Texture features from mammographic images and risk of breast cancer.
Texture features from mammographic images and risk of breast cancer.
复制标题
DOI：
10.1158/1055-9965.epi-08-0631
复制
发表时间：
2009-03
期刊：
影响因子：
--
通讯作者：
Cerhan JR
中科院分区：
文献类型：
--
作者：
Manduca A;Carston MJ;Heine JJ;Scott CG;Pankratz VS;Brandt KR;Sellers TA;Vachon CM;Cerhan JR
Mammographic percent density (PD) is a strong risk factor for breast cancer, but there has been relatively little systematic evaluation of other features in mammographic images that might additionally predict breast cancer risk. We evaluated the association of a large number of image texture features with risk of breast cancer using a clinic-based case-control study of digitized film mammograms, all with screening mammograms prior to breast cancer diagnosis. The sample was split into training (123 cases, 258 controls) and validation (123 cases, 264 controls) datasets. Age and body mass index (BMI)-adjusted Odds Ratios (ORs) per standard deviation change in the feature, 95% confidence intervals, and the area under the receiver operator characteristic curve (AUC) were obtained using logistic regression. A bootstrap approach was used to identify the strongest features in the training dataset, and results for features that validated in the second half of the sample were reported using the full dataset. The mean age at mammography was 64.0 ± 10.2 years, and the mean time from mammography to breast cancer was 3.7 ± 1.0 (range 2.0-5.9 years). PD was associated with breast cancer risk (OR=1.49; 1.25-1.78). The strongest features that validated from each of several classes (Markovian, run-length, Laws, wavelet and Fourier) showed similar ORs as PD and predicted breast cancer at a similar magnitude (AUC=0.58-0.60) as PD (AUC=0.58). All of these features were automatically calculated (unlike PD), and measure texture at a coarse scale. These features were moderately correlated with PD (r = 0.39-0.64), and after adjustment for PD, each of the features attenuated only slightly and retained statistical significance. However, simultaneous inclusion of these features in a model with PD did not significantly improve the ability to predict breast cancer.
