Browsing by Subject "mammography"

Now showing 1 - 2 of 2

Open Access
A comprehensive methodology for determining the most informative mammographic features
(2013) Wu, Y.; Alagoz O.; Ayvaci, M.U.S.; Munoz Del Rio, A.; Vanness, D.J.; Woods, R.; Burnside, E.S.
This study aims to determine the most informative mammographic features for breast cancer diagnosis using mutual information (MI) analysis. Our Health Insurance Portability and Accountability Act-approved database consists of 44,397 consecutive structured mammography reports for 20,375 patients collected from 2005 to 2008. The reports include demographic risk factors (age, family and personal history of breast cancer, and use of hormone therapy) and mammographic features from the Breast Imaging Reporting and Data System lexicon. We calculated MI using Shannon's entropy measure for each feature with respect to the outcome (benign/malignant using a cancer registry match as reference standard). In order to evaluate the validity of the MI rankings of features, we trained and tested naïve Bayes classifiers on the feature with tenfold cross-validation, and measured the predictive ability using area under the ROC curve (AUC). We used a bootstrapping approach to assess the distributional properties of our estimates, and the DeLong method to compare AUC. Based on MI, we found that mass margins and mass shape were the most informative features for breast cancer diagnosis. Calcification morphology, mass density, and calcification distribution provided predictive information for distinguishing benign and malignant breast findings. Breast composition, associated findings, and special cases provided little information in this task. We also found that the rankings of mammographic features with MI and AUC were generally consistent. MI analysis provides a framework to determine the value of different mammographic features in the pursuit of optimal (i.e., accurate and efficient) breast cancer diagnosis. © 2013 Society for Imaging Informatics in Medicine.
Open Access
A simulation model for breast cancer epidemiology in Turkey
(2014) Ada, Kumru
Breast cancer has a vital importance in women's life. In the world, breast cancer incidence and mortality rates are increasing. Considering the burden of disease, in 2012 1.67 million women got breast cancer and about 522,000 women died due to breast cancer. With this numbers, breast cancer ranks as the most common cancer among women in the world and the fifth cause of death from cancer overall. Breast cancer has a high incidence and mortality rates especially in developing countries, where late diagnosis of cancer is also increasing the disease burden. Lack of knowledge of the exact causes of breast cancer increases the importance of early detection. The most effective way of early detection is to apply mammography screening. Screening the accurate target population increases the rate of early detection of breast cancer and lessens the economic and health burden of disease. In this study, two simulation models were constructed in order to analyze the population-based mammography screening programs for Turkey. The first model was run for 10 years for validation purpose while the second one was run for the women born in 1980 during their lifetime to analyze several screening programs. The screening programs differ from each other in terms of beginning and final age of screening and screening frequency. Costs and health outcomes of the screening policies were examined and non-dominated screening policies are determined according to these performance measures.