Texture feature standardization in digital mammography for improving generalizability across devices

Growing evidence suggests a relationship between mammographic texture and breast cancer risk. For studies performing texture analysis on digital mammography (DM) images from various DM systems, it is important to evaluate if different systems could introduce inherent differences in the images analyzed and how to construct a methodological framework to identify and standardize such effects, if these differences exist. In this study, we compared two DM systems, the GE Senographe 2000D and DS using a validated physical breast phantom (Rachel, Gammex). The GE 2000D and DS systems use the same detector, but a different automated exposure control (AEC) system, resulting in differences in dose performance. On each system, images of the phantom are acquired five times in the Cranio-Caudal (CC) view with the same clinically optimized phototimer setting. Three classes of texture features, namely grey-level histogram, cooccurrence, and run-length texture features (a total of 26 features), are generated within the breast region from the raw DM images and compared between the two imaging systems. To alleviate system effects, a range of standardization steps are applied to the feature extraction process: z-score normalization is performed as the initial step to standardize image intensities, and the parameters in generating co-occurrence features are varied to decrease system differences introduced by detector blurring effects. To identify texture features robust to detectors (i.e. the ones minimally affected only by electronic noise), the distribution of each texture feature is compared between the two systems using the Kolmogorov-Smirnov (K-S) test at 0.05 significance, where features with p>0.05 are deemed robust to inherent system differences. Our approach could provide a basis for texture feature standardization across different DM imaging systems and provide a systematic methodology for selecting generalizable texture descriptors in breast cancer risk assessment.

[1]  C. Isaacs,et al.  Management of women at increased risk for hereditary breast cancer. , 2007, Breast disease.

[2]  M. Gail,et al.  Projecting individualized probabilities of developing breast cancer for white females who are being examined annually. , 1989, Journal of the National Cancer Institute.

[3]  C B Caldwell,et al.  Development of an anthropomorphic breast phantom. , 1990, Medical physics.

[4]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[5]  N. Smirnov.  Table for Estimating the Goodness of Fit of Empirical Distributions , 1948 .

[6]  Yan Wang,et al.  A Phantom Study for Assessing the Effect of Different Digital Detectors on Mammographic Texture Features , 2012, Digital Mammography / IWDM.

[7]  N. Boyd,et al.  Mammographic density and the risk and detection of breast cancer. , 2007, The New England journal of medicine.

[8]  Jim Freeman.  Probability Metrics and the Stability of Stochastic Models , 1991 .

[9]  V. McCormack,et al.  Breast Density and Parenchymal Patterns as Markers of Breast Cancer Risk: A Meta-analysis , 2006, Cancer Epidemiology Biomarkers & Prevention.

[10]  Michael J. Carston,et al.  Texture Features from Mammographic Images and Risk of Breast Cancer , 2009, Cancer Epidemiology Biomarkers & Prevention.

[11]  M. Giger,et al.  Computerized analysis of mammographic parenchymal patterns for assessing breast cancer risk: effect of ROI size and location. , 2004, Medical physics.

[12]  M. Giger,et al.  Computerized analysis of mammographic parenchymal patterns for breast cancer risk assessment: feature selection. , 2000, Medical physics.