는 것을 보완하기 위하여 표본 추출된 학습데이터로부터 조명 보정 곡선을 생성한다. 20종류의 색상패턴을 대상으로 적용한 실험 결과를 통하여 제안된 이론의 유용성을 고찰한다.