A comprehensive methodology for determining the most informative mammographic features
dc.citation.epage | 947 | en_US |
dc.citation.issueNumber | 5 | en_US |
dc.citation.spage | 941 | en_US |
dc.citation.volumeNumber | 26 | en_US |
dc.contributor.author | Wu, Y. | en_US |
dc.contributor.author | Alagoz O. | en_US |
dc.contributor.author | Ayvaci, M.U.S. | en_US |
dc.contributor.author | Munoz Del Rio, A. | en_US |
dc.contributor.author | Vanness, D.J. | en_US |
dc.contributor.author | Woods, R. | en_US |
dc.contributor.author | Burnside, E.S. | en_US |
dc.date.accessioned | 2016-02-08T09:35:03Z | |
dc.date.available | 2016-02-08T09:35:03Z | |
dc.date.issued | 2013 | en_US |
dc.department | Department of Industrial Engineering | en_US |
dc.description.abstract | 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. | en_US |
dc.description.provenance | Made available in DSpace on 2016-02-08T09:35:03Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2013 | en |
dc.identifier.doi | 10.1007/s10278-013-9588-5 | en_US |
dc.identifier.issn | 0897-1889 | |
dc.identifier.uri | http://hdl.handle.net/11693/20778 | |
dc.language.iso | English | en_US |
dc.relation.isversionof | http://dx.doi.org/10.1007/s10278-013-9588-5 | en_US |
dc.source.title | Journal of Digital Imaging | en_US |
dc.subject | BI-RADS | en_US |
dc.subject | Breast cancer | en_US |
dc.subject | Decision support | en_US |
dc.subject | Informatics | en_US |
dc.subject | Mammography | en_US |
dc.subject | Mutual information | en_US |
dc.subject | BI-RADS | en_US |
dc.subject | Breast Cancer | en_US |
dc.subject | Decision supports | en_US |
dc.subject | Informatics | en_US |
dc.subject | Mutual informations | en_US |
dc.subject | Biomineralization | en_US |
dc.subject | Bone | en_US |
dc.subject | Decision support systems | en_US |
dc.subject | Diseases | en_US |
dc.subject | Health insurance | en_US |
dc.subject | Mammography | en_US |
dc.subject | Medical imaging | en_US |
dc.subject | aged | en_US |
dc.subject | area under the curve | en_US |
dc.subject | Breast Neoplasms | en_US |
dc.subject | calcinosis | en_US |
dc.subject | computer assisted diagnosis | en_US |
dc.subject | factual database | en_US |
dc.subject | female | en_US |
dc.subject | hospital information system | en_US |
dc.subject | human | en_US |
dc.subject | mammography | en_US |
dc.subject | middle aged | en_US |
dc.subject | procedures | en_US |
dc.subject | radiography | en_US |
dc.subject | receiver operating characteristic | en_US |
dc.subject | retrospective study | en_US |
dc.subject | risk factor | en_US |
dc.subject | article | en_US |
dc.subject | breast tumor | en_US |
dc.subject | computer assisted diagnosis | en_US |
dc.subject | mammography | en_US |
dc.subject | methodology | en_US |
dc.subject | Aged | en_US |
dc.subject | Area Under Curve | en_US |
dc.subject | Breast Neoplasms | en_US |
dc.subject | Calcinosis | en_US |
dc.subject | Databases, Factual | en_US |
dc.subject | Female | en_US |
dc.subject | Humans | en_US |
dc.subject | Mammography | en_US |
dc.subject | Middle Aged | en_US |
dc.subject | Radiographic Image Interpretation, Computer-Assisted | en_US |
dc.subject | Radiology Information Systems | en_US |
dc.subject | Retrospective Studies | en_US |
dc.subject | Risk Factors | en_US |
dc.subject | ROC Curve | en_US |
dc.subject | Aged | en_US |
dc.subject | Area Under Curve | en_US |
dc.subject | Breast Neoplasms | en_US |
dc.subject | Calcinosis | en_US |
dc.subject | Databases, Factual | en_US |
dc.subject | Female | en_US |
dc.subject | Humans | en_US |
dc.subject | Mammography | en_US |
dc.subject | Middle Aged | en_US |
dc.subject | Radiographic Image Interpretation, Computer-Assisted | en_US |
dc.subject | Radiology Information Systems | en_US |
dc.subject | Retrospective Studies | en_US |
dc.subject | Risk Factors | en_US |
dc.subject | ROC Curve | en_US |
dc.title | A comprehensive methodology for determining the most informative mammographic features | en_US |
dc.type | Article | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- A comprehensive methodology for determining the most informative mammographic features.pdf
- Size:
- 230.19 KB
- Format:
- Adobe Portable Document Format
- Description:
- Full printable version