An exploratory radiomics analysis on digital breast tomosynthesis in women with mammographically negative dense breasts.

PURPOSE To compare Digital Breast Tomosynthesis (DBT) for cancers and normal screens in women with dense breasts and negative mammography using a Radiomics approach. MATERIALS AND METHODS A substudy (N = 40) of the 'Adjunct Screening With Tomosynthesis or Ultrasound in Women With Mammography-Negative Dense Breasts (ASTOUND)' trial was done based on 20 women who had DBT-detected, histology-proven, breast cancer and 20 controls matched for age and density. Using a Radiomics approach normal and pathological breast parenchyma were evaluated, and correlations among Radiomics features and clinical and prognostic parameters were investigated. RESULTS The median age of the patients was 50 years (range 39-70 years). After Radiomics feature number reduction, 3 of 6 (50%) selected features differed between controls and cancers (Skewness (0.002); Entropy (p.004); 90percentile (p.006)). Three Radiomics features (Energy, Entropy and Dissimilarity) significantly correlated to tumor size (r = -0.15,r = 0.49,r = 0.51), but not with prognostic factors. Entropy correlated with Estrogen Receptor status (r = -0,46; p.004). CONCLUSION Radiomics features in patients with dense breasts and negative mammography appear to differ between cancerous and normal breast tissue, with evidence of correlation with tumor size and estrogen receptors. This new information warrants further evaluation in larger studies and could contribute to improved understanding of breast cancer through imaging, and may support tailored screening and treatments.

[1]  Mark J. Ratain,et al.  Tumour heterogeneity in the clinic , 2013, Nature.

[2]  Paul Kinahan,et al.  Radiomics: Images Are More than Pictures, They Are Data , 2015, Radiology.

[3]  B. Keller,et al.  Association between Breast Parenchymal Complexity and False-Positive Recall From Digital Mammography Versus Breast Tomosynthesis: Preliminary Investigation in the ACRIN PA 4006 Trial. , 2016, Academic radiology.

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

[5]  D. Altman,et al.  Statistics notes: Cronbach's alpha , 1997 .

[6]  Maryellen L. Giger,et al.  Computerized Texture Analysis of Mammographic Parenchymal Patterns of Digitized Mammograms1 , 2005 .

[7]  N. Houssami,et al.  Rapid review: radiomics and breast cancer , 2018, Breast Cancer Research and Treatment.

[8]  N. Houssami,et al.  The epidemiology, radiology and biological characteristics of interval breast cancers in population mammography screening , 2017, npj Breast Cancer.

[9]  M. Sormani,et al.  Adjunct Screening With Tomosynthesis or Ultrasound in Women With Mammography-Negative Dense Breasts: Interim Report of a Prospective Comparative Trial. , 2016, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[10]  C. Begg,et al.  The effect of changes in tumor size on breast carcinoma survival in the U.S.: 1975–1999 , 2005, Cancer.

[11]  P. Lambin,et al.  Robust Radiomics Feature Quantification Using Semiautomatic Volumetric Segmentation , 2014, PloS one.

[12]  N Houssami,et al.  Application of breast tomosynthesis in screening: incremental effect on mammography acquisition and reading time. , 2012, The British journal of radiology.

[13]  Hiroko Yamashita,et al.  Identifying Triple-Negative Breast Cancer Using Background Parenchymal Enhancement Heterogeneity on Dynamic Contrast-Enhanced MRI: A Pilot Radiomics Study , 2015, PloS one.

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

[15]  Yi Guo,et al.  Radiomics Analysis on Ultrasound for Prediction of Biologic Behavior in Breast Invasive Ductal Carcinoma , 2017, Clinical breast cancer.

[16]  Milan Sonka,et al.  3D Slicer as an image computing platform for the Quantitative Imaging Network. , 2012, Magnetic resonance imaging.

[17]  Zhimin Huo,et al.  Computerized analysis of digitized mammograms of BRCA1 and BRCA2 gene mutation carriers. , 2002, Radiology.

[18]  Alessio Signori,et al.  Accuracy and reading time for six strategies using digital breast tomosynthesis in women with mammographically negative dense breasts , 2017, European Radiology.

[19]  Erich P Huang,et al.  Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set , 2016, npj Breast Cancer.

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

[21]  N. Paragios,et al.  Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology , 2017, Annals of oncology : official journal of the European Society for Medical Oncology.

[22]  Andrew D. A. Maidment,et al.  Analysis of parenchymal texture with digital breast tomosynthesis: comparison with digital mammography and implications for cancer risk assessment. , 2011, Radiology.

[23]  Ann-Katherine Carton,et al.  Breast percent density: estimation on digital mammograms and central tomosynthesis projections. , 2009, Radiology.

[24]  Li Lan,et al.  Fractal analysis of mammographic parenchymal patterns in breast cancer risk assessment. , 2007, Academic radiology.