A comprehensive methodology for determining the most informative mammographic features
Author
Wu, Y.
Alagoz O.
Ayvaci, M.U.S.
Munoz Del Rio, A.
Vanness, D.J.
Woods, R.
Burnside, E.S.
Date
2013Source Title
Journal of Digital Imaging
Print ISSN
0897-1889
Volume
26
Issue
5
Pages
941 - 947
Language
English
Type
ArticleItem Usage Stats
134
views
views
92
downloads
downloads
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.
Keywords
BI-RADSBreast cancer
Decision support
Informatics
Mammography
Mutual information
BI-RADS
Breast Cancer
Decision supports
Informatics
Mutual informations
Biomineralization
Bone
Decision support systems
Diseases
Health insurance
Mammography
Medical imaging
aged
area under the curve
Breast Neoplasms
calcinosis
computer assisted diagnosis
factual database
female
hospital information system
human
mammography
middle aged
procedures
radiography
receiver operating characteristic
retrospective study
risk factor
article
breast tumor
computer assisted diagnosis
mammography
methodology
Aged
Area Under Curve
Breast Neoplasms
Calcinosis
Databases, Factual
Female
Humans
Mammography
Middle Aged
Radiographic Image Interpretation, Computer-Assisted
Radiology Information Systems
Retrospective Studies
Risk Factors
ROC Curve
Aged
Area Under Curve
Breast Neoplasms
Calcinosis
Databases, Factual
Female
Humans
Mammography
Middle Aged
Radiographic Image Interpretation, Computer-Assisted
Radiology Information Systems
Retrospective Studies
Risk Factors
ROC Curve
Permalink
http://hdl.handle.net/11693/20778Published Version (Please cite this version)
http://dx.doi.org/10.1007/s10278-013-9588-5Collections
Related items
Showing items related by title, author, creator and subject.
-
Localization of diagnostically relevant regions of interest in whole slide images: a comparative study
Mercan, E.; Aksoy, S.; Shapiro, L. G.; Weaver, D. L.; Brunyé, T. T.; Elmore, J. G. (Springer New York LLC, 2016-08)Whole slide digital imaging technology enables researchers to study pathologists’ interpretive behavior as they view digital slides and gain new understanding of the diagnostic medical decision-making process. In this ... -
A resampling-based meta-analysis for detection of differential gene expression in breast cancer
Gur-Dedeoglu, B.; Konu, O.; Kir, S.; Ozturk, A. R.; Bozkurt, B.; Ergul, G.; Yulug, I.G. (BioMed Central, 2008)Background: Accuracy in the diagnosis of breast cancer and classification of cancer subtypes has improved over the years with the development of well-established immunohistopathological criteria. More recently, diagnostic ... -
Detection of microcalcifications in mammograms using local maxima and adaptive wavelet transform analysis
Bagci, A. M.; Çetin, A. Enis (The Institution of Engineering and Technology(IET), 2002-10-24)A method for computer-aided diagnosis of microcalcification clusters in mammogram images is presented. Microcalcification clusters which are an early sign of breast cancer appear as isolated bright spots in mammograms. ...