Currently, call-back rates for screening mammography in the U.S. are high at about 10%. Due to the effect of tissue superimposition on the 2D projection images, many women, especially women with dense breasts, are recalled for additional imaging of """"""""pseudo-lesions"""""""", essentially suspicious-looking superimpositions of normal tissues which, after diagnostic workup, prove to be normal. Digital breast tomosynthesis (DBT) is a new 3D x-ray imaging modality in which tomographic breast images are reconstructed from multiple low-dose source projections. In DBT, the effects of tissue superposition are largely removed from the image set, thereby providing superior breast tissue visualization compared to mammography. Early clinical trials suggest up to a 40% reduction in false positive recalls when DBT is incorporated in the screening setting. There is however, a higher radiation dose when DBT is incorporated into the screening paradigm. Therefore this potential benefit of DBT must be carefully weighed against a potential increase of dose. The identification of a subset of women who would benefit most from DBT imaging is critical. To address this concern, our study will compare the effect of breast density and overall breast parenchymal complexity on the recall decision in breast cancer screening with digital mammography (DM) versus DBT. Our hypothesis is that complex parenchymal patterns (i.e., dense and/or texturally complex breasts) have a higher likelihood of being recalled for false positive findings with DM than when DBT is incorporated in the screening process. Towards this end, we propose to develop an imaging index for characterizing breast parenchymal tissue complexity. Currently, there is no standard lexicon to comprehensively reflect parenchymal complexity. Breast density is the only such image-based descriptor in the standard mammography BIRADS lexicon. Therefore, we propose to combine the standard density measures with advanced image texture features into a quantitative breast complexity index (BCI) that can be used to identify a subset of women who would benefit most from DBT screening. The rapidly evolving technology and the potential for superior performance will determine the role of DBT in clinical practice. If our hypothesis proves to be true, DBT could replace or complement DM for the screening of women with dense and/or texturally complex breasts, to reduce unnecessary recalls and additional diagnostic imaging procedures.
The recent FDA approval coupled with the rapidly evolving technology and a potential for superior performance will determine the role of DBT in clinical practice. If our hypothesis proves to be true, DBT could replace or complement DM for the screening of women with dense and/or texturally complex breasts, and ultimately reduce unnecessary recalls and additional diagnostic imaging procedures. Our proposed breast complexity index (BCI) could be used as an imaging marker to identify women that can benefit most from DBT screening, understanding that the improvement in tissue visualization comes with an increase in radiation dose.
|Gastounioti, Aimilia; Oustimov, Andrew; Hsieh, Meng-Kang et al. (2018) Using Convolutional Neural Networks for Enhanced Capture of Breast Parenchymal Complexity Patterns Associated with Breast Cancer Risk. Acad Radiol 25:977-984|
|Conant, Emily F; Keller, Brad M; Pantalone, Lauren et al. (2017) Agreement between Breast Percentage Density Estimations from Standard-Dose versus Synthetic Digital Mammograms: Results from a Large Screening Cohort Using Automated Measures. Radiology 283:673-680|
|Ray, Shonket; Chen, Lin; Keller, Brad M et al. (2016) Association between Breast Parenchymal Complexity and False-Positive Recall From Digital Mammography Versus Breast Tomosynthesis: Preliminary Investigation in the ACRIN PA 4006 Trial. Acad Radiol 23:977-86|
|Gastounioti, Aimilia; Oustimov, Andrew; Keller, Brad M et al. (2016) Breast parenchymal patterns in processed versus raw digital mammograms: A large population study toward assessing differences in quantitative measures across image representations. Med Phys 43:5862|
|Chen, Lin; Ray, Shonket; Keller, Brad M et al. (2016) The Impact of Acquisition Dose on Quantitative Breast Density Estimation with Digital Mammography: Results from ACRIN PA 4006. Radiology 280:693-700|
|Gastounioti, Aimilia; Conant, Emily F; Kontos, Despina (2016) Beyond breast density: a review on the advancing role of parenchymal texture analysis in breast cancer risk assessment. Breast Cancer Res 18:91|
|McCarthy, Anne Marie; Keller, Brad M; Pantalone, Lauren M et al. (2016) Racial Differences in Quantitative Measures of Area and Volumetric Breast Density. J Natl Cancer Inst 108:|
|Pertuz, Said; McDonald, Elizabeth S; Weinstein, Susan P et al. (2016) Fully Automated Quantitative Estimation of Volumetric Breast Density from Digital Breast Tomosynthesis Images: Preliminary Results and Comparison with Digital Mammography and MR Imaging. Radiology 279:65-74|
|McCarthy, Anne Marie; Keller, Brad; Kontos, Despina et al. (2015) The use of the Gail model, body mass index and SNPs to predict breast cancer among women with abnormal (BI-RADS 4) mammograms. Breast Cancer Res 17:1|
|Zheng, Yuanjie; Keller, Brad M; Ray, Shonket et al. (2015) Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment. Med Phys 42:4149-60|
Showing the most recent 10 out of 19 publications