• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.367-369
• /
• 2005

In this paper, we present a new method for the detection of spiculation on digital mammograms. Traditional methods have defects; sensitive to noise, fixed size processing, and long processing time, however, the proposed method has merits; not sensitive to noise, adaptive size processing, and fast processing time. Experimental results show that the spiculation detection performance of the proposed method is improved much compared to the other methods.

• 한국의학물리학회:학술대회논문집
• /
• 한국의학물리학회 1999년도 Japanese Journal of Medical Physics
• /
• pp.287-288
• /
• 1999

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권11호
• /
• pp.4723-4726
• /
• 2014

Background: Breast cancer is the second most common cancer in the world and by far the most frequent cancer among women. Objective: The present study was undertaken to assess the awareness of breast cancer warning signs and screening methods among the women of Pokhara valley, Nepal. Materials and Methods: A cross-sectional questionnaire survey was carried out in a community setting with the female population. The questionnaire was administered in face-to-face interviews by trained research assistants. Results: Nepalese women demonstrated poor awareness of warning signs like a breast lump, lump under the armpit, bleeding or discharge from the nipple, pulling of the nipple, changes in the position of the nipple, nipple rash, redness of the breast skin, changes in the size of the breast or nipple, changes in the shape of the breast or nipple, pain in the breast or armpit, and dimpling of the breast skin. While 100% of nurses were aware about breast self-examination(BSE), mammography and warning signs of breast cancer. Levels of knowledge were significantly poorer in women with other occupations. Graduates were more aware about BSE, mammogram and warning signs of breast cancer compared to those with other educational levels. Conclusions: The findings indicated that the level of awareness of breast cancer, including knowledge of warning signs and BSE, is sub-optimal among Nepalese women.

• 전자공학회논문지SC
• /
• 제43권5호
• /
• pp.80-88
• /
• 2006

본 논문에서는 치밀 유방영상에서 mass형 암 검출을 목적으로 하는 시스템을 개발한다. 본 논문에서 제시하는 방법과 기존의 방법과의 차이점은 1) mass 영역의 중심의 위치와 반경을 영상신호의 불규칙성에 영향을 받지 않고 안정적으로 결정하는 방법을 제시하고, 2) mass형 유방암 영상에 적용하기 적합한 방사형 필터를 개발하며, 3) mass형 유방암 검출을 위해 mass 경계선의 불규칙성, mass 영역 중심부의 homogeneity, mass 영역의 이심율에 근거하여 다중 특징 함수 개발에 있다. 본 논문에서 제안한 시스템은 기존의 시스템보다 치밀 유방에 적용하였을 때 false alarm은 영상 당 1개 정도 높으나 true alarm 비율은 10%이상 향상 되었다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권17호
• /
• pp.7309-7316
• /
• 2014

Background: While many researchers often use a theoretical framework for mammogram repeat interventions, it seems they do not apply an identified mediation analysis method. The aim of this study was to determine the mediators of mammogram replication behavior in two tailored interventions for non-adherent Iranian women. Materials and Methods: A sample population of 184 women over 50 years old in Sanandaj, Iran, was selected for an experiment. Participants were randomly allocated into one of the three conditions: 1) an intervention based on the Health Belief Model (HBM) 2) an intervention based on an integration of the HBM and selected constructs from the Theory of Planned Behavior (TPB), and 3) a control group. Constructs were measured before the intervention, and after a 6-month follow-up. Results: Perceived self-efficacy, behavioral control, and subjective norms were recognized as mediators in the HBM and selected constructs from the TPB intervention. Perceived susceptibility, severity, barriers, self-efficacy and behavioral control met the criteria for mediation in the HBM intervention. Conclusions: This study was successful in establishing mediation in a sample of women. Our findings enrich the literature on mammography repeat, indicating key intervention factors, and relegating redundant ones in the Iranian populations. The use of strategies to increase mammography repeat, such HBM and TPB constructs is suggested to be important for maintaining a screening behavior, once the behavior has been adopted.

• 대한전자공학회논문지SP
• /
• 제38권6호
• /
• pp.721-734
• /
• 2001

제안된 연구는 유방촬영영상(Mammogram)에서 종양의 추출에 관한 연구로서, 맘모그램의 특성을 파악하여 종양에 대한 자동적인 추출을 시행하였다. 처리과정에서 동질성 특성을 이용하여 정상조직인 Cooper's ligament로부터 종양조직을 분리하였고 고밀도 후보에 대한 처리방법으로 다중 문턱값 적용방식을 사용하였다. 추출된 부분을 8-연결성 관계를 사용하여 1차 후보를 추출하였다. 1차 추출된 각 후보에 대하여 명암값을 지형적 높이정보로 해석한 이분화영상으로 표현하여 이중원형성과 분포 비율을 비교하는 방법을 통하여 2차 후보 추출을 시행하였다. 최종적인 종양의 결정은 공간원형성 판단을 위한 반구 형태의 템플리트를 생성하여 비교하는 방법을 이용하여 후보에 대한 순위를 결정하였다. 알고리즘을 실제 종양이 확진된 환자의 136 예에 적용하여 추출된 결과와 전문의가 지적한 결과를 비교하여 93.38%의 민감도를 얻었으며, 최종추출 단계에서는 124 예에서 1 순위로 종양을 추출하여 97.63%의 FP(False positive)의 결과를 나타냈다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제13권7호
• /
• pp.3443-3449
• /
• 2012

Introduction: Despite health education efforts to educate women on breast cancer and breast cancer screening modalities, the incidence of breast cancer and presentation at an advanced stage are still a problem in Malaysia. Objectives: To determine factors associated with the uptake of breast cancer screening among women in the general population. Methods: This pre-intervention survey was conducted in a suburban district. All households were approached and women aged 20 to 60 years old were interviewed with pre-tested guided questionnaires. Variables collected included socio-demographic characteristics, knowledge on breast cancer and screening practice of breast cancer. Univariate and multivariate analysis were performed. Results: 41.5% of a total of 381 respondents scored above average; the mean knowledge score on causes and risks factors of breast cancer was 3.41 out of 5 (SD1.609). 58.5% had ever practiced BSE with half of them performing it at regular monthly intervals. Uptake of CBE by nurses and by doctors was 40.7% and 37.3%, respectively. Mammogram uptake was 14.6%. Significant predictors of BSE were good knowledge of breast cancer (OR=2.654, 95% CI: 1.033-6.816), being married (OR=2.213, 95% CI: 1.201-4.076) and attending CBE (OR=1.729, 95% CI: 1.122-2.665). Significant predictors for CBE included being married (OR=2.161, 95% CI: 1.174-3.979), good knowledge of breast cancer (OR=2.286, 95% CI: 1.012-5.161), and social support for breast cancer screening (OR=2.312, 95% CI: 1.245-4.293). Women who had CBE were more likely to undergo mammographic screening of the breast (OR=5.744, 95% CI: 2.112-15.623), p<0.005. Conclusion: CBE attendance is a strong factor in promoting BSE and mammography, educating women on the importance of breast cancer screening and on how to conduct BSE. The currently opportunistic conduct of CBE should be extended to active calling of women for CBE.

• 융합신호처리학회논문지
• /
• 제15권2호
• /
• pp.24-29
• /
• 2014

X-선 유방촬영술은 유방암의 조기발견을 위해 가장 일반적으로 이용되고 있다. 유방암의 조기 발견과 진단의 효율성을 증가시키기 위하여 많은 영상향상 방법들이 연구개발 되었다. 본 논문은 디지털 맘모그램을 위하여 라플라시안 피라미드에서 대비척도를 이용한 다중 스케일 대비 향상 방법을 제안한다. 제안한 방법은 입력 영상을 가우시안 피라미드와 라플라시안 피라미드로 분해하고, 분해된 다해상도 영상의 피라미드 계수들은 저주파수 성분들과 고주파수 성분들의 비율로 대역 제한된 국부 대비척도를 정의한다. 대비 향상을 위하여 정의된 대비척도를 이용하여 분해된 피라미드 계수들을 수정하고, 수정된 계수들로 피라미드 복원 과정을 거처 최종 향상된 영상을 얻는다. 제안된 방법의 성능은 실험을 통하여 기존 방법들과 향상결과를 비교하고, 대비 측정 알고리즘을 이용한 정량적인 평가결과에서 우수한 성능을 확인하였다.

• 한국방사선학회논문지
• /
• 제8권1호
• /
• pp.27-33
• /
• 2014

건강에 대한 관심의 증대로 의료영상이 빠르게 증가하고 있으며, 컴퓨터 기술의 발전으로 의료영상의 디지털화가 빠르게 진전되어 PACS가 의료현장에 도입되었다. 이러한 현상에 의한 의료영상 생산의 증가는 의료영상을 판독하여야 하는 영상의학과 전문의의 업무량을 증가하게 하였다. 이러한 추세에 따라 컴퓨터를 이용한 보조 진단의 필요성이 대두되어 의료영상 판독 분야에 CAD라는 용어가 생겨나게 되었다. 본 연구에서는 디지털 X-선 유방촬영장치에 의하여 획득된 영상의 판독을 위한 CAD 알고리즘을 제안하였다. 제안된 알고리즘을 Visual C++로 프로그램하여 실험하였다. 본 연구에 사용한 일곱 샘플영상을 CAD 알고리즘으로 실행한 결과 다섯 샘플의 결과는 양성종양 및 유방암으로 확인되었고 두 샘플 영상은 error처리 되었다. 본 연구에서 제시한 알고리즘과 이를 구현한 프로그램을 이용한다면 판독업무에 많은 도움이 될 것이며, 유방암의 조기발견에 크게 기여할 것으로 사료된다.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.420-426
• /
• 2022

Breast cancer is among the cancers that may be healed as the disease diagnosed at early times before it is distributed through all the areas of the body. The Automatic Analysis of Diagnostic Tests (AAT) is an automated assistance for physicians that can deliver reliable findings to analyze the critically endangered diseases. Deep learning, a family of machine learning methods, has grown at an astonishing pace in recent years. It is used to search and render diagnoses in fields from banking to medicine to machine learning. We attempt to create a deep learning algorithm that can reliably diagnose the breast cancer in the mammogram. We want the algorithm to identify it as cancer, or this image is not cancer, allowing use of a full testing dataset of either strong clinical annotations in training data or the cancer status only, in which a few images of either cancers or noncancer were annotated. Even with this technique, the photographs would be annotated with the condition; an optional portion of the annotated image will then act as the mark. The final stage of the suggested system doesn't need any based labels to be accessible during model training. Furthermore, the results of the review process suggest that deep learning approaches have surpassed the extent of the level of state-of-of-the-the-the-art in tumor identification, feature extraction, and classification. in these three ways, the paper explains why learning algorithms were applied: train the network from scratch, transplanting certain deep learning concepts and constraints into a network, and (another way) reducing the amount of parameters in the trained nets, are two functions that help expand the scope of the networks. Researchers in economically developing countries have applied deep learning imaging devices to cancer detection; on the other hand, cancer chances have gone through the roof in Africa. Convolutional Neural Network (CNN) is a sort of deep learning that can aid you with a variety of other activities, such as speech recognition, image recognition, and classification. To accomplish this goal in this article, we will use CNN to categorize and identify breast cancer photographs from the available databases from the US Centers for Disease Control and Prevention.