• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.903-906
• /
• 2021

인공지능 기술 발전으로, 의료영상 분야에서도 딥러닝 기반 질병 진단 연구가 활발히 진행되고 있다. 딥러닝 모델 개발 시, 학습 데이터 품질은 모델의 성능과 신뢰성에 매우 큰 영향을 미친다. 그러나 의료 분야의 경우 도메인 지식에 대한 진입 장벽이 높아 개발자가 학습에 사용되는 의료영상 데이터의 품질을 평가하기 어렵다. 이로 인해, 많은 의료영상 분야에서는 각 분야의 특성(질병의 종류, 관찰 아나토미 등)에 따른 영상 품질 평가 방법을 제시해왔다. 그러나 기존의 방법은 특정 질병에 초점이 맞춰져, 일반화된 품질 평가 기준을 제시하고 있지 않다. 따라서 본 논문에서는 대부분의 흉부 질환을 진단하기 위한 흉부 X선 영상의 품질을 평가할 수 있는 기준을 제안한다. 우선, 흉부 X선 영상을 대상으로 관찰된 영역인 심장, 횡격막, 견갑골, 폐 등을 분할하여, 3D 히스토그램을 기반으로 각 영역별 통계적인 정밀 품질 평가 기준을 제안한다. 본 연구에서는 JSRT, Chest 14의 오픈 데이터셋을 활용하여 적용 실험을 수행하였으며, 민감도는 97.6%, 특이도는 92.8%의 우수한 성능을 확인하였다.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.1
• /
• pp.92-97
• /
• 2009

Low power consumption is crucial for medical implantable devices. A low-power 4th-order band-pass Gm-C filter with distributed gain stage for the sensing stage of the implantable cardiac pacemaker is proposed. For the implementation of large-time constants, a floating-gate operational transconductance amplifier with current division is employed. Experimental results for the filter have shown a SFDR of 50 dB. The power consumption is below $1.8{\mu}W$, the power supply is 1.5 V, and the core area is $2.4\;mm{\times}1.3\;mm$. The filter was fabricated in a 1-poly 4-metal $0.35-{\mu}m$ CMOS process.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.2
• /
• pp.196-204
• /
• 2016

World Health Organization reported that heart-related diseases such as coronary artery stenoses show the highest occurrence rate which may cause heart attack. Using Computed Tomography angiography images will allow radiologists to detect and have intervention by creating 3D roadmapping of the vessels. However, it is often complex and difficult do reconstruct 3D vessel which causes very large amount of time and previous researches were studied to segment vessels more accurate automatically. Therefore, in this paper, Region Competition, Geodesic Active Contour (GAC), Multi-atlas based segmentation and Active Shape Model algorithms were applied to segment aortic root from CTA images and the results were analyzed by using mean Hausdorff distance, volume to volume measure, computational time, user-interaction and coronary ostium detection rate. As a result, Extracted 3D aortic model using GAC showed the highest accuracy but also showed highest user-interaction results. Therefore, it is important to improve automatic segmentation algorithm in future

• Progress in Medical Physics
• /
• v.24 no.4
• /
• pp.278-283
• /
• 2013

Breast cancer is the leading cause of cancer death in women worldwide and the number of women breast cancer patient was increased continuously. Most of breast cancer patient has suffered from unnecessary radiation exposure to heart, lung. Low radiation dose to the heart could lead to the worsening of preexisting cardiovascular lesions caused by radiation induced pneumonitis. Also, several statistical reports demonstrated that left-sided breast cancer patient showed higher mortality than right-sided breast cancer patient because of heart disease. In radiation therapy, Deep Inspiration Breath Hold (DIBH) technique which the patient takes a deep inspiration and holds during treatment and could move the heart away from the chest wall and lung, has showed to lead to reduction in cardiac volume and to minimize the unnecessary radiation exposure to heart during treatment. In this study, we investigated the displacement of heart using DIBH CT data compared to free-breathing (FB) CT data and radiation exposure to heart. Treatment planning was performed on the computed tomography (CT) datasets of 10 patients who had received lumpectomy treatments. Heart, lung and both breasts were outlined. The prescribed dose was 50 Gy divided into 28 fractions. The dose distributions in all the plans were required to fulfill the International Commission on Radiation Units and Measurement specifications that include 100% coverage of the CTV with ${\geq}95%$ of the prescribed dose and that the volume inside the CTV receiving >107% of the prescribed dose should be minimized. Scar boost irradiation was not performed in this study. Displacement of heart was measured by calculating the distance between center of heart and left breast. For the evaluation of radiation dose to heart, minimum, maximum and mean dose to heart were calculated. The present study demonstrates that cardiac dose during left-sided breast radiotherapy can be reduced by applying DIBH breathing control technique.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.568-570
• /
• 1999

복잡한 인체기관의 해부학적 형태 및 상대적 관계를 파악하기 위하여 단일 볼륨에 대한가시화 뿐 아니라 다중 볼륨에 대한 가시화가 요구된다. 본 논문에서는 특정기관의 표면을 추출하여 가시화하는 선택적 렌더링 방법과 투명도 가중치 혼합 방법을 이용한 다중 볼륨렌더링 방법을 제안한다. 해부학적 형태로부터 관심부위의 표면을 추출하여 가시화하는 선택적 렌더링 방법은 분할된 외곽선으로부터 거리변환을 통하여 거리볼륨을 생성하고 이를 렌더링하는 방법으로 거리볼륨을 이용함으로써 가시화시간을 가속화시킬 수 있으며, 다중 볼륨 렌더링 방법은 투명도 가중치 혼합방법을 사용한 렌더링 방법으로 심장의 해부학적 형태와 좌심실, 우심실 간의 혼합된 렌더링 결과를 제시한다. 본 제안방법은 단일 볼륨 렌더링의 한계를 극복하여 복잡한 해부학적 형태로부터 관심부위의 형태와 상대적 관계를 효과적으로 나타낼 수 있다.

• Journal of Veterinary Clinics
• /
• v.31 no.2
• /
• pp.112-116
• /
• 2014

A 2-month-old intact male Pitbull terrier (weighing 1.01 kg) were referred with primary complaints of severe abdominal distension, exercise intolerance, retarded growth, yellow nasal discharge and anorexia. Diagnostic imaging studies found enlarged right atrium partitioned by abnormal membrane, severe pulmonic systolic jets (5.66 m/s of peak velocity) and right-to-left blood shunt at the inter-atrial septum. Based on clinical and diagnostic findings, the case was diagnosed as cor triatriatum dexter complicated with severe pulmonic stenosis and right-to-left shunted patent foramen ovale. Either surgical or interventional therapy has not been attempted, because of unstable patient's condition. Using blood transfusion, oxygen supply and cardiac medications (i.e., sildenafil, spironolactone, enalapril), the dog was recovered.

• Journal of radiological science and technology
• /
• v.35 no.2
• /
• pp.133-139
• /
• 2012

For the examination of nuclear medicine, myocardial scan is a good method to evaluate a hemodynamic importance of coronary heart disease. but, the automatized qualitative measurement is additionally necessary to improve the decoding efficiency. we suggests the creation of cardiac three-dimensional model and model of three-dimensional cardiac thickness as a new measurement. For the experiment, cardiac reduced cross section was obtained from SPECT. Next, the pre-process was performed and image segmentation was fulfilled by level set. for the modeling of left cardiac thickness, it was realized by applying difference equation of two-dimensional laplace equation. As the result of experiment, it was successful to measure internal wall and external wall and three-dimensional modeling was realized by coordinate. and, with laplace formula, it was successful to develop the thickness of cardiac wall. through the three-dimensional model, defects were observed easily and position of lesion was grasped rapidly by the revolution of model. The model which was developed as the support index of decoding will provide decoding information to doctor additionally and reduce the rate of false diagnosis as well as play a great role for diagnosing IHD early.

• Journal of Chest Surgery
• /
• v.30 no.2
• /
• pp.146-151
• /
• 1997

Between December 1993 and March 1996, 75 patients had undergone ubannular procedures in mitral valve reconstruction. Their mean age was 45 years and they consisted of 28 males and 47 females. The cause of mitral disease in 75 patients were classified as follow : 29 cases were degenerative, 40 cases were rheumatic, 3 cases were congenital, 2 cases were infectious and 1 case was ischemic. Average number of mitral anatomical lesion per patient was 3.1 and we used average 1.5 procedures on subannular structure in mitral valve per patient. Subannular procedures were chordae shortening 21, chordae transfer 22, new chordae formation 20, papillary muscle splitting 33, shortening of papillary muscle 2. Intraoperative transesophageal echocardiography was carried out for providing an immediate and accurate assessment of the adequacy of the reconstruction. There was no operative death. Patients have been followed up from 2 to 29months, mean 12.5. There were two failures that necessitated reoperation. The mean functional class (NYHA) was 3.19 preoperative and improved to 1.12 postoperatively. After mitral valve repair, the patients were improved hemodynamic, echocardiographic data. In conclusion, subannular procedure in mitral valve repair when feasible is stable and safe with a low prevalence of reoperation.

• 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 the Korea Institute of Information and Communication Engineering
• /
• v.16 no.5
• /
• pp.1047-1054
• /
• 2012

Atrial fibrillation (AF) is the most common arrhythmia encountered in clinical practice, and its risk increases with age. Conventionally, the way of detecting AF was the time·frequency domain analysis of RR variability. However, the detection of ECG signal is difficult because of the low amplitude of the P wave and the corruption by the noise. Also, the time·frequency domain analysis of RR variability has disadvantage to get the details of irregular RR interval rhythm. In this study, we describe an atrial fibrillation pattern analysis based on symbolization and information entropy. We transformed RR interval data into symbolic sequence through differential partition, analyzed RR interval pattern, quantified the complexity through Shannon entropy and detected atrial fibrillation. The detection algorithm was tested using the threshold between 10ms and 100ms on two databases, namely the MIT-BIH Atrial Fibrillation Database.