• Journal of Yeungnam Medical Science
• /
• v.27 no.1
• /
• pp.52-56
• /
• 2010

Idiopathic peripartum cardiomyopathy is an uncommon malady disease. Making the diagnosis is often difficult and it is always necessary to exclude other prior heart disease and other causes of left ventricular dysfunction in pregnant women. Heart failure in these women ensues when the cardiovascular demands of normal pregnancy are further amplified when the common complications of pregnancy complications superimposed upon these underlying conditions that cause compensated ventricular hypertrophy. This may be aggravated by making a late diagnosis and providing inappropriate treatment. We experienced a 38-year-primigravida who has diagnosed with idiopathic peripartum cardiomyopathy and underwent elective cesarean section with general anesthesia.

• Korean Journal of Veterinary Pathology
• /
• v.3 no.2
• /
• pp.93-94
• /
• 1999

Spontaneous hydronephrosis was found in a 19 month-old female C57BL/KsJ-Lep $r^{db}$ / Lep $r^{db}$ mouse. We described the gross and histological appearance of spontaneous in db mouse The left kidney was dilated and filled with urine. Microscopically the renal pelvis was remarkedly dilated and the renal cortex and renal papilla were flattened.

• Journal of Chest Surgery
• /
• v.21 no.1
• /
• pp.143-147
• /
• 1988

Congenital coronary arteriovenous fistula is a communication of a coronary artery with one of the atria, ventricles, the coronary sinus, the superior vena cava, or the pulmonary artery. We had a successful surgical experience with 63 year-old-female patient who complained substernal chest pain on exertion for 8 years. On auscultation, a continuous murmur was heard at the left second to third intercostal space along the left sternal border. The right cardiac catheterization was revealed to 4% oxygen step up between right ventricle to main pulmonary artery, and Qp/Qs was 1.3:1. The selective coronary arteriography showed markedly tortuous dilated vessel which originated from left coronary artery draining into the main pulmonary artery. The operation performed to mid portion of tortuous and dilated fistula by multiple ligation with 3-0 Mersilene and suture ligation with pledgetted 3-0 Prolene on distal draining site, Postoperative course were uneventful without any symptoms and complications.

• Investigative Magnetic Resonance Imaging
• /
• v.23 no.4
• /
• pp.395-400
• /
• 2019

Acromegaly is a rare endocrine disorder caused by excessive secretion of the growth hormone. There is a wide range of clinical manifestations from somatic symptoms to respiratory or cardiac failure. Among them, cardiovascular involvement is a leading cause of morbidity and mortality. There are relatively few cases reporting cardiac magnetic resonance imaging (CMR) findings of cardiomyopathy in patients with acromegaly. Thus, we report a case of acromegaly showing dilated cardiomyopathy focusing on the findings of CMR.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.335-338
• /
• 2021

본 논문에서는 기존 AHDRNet에 channel attention 기법을 적용했을 때 성능에 어떠한 변화가 있는지를 평가하였다. 기존 모델의 병합 망에 존재하는 DRDB(Dilated Residual Dense Block) 사이, 그리고 DRDB 내의 확장된 합성곱 레이어 (dilated convolutional layer) 뒤에 또다른 합성곱 레이어를 추가하는 방식으로 channel attention 기법을 적용하였다. 데이터셋은 Kalantari의 데이터셋을 사용하였으며, PSNR(Peak Signal-to-Noise Ratio)로 비교해본 결과 기존의 AHDRNet의 PSNR은 42.1656이며, 제안된 모델의 PSNR은 42.8135로 더 높아진 것을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.709-711
• /
• 2023

안전관리를 위한 인공지능 기술은 꾸준히 연구되고 있는 분야다. 특히, 컴퓨터 비전 기술을 활용한 CCTV 영상 분석은 군중의 동선과 밀도를 파악하는데 유용하며, 대규모 실내 공간에서 체계적인 안전관리를 가능하게 한다. 그러나 기존의 CCTV 카메라를 사용한 군중 수 추정은 가려짐(occlusion)과 같은 한계가 있다. 본 논문은 무선 랜 신호 데이터 분석 기법을 활용하여 수집한 데이터를 활용하여 실내 환경에서 군중 수를 추정하고자 한다. 본 논문에서는 인원 수 분류 예측을 위해 셰이플릿 확장 변환(Random Dilated Shapelet Transform) 기법을 제안한다. 단일 데이터 세트 내 분류 결과와, TX, RX 배치 방식에 따른 분류 성능의 차이는 모델의 성능 부족보다 데이터의 특성을 고려한 새로운 접근 방법의 필요성을 알려준다.

• Clinical and Experimental Pediatrics
• /
• v.46 no.9
• /
• pp.921-925
• /
• 2003

Intestinal lymphangiectasia, one of the protein-losing gastroenteropathies, is an uncommon disease characterized by dilated intestinal lymphatics, enteric protein loss, edema, hypoalbuminemia, and lympocytopenia. Small bowel biopsy and CT have been used to confirm the diagnosis of intestinal lymphangiectasia. Small bowel biopsy shows collections of abnormal dilated lacteals in submucosa with distortion of villi and CT findings have been described as diffuse nodular thickening of the small bowel and as linear hypodense streaking densities in the small bowel caused by dilated lymphatic channels. Demonstration of increased enteric protein loss using $^{51}Cr-$, $^{131}I-$ or $^{99m}Tc-labeled$ albumin, timed measurement of fecal excretion of radioactivity or by measuring fecal clearance of alpha 1-antitrypsin can also help the diagnosis. We experienced a rare case of intestinal lymphangiectasia in an eight year old boy who presented with facial edema, abdominal distension and intermittent diarrhea. We report a patient with intestinal lymphangiectasia, in whom abdominal CT, $^{99m}Tc-labeled$ albumin scintitigraphy, and stool alpha 1-antitrypsin measurement played key roles in determining the diagnosis. A brief review of literature was made.

• Korean Journal of Veterinary Service
• /
• v.40 no.4
• /
• pp.287-292
• /
• 2017

A five-year-old, male, Great Dane weighing 107 kg was presented with anorexia, abdominal distension, and dyspnea for 5 days. Physical examination, blood works, radiography, electrocardiography (ECG), and echocardiography were performed. Based on severely low fractional shortening (FS) and marked four chamber enlargement in echocardiography, continuous atrial fibrillation and occasional ventricular premature complex (VPC) on ECG, the dog was diagnosed as dilated cardiomyopathy (DCM) concurrent with congestive heart failure. Pleural effusion and ascites were modified transudate. In accordance with DCM scoring system recommended by European Society of Veterinary Cardiology (ESVC), DCM score was 13/15 in this case. Concentrations of cTnI and NT-pro-BNP were 1.0 ng/mL and 693 pmol/L, respectively. Since the former and the latter were remarkably high values, it was certain that the patient had grave prognosis. Intensive care was performed for the dog and the clinical signs as well as the radiographic abnormalities were resolved. However, when he presented serious dyspnea again at 25 days post therapy, the dog was dead. In case of canine DCM, the scoring system for the diagnosis and cardiac biomarkers including NT-pro-BNP and cTnI could be useful to advise owners on the status and prognosis of their dog with DCM.

• Journal of Chest Surgery
• /
• v.40 no.7 s.276
• /
• pp.499-502
• /
• 2007

Left ventricular inflow obstruction can be caused by a persistent left superior vena cava (SVC) and a dilated coronary sinus. A 31-day-old male infant with secondum atrial septal defect (ASD) and bilateral SVC underwent an operation for treating his uncontrollable congestive heart failure. The preoperative 2-dimensional echocardiography showed a normally sized mitral valve shrouded by a dilated coronary sinus. The operation consisted of pericardial patch closure of the ASD, coronary sinus unroofing and left SVC transfer to the right atrial auricle. The postoperative course was complicated by persistent chylothorax, which was controlled by thoracic duct ligation, He was discharged to home at the postoperative day 39. He has been followed up for 9 months and has displayed normal development.

• Phonetics and Speech Sciences
• /
• v.11 no.4
• /
• pp.89-96
• /
• 2019

In this paper, we propose a deep learning architecture that can effectively detect speech segmentation in broadcast contents. We also propose a multi-scale time-dilated layer for learning the temporal changes of feature vectors. We implement several comparison models to verify the performance of proposed model and calculated the frame-by-frame F-score, precision, and recall. Both the proposed model and the comparison model are trained with the same training data, and we train the model using 32 hours of Korean broadcast data which is composed of various genres (drama, news, documentary, and so on). Our proposed model shows the best performance with F-score 91.7% in Korean broadcast data. The British and Spanish broadcast data also show the highest performance with F-score 87.9% and 92.6%. As a result, our proposed model can contribute to the improvement of performance of speech detection by learning the temporal changes of the feature vectors.