• 분석과학
• /
• 제9권2호
• /
• pp.192-197
• /
• 1996

현재 사용되고 있는 생체용 금속재료로 스테인레스강(SUS 316), Co-Cr강, 순수 Ti, Ti-6Al-4V이 많이 사용되고 있으며 그 중에서도 특히 Ti이 각광을 받고 있다. 그러나 순수한 Ti은 생체적합성과 내식성은 좋은 반면 기계적 성질이 합금에 비해 뒤떨어지고, Ti-6Al-4V은 V의 세포독성이 지적되고 있어 이러한 문제를 해결하기 위해 세포독성이 없는 함금원소를 Ti에 첨가한 새로운 합금을 설계하였다. 그 중에서 Ti-20Zr-3Nb-3Ta-0.2Pd-1In과 Ti-5AI-4Zr-2.5Mo은 기계적 성질도 뛰어나고 우수한 전기화학적 부식특성을 가지고 있었다.

• Advances in nano research
• /
• 제12권2호
• /
• pp.185-195
• /
• 2022

Deep learning is another field of artificial intelligence (AI) utilized for computer aided diagnosis (CAD) and image processing in scientific research. Considering numerous mechanical repetitive tasks, reading image slices need time and improper with geographical limits, so the counting of image information is hard due to its strong subjectivity that raise the error ratio in misdiagnosis. Regarding the highest mortality rate of Lung cancer, there is a need for biopsy for determining its class for additional treatment. Deep learning has recently given strong tools in diagnose of lung cancer and making therapeutic regimen. However, identifying the pathological lung cancer's class by CT images in beginning phase because of the absence of powerful AI models and public training data set is difficult. Convolutional Neural Network (CNN) was proposed with its essential function in recognizing the pathological CT images. 472 patients subjected to staging FDG-PET/CT were selected in 2 months prior to surgery or biopsy. CNN was developed and showed the accuracy of 87%, 69%, and 69% in training, validation, and test sets, respectively, for T1-T2 and T3-T4 lung cancer classification. Subsequently, CNN (or deep learning) could improve the CT images' data set, indicating that the application of classifiers is adequate to accomplish better exactness in distinguishing pathological CT images that performs better than few deep learning models, such as ResNet-34, Alex Net, and Dense Net with or without Soft max weights.

• 한국인터넷방송통신학회논문지
• /
• 제22권3호
• /
• pp.133-138
• /
• 2022

디지털 방사선 검사장 치는 인간의 생명을 다루는 의료장치로 안정성과 고신뢰성이 필요하지만 이러한 시스템은 현재 최첨단 기술로 일본을 비롯한 유럽제품에 의해서 국내시장은 거의 점유된 실정이다. 따라서 상당한 부분 값비싼 수입품에 의존하고 있는 의료기기의 국산품 대체는 물론, 보다 경제적이고 조작하기 쉬운 사용자 위주의 제품을 개발, 정확한 진단을 이끄는 장치의 생산을 위한 연구와 개발이 필요하다. 특별히 디지털 X-ray 시스템 중에서 전동기 구동기술과 기계장치 개발 관련 메카트로닉스 기술은 국내에 어느 정도 성숙되어 있는 단계로 본 논문에서는 디지털 방사선 검사 장치(DR)의 전동기 서보 시스템 설계를 통하여 제어기법과 성능을 확인하고자 한다. 본 논문에서는 촬영용도에 부합하는 디지털 방사선 검사용 AC 서보전동기의 선정과 변환장치 및 제어기법을 적용하여 성능을 확인하고 문제점을 개선함에 있다.

• Korean Journal of Radiology
• /
• 제24권9호
• /
• pp.849-859
• /
• 2023

Objective: The prognostic value of the volume and density of skeletal muscles in the abdominal waist of patients with colon cancer remains unclear. This study aimed to investigate the association between the automated computed tomography (CT)-based volume and density of the muscle in the abdominal waist and survival outcomes in patients with colon cancer. Materials and Methods: We retrospectively evaluated 474 patients with colon cancer who underwent surgery with curative intent between January 2010 and October 2017. Volumetric skeletal muscle index and muscular density were measured at the abdominal waist using artificial intelligence (AI)-based volumetric segmentation of body composition on preoperative pre-contrast CT images. Patients were grouped based on their skeletal muscle index (sarcopenia vs. not) and muscular density (myosteatosis vs. not) values and combinations (normal, sarcopenia alone, myosteatosis alone, and combined sarcopenia and myosteatosis). Postsurgical disease-free survival (DFS) and overall survival (OS) were analyzed using univariable and multivariable analyses, including multivariable Cox proportional hazard regression. Results: Univariable analysis showed that DFS and OS were significantly worse for the sarcopenia group than for the non-sarcopenia group (P = 0.044 and P = 0.003, respectively, by log-rank test) and for the myosteatosis group than for the non-myosteatosis group (P < 0.001 by log-rank test for all). In the multivariable analysis, the myosteatotic muscle type was associated with worse DFS (adjusted hazard ratio [aHR], 1.89 [95% confidence interval, 1.25-2.86]; P = 0.003) and OS (aHR, 1.90 [95% confidence interval, 1.84-3.04]; P = 0.008) than the normal muscle type. The combined muscle type showed worse OS than the normal muscle type (aHR, 1.95 [95% confidence interval, 1.08-3.54]; P = 0.027). Conclusion: Preoperative volumetric sarcopenia and myosteatosis, automatically assessed from pre-contrast CT scans using AI-based software, adversely affect survival outcomes in patients with colon cancer.

• 대한의용생체공학회:의공학회지
• /
• 제45권4호
• /
• pp.139-147
• /
• 2024

This study enhances AI algorithms for extracting spinal regions from Whole Spine X-rays, aiming for higher accuracy while minimizing learning and detection times. Whole Spine X-rays, critical for diagnosing conditions such as scoliosis and kyphosis, necessitate precise differentiation of spinal contours. The conventional manual methodology encounters challenge due to the overlap of anatomical structures, prompting the integration of AI to overcome these limitations and enhance diagnostic precision. In this study, 1204 AP and 500 LAT Whole Spine X-ray images were meticulously labeled, spanning the third cervical to the fifth lumbar vertebrae. We based our efforts on the HR-Net algorithm, which exhibited the highest accuracy, and proceeded to simplify its network architecture and enhance the block structure for optimization. The optimized HR-Net algorithm demonstrates an improvement, increasing accuracy by 2.98% for the AP dataset and 1.59% for the LAT dataset compared to its original formulation. Additionally, the modification resulted in a substantial reduction in learning time by 70.06% for AP images and 68.43% for LAT images, along with a decrease in detection time by 47.18% for AP and 43.07% for LAT images. The time taken per image for detection was also reduced by 47.09% for AP and 43.07% for LAT images. We suggest that the application of the proposed HR-Net in this study can lead to more accurate and efficient extraction of spinal regions in Whole Spine X-ray images. This can become a crucial tool for medical professionals in the diagnosis and treatment of spinal-related conditions, and it will serve as a foundation for future research aimed at further improving the accuracy and speed of spinal region segmentation.

• Clinical and Experimental Reproductive Medicine
• /
• 제21권3호
• /
• pp.253-259
• /
• 1994

A clinical investigation was undertaken on primary male infertility patients of recent 5 years. The results obtained were as follow: 1. Suspective etiologic factors were: 1) testicular failure, 36.1 %; 2) varicocele, 18.7%; 3) endocrine abnormality, 13.5%; 4) obstruction, 13.5%; 5) idiopathic, 10.9%; 6) cryptorchidism, 2.6%; 7) necrospermia, 0.9%. 2. On semen analyses, azoospermia was found in 55.8%, single abnormal parameter in 21.5 %, and multiple/all abnormal parameter in 22.7% of the 163 cases. 3. For the evaluation of the sensitivity and specificity of noninvasive variables in predict in obstruction as the cause of azoospermia in patient who had undergone testicular biopsy, the testicular size and serum follicle-stimulating hormone(FSH) level revealed 100% of sensitivity. 4. Among the 43 patients with a testicular biopsy confirmed diagnosis there was a significant difference in testicular size, ejaculate volume(p<0.0001) and serum FSH(p<0.0001) between patients with testicular failure and those with ductal obstruction. 5. Of 93 treated patients with primary male infertility, 42 were managed by medical treatment including endocrine treament, retrograde ejaculation treatment, infection treatment and observation; 29 were managed by surgical treatment including varicocelectomy, vasovasostomy, vasoepididymostomy and TUR of ejaculatory duct; 20 were managed by sperm preparation treatment including artificial insemination(AI), electroejaculation plus AI and vibration ejaculation plus AI ; 2 were managed by microscopic epididymal sperm aspiration plus IVF, repectively. 6. 42 patients who could be followed-up, 21 patients(50%) impregnated their wives.

• 한국식품과학회지
• /
• 제24권2호
• /
• pp.142-148
• /
• 1992

95종의 식용 혹은 약용식물로부터 에탄올과 물을 용매로 하여 얻은 126종의 추출물을 괌유, 돈지 및 대두유에 첨가하여 Rancimat으로 항산화 효과를 비교하였다. 항산화 효과가 인정되면서 추출 수율이 높은 민들레, 질경이, 붉나무, 택란엽, 황기, 포공영 등 6종을 1차 선발하여 각 추출물을 농도별로 실험한 결과 붉나무 추출물이 팜유 및 돈지의 유도기간을 연장시키는데 우수한 효과를 보였다. 붉나무 추출물을 팜유에 600ppm 첨가시 AI(Antioxidant index, 각 항산화제 첨가구의 유도기간을 무첨가구의 유도기간으로 나눈 값)는 1.35였고, 돈지에서는 AI가 3.03으로 돈지에 효과가 우수하였다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권6호
• /
• pp.243-250
• /
• 2023

흉부 X-ray 영상은 폐와 심장을 검사하는 방사선 검사이며 특히, 폐 질환을 진단하는 데 널리 사용되고 있다. 이러한 흉부 X-ray의 품질은 의사의 진단에 영향을 줄 수 있으므로 품질을 평가하는 과정이 필수적으로 거쳐야 하는데, 이 과정은 영상의학과 전문의의 주관이 개입될 수 있고, 수작업으로 이루어지기 때문에 많은 시간과 비용이 소모된다. 또한, 이러한 품질평가는 X-ray 영상의 특징과 사용 목적에 따라 일반적인 품질평가와는 다른 평가 요소가 필요하다. 따라서 본 논문에서는 X-ray 영상에서 검출되는 장기의 해상도, ,해부학적인 구조, 균형 등을 고려하여 임상 현장에서 사용되는 흉부 X-ray 영상 화질 평가 가이드라인을 적용하여 품질요소를 5가지(인공음영, 포함범위, 환자자세, 흡기정도, 그리고 투과상태)로 나누고 이를 자동화하는 도구를 제안한다. 제안하는 도구는 수작업으로 품질평가를 진행하는 본래의 방식 대비 소요 시간과 비용을 줄여주고, 더 나아가 흉부 X-ray를 이용한 학습 모델 개발에 높은 품질의 학습데이터를 선별하는 과정에도 사용될 수 있다.

• 한국산업정보학회논문지
• /
• 제29권4호
• /
• pp.25-34
• /
• 2024

본 논문은 반려견의 피부질환 발병 여부와 부위를 추론하기 위해서 딥러닝 기반 U-Net 모델을 학습하여 이미지 촬영을 통한 반려견의 피부병 발병 여부와 추론되는 병명을 제공하는 애플리케이션을 개발하였다. U-Net은 의료영상 분야에서 주로 사용되는 영역 분할(Image Segmentation) 기반 학습 모델로써 폴리곤 형태의 특정 이미지 영역을 구분하는 데 효과적이다. 따라서 반려견의 피부 이미지에서 병변 영역 식별에 활용할 수 있다. 본 논문에서는 반려견의 6가지 주요 피부질환을 클래스로 정의하고 이를 분별하는 U-Net 모델을 학습시켰다. 이를 모바일 앱으로 구현하여 간단한 카메라 촬영으로 병변 분석과 예측 작업을 수행하여 결과를 제공한다. 이를 통해서 반려인들은 반려동물의 건강 상태를 관찰하고 조기 진단에 도움이 되는 정보를 얻을 수 있다. 이와 같이 딥러닝을 통해서 반려동물 건강관리에 신속하고 정확한 진단 도구를 제공함으로써 가정에서도 손쉽게 이용할 수 있는 서비스 개발에 중요한 의미를 두고 있다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권19호
• /
• pp.8143-8147
• /
• 2014

To investigate the expression intensity and prognostic significance of TGF-${\beta}1$ protein in non-small cell lung cancer (NSCLC), immunohistochemistry was carried out in 194 cases of NSCLC and 24 cases of normal lung tissues by SP methods. The PU (positive unit) value was used to assess the TGF-${\beta}1$ protein expression in systematically selected fields under the microscope with Leica Q500MC image analysis. We found that the TGF-${\beta}1$ PU value was nearly two-fold higher in NSCLC than in normal lung tissues (p=0.000), being associated with TNM stages (p=0.000) and lymph node metastases (p=0.000), but not to patient age, gender, smoking history, tumor differentiation, histological subtype and tumor location (P>0.05). Univariate analysis indicated that patients with high TGF-${\beta}1$ protein expression and lymph node metastases demonstrated a poor prognosis (both p=0.000,). Multivariate analysis showed that TGF-${\beta}1$ protein expression (RR = 2.565, p=0.002) and lymph node metastases (RR=1.874, p=0.030) were also independent prognostic factors. Thus, TGF-${\beta}1$ protein expression may be correlated to oncogenesis and serve as an independent prognostic biomarker for NSCLC.