• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.4
• /
• pp.325-334
• /
• 2001

It is shown that the multiscale prewhitening matched filter for detecting Gaussian objects in Markov noise can be implemented by the undecimated wavelet transform with a biorthogonal spline wavelet. If the object to be detected is Gaussian shaped and its scale coincides with one of those computed by the wavelet transform, and if the background noise is truly Markov, then optimum detection is realized by thresholding the appropriate details image. Our detection algorithm is applied to the digitized mammograms for detecting microcalcifications. However, microcalcifications are not exactly Gaussian shaped and its background noise may not be Markov. In order to campensate for these discrepancy, Hotelling observer is employed, which is applied to feature vectors comprised of 3-octave wavelet coefficients.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.10
• /
• pp.4578-4589
• /
• 2011

The technologies of image acquisition, display, and storage of the breast have been developed in their specialized fields in recent years. The image acquisition system is a device that absorbs and stores images after examining breast tissue using X-ray. Due to the specificity and sensitivity of imaging, the early detection of breast cancer is feasible. In this paper, the current technologies for digital mammography are reviewed, and we propose a digital mammography and evaluate the performance of the implemented system.

• Asian Oncology Nursing
• /
• v.7 no.1
• /
• pp.79-89
• /
• 2007

연구 목적: 1980년대 이후 미국 여성들의 유방암 조기 진단을 위한 방사선 검진율은 급속히 증가하였음에도 불구하고 유색 인종의 여성들은 여전히 조기 검진의 혜택을 받지 못하고 있다. 유색인종 여성들의 낮은 검진율을 설명하기 위해 여러 건강행위이론을 이용한 관련 요인들이 연구되어 왔다. 이 논문은 미국 보건 의료관련 연구에서 가장 많이 쓰이는 다섯 건강행위 이론을 유색 인종 여성, 특히 한국 이민 여성들의 유방암 조기검진 이행에 적용하기 위해 사회문화적 적합성을 평가하기 위해 고안되었다. 연구 방법: 네 종류의 데이터 베이스(CINAHL, MEDLINE, PsycINFO, Sociological Abstracts)를 이용한 심층적 문헌 고찰을 통해 각각의 이론으로 유방암 조기 검진을 설명한 연구들을 모두 분석하였다. 연구 결과: 각 이론들의 배경, 주요 요인, 그리고 유색인종의 유방암 조기 검진에서의 적용 연구 등을 분석하였다. 결론: 서양 문화권 속에서 개발된 각 이론들이 한국적 정서와 행동을 설명하는데 명확한 한계가 있으며 이러한 한계를 극복하기 위해서는 기존의 이론들을 면밀하게 재분석하여 한국적 특성을 담아낼 수 있는 새로운 이론의 도출이 요구된다.

• Journal of Sensor Science and Technology
• /
• v.13 no.1
• /
• pp.56-65
• /
• 2004

In this paper, we proposed the detection algorithm of microcalcification based on region growing method with contrast and edge sharpness in digital X-ray mammographic images. We extracted the local maximum pixel and watershed regions by using watershed algorithm. Then, we used the mean slope between local maximum and neighborhood pixels to extract microcalcification candidate pixels among local maximum pixels. During increasing threshold value to grow microcalcification region, at the maximum threshold value of the contrast and edge sharpness, the microcalcification area is decided. The regions of which area of grown candidate microcalfication region is larger than that of watershed region are excluded from microcalcifications. We showed the diagnosis algorithm can be used to aid diagnostic-radiologist in the early detection breast cancer.

• Journal of Biomedical Engineering Research
• /
• v.27 no.5
• /
• pp.291-299
• /
• 2006

A Computer-Aided Diagnosis system has been examined to reduce the effort of radiologist. In this paper, we propose the algorithm using Support Vector Machine(SVM) classifier to discriminate whether microcalcifications are malignant or benign tumors. The proposed method to detect microcalcifications is composed of two detection steps each of which uses SVM classifier. The coarse detection step finds out pixels considered high contrasts comparing with neighboring pixels. Then, Region of Interest(ROI) is generated based on microcalcification characteristics. The fine detection step determines whether the found ROIs are microcalcifications or not by merging potential regions using obtained ROIs and SVM classifier. The proposed method is specified on Korean mammogram database. The experimental result of the proposed algorithm presents robustness in detecting microcalcifications than the previous method using Artificial Neural Network as classifier even when using small training data.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1363-1369
• /
• 2018

Breast cancer is one of the most common cancers in women worldwide. In Korea, breast cancer is most common cancer in women followed by thyroid cancer. The purpose of this study is to evaluate the possibility of using deep - run model for segmentation of breast masses and to identify the best deep-run model for breast mass segmentation. In this study, data of patients with breast masses were collected at Asan Medical Center. We used 596 images of mammography and 596 images of gold standard. In the area of interest of the medical image, it was cut into a rectangular shape with a margin of about 10% up and down, and then converted into an 8-bit image by adjusting the window width and level. Also, the size of the image was resampled to $150{\times}150$. In Deconvolution net, the average accuracy is 91.78%. In U-net, the average accuracy is 90.09%. Deconvolution net showed slightly better performance than U-net in this study, so it is expected that deconvolution net will be better for breast mass segmentation. However, because of few cases, there are a few images that are not accurately segmented. Therefore, more research is needed with various training data.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.9
• /
• pp.4289-4294
• /
• 2012

While the incidence of breast cancer (BC) has been relatively low in Asian countries, it has been rising rapidly in Taiwan. Within the last decade, it has replaced cervical cancer as the most diagnosed cancer site for women. Nevertheless, there is a paucity of studies reporting the attitudes and practices of breast cancer screening among Chinese women. The aim of this study is to assess Taiwanese women's knowledge of and attitudes toward BC screening and to identify potential factors that may influence screening behavior. The study population consisted of a sample of 434 Taiwanese women aged 40 and older. Despite access to universal health care for Taiwanese women and the fact that a majority of the women had heard of the breast cancer screening (mammogram, clinical breast exams, etc.), the actual utilization of these screening modalities was relatively low. In the current study, the majority of women had never had mammograms or ultrasound in the past 5 years. The number one most reported barriers were "no time," "forgetfulness," "too cumbersome," and "laziness," followed by the perception of no need to get screened. In addition, the results revealed several areas of misconceptions or incorrect information perceived by study participants. Based on the results from the regression analysis, significant predictors of obtaining repeated screening modalities included age, coverage for screening, barriers, self-efficacy, intention, family/friends diagnosed with breast cancer. The findings from the current study provide the potential to build evidence-based programs to effectively plan and implement policies in order to raise awareness in breast cancer and promote BC screening in order to optimize health outcomes for women affected by this disease.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.22
• /
• pp.9817-9822
• /
• 2014

Background: Breast cancer is a serious health problem. Early detection is crucial for optimal treatment and reducing mortality. Objective: The aim of this study was to evaluate health beliefs concerning performance of breast self- examination (BSE) and mammography in a sample of Iranian female health workers. Materials and Methods: This cross-sectional study was performed among 441 female health care workers (physicians=88, nurses=163, midwives=38, officers=68, and others=84) in 3 different health centers in Yazd, Iran. Data were collected using a self administered questionnaire which included demographic characteristics and thenPersian version of the Champion's Health Belief Model Scale (CHBMS). Results: The mean age of the participants was $34.7{\pm}13.7$. It was found that 41.9% of the workers performed BSE in the past and 14.9% of them regularly, but only 10.6% of them had undergone a mammogram. Perceived barriers to BSE (F=6.351, P=0.021) and mammography (F=5.214, p=0.022) were significantly higher in officers than physicians, nurses or midwives. Perceived barriers were lower among those who had performed BSE and mammography, but not significant (p=0.34 and p=0.56, respectively). Furthermore, perceived susceptibility and perceived benefits of the workers who had BSE and mammography were significantly higher than who did not (p<0.05). Perceived seriousness was not a significant variable in BSE and mammography (p=0.71 and p=0.43, respectively). Conclusions: The health beliefs of health workers concerning the perceived susceptibility of breast cancer and the perceived benefits BSE and mammography significantly impact their screening practices.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.1
• /
• pp.117-120
• /
• 2013

Background: Breast cancer is an increasing health problem in India. Screening for early detection should lead to a reduction in mortality from the disease. It is known that motivation by nurses influences uptake of screening methods by women. This study aimed to investigate knowledge of breast cancer risk factors & early detection methods and the practice of screening among nurses in Indira Gandhi Medical College, Shimla, Himachal Pradesh. Materials and Methods: A cross-sectional study was conducted using a self-administered questionnaire to assess the knowledge of breast cancer risk factors, early detection methods and practice of screening methods among 457 nurses working in a Indira Gandhi Medical College, Shimla-H.P. Chi square test, Data was analysed using SPSS version 16. Test of significance used was chi square test. Results: The response rate of the study was 94.9%. The average knowledge of risk factors about breast cancer of the entire population is 49%. 10.5% of nurses had poor knowledge, 25.2% of the nurses had good knowledge, 45% had very good knowledge and 16.3% of the nurses had excellent knowledge about risk factors of breast cancer and early detection methods. The knowledge level was significantly higher among BSC nurses than nurses with Diploma. 54% of participants in this study reportedly practice BSE at least once every year. Less than one-third reported that they had CBE within the past one year. 7% ever had mammogram before this study. Conclusions: Results from this study suggest the frequent continuing medical education programmes on breast cancer at institutional level is desirable.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.15
• /
• pp.6347-6352
• /
• 2015

Background: Breast malignancies are one of the leading causes of deaths in females worldwide. There are a number of risk factors associated with breast cancer but in Karachi Pakistan there are insufficient data available. Materials and Methods: A case control study was conducted on females in age group between 30-80 years. This study was accomplished by retrospective data collection in Aga Khan University Hospital Karachi, Pakistan. A total of 108 females with primary malignancy of breast were included along with 108 matched controls. Relationship of various factors with disease was studied using logistic regression to calculate odds ratios with 95 % confidence intervals. Results: A total of 14 variables were analyzed and based on and 7 were found to be risk factors: old age, family history of breast cancer, family history of other carcinomas, personal history of breast carcinoma, early age of menarche, older age of mother at first delivery and lower number of children. Five factors, parity, breast feeding, history of oral contraceptive pills intake, past history of oophorectomy and hysterectomy showed protective associations. One variable, use of hormonal replacement therapy, showed a controversial link and one other, marital status, was not significant in this study. Conclusions: It is concluded that most of the well-known risk factors for breast cancer are also associated with the disease in the female population of Karachi, Pakistan. High risk patients should be the focus with the help of this study so that screening can be more effective for early diagnosis before clinically evident breast malignancy.