Alberto Stefano Tagliafico1, Francesca Valdora2, Giovanna Mariscotti3, Maunela Durando3, Jacopo Nori4, Daniele La Forgia5, Ilan Rosenberg6, Francesca Caumo7, Nicoletta Gandolfo8, Nehmat Houssami9, Massimo Calabrese10. 1. Department of Health Sciences (DISSAL), Radiology Section, University of Genoa, Italy; Emergency Radiology, Policlinico San Martino, Genoa, Italy. Electronic address: alberto.tagliafico@unige.it. 2. Department of Health Sciences (DISSAL), Radiology Section, University of Genoa, Italy. 3. Azienda Ospedaliera Universitaria Citta della Salute e della Scienza di Torino, Torino, Italy. 4. Azienda Ospedaliero-Universitaria Carreggi, Firenze, Italy. 5. Istituto Tumori Bari "Giovanni Paolo II"-IRCCS, Italy. 6. Unit of Radiology, San Bartolomeo Hospital, ASL 5 "Spezzino", Sarzana SP, Italy. 7. Veneto Institute of Oncology IOV - IRCCS, Padua, Italy. 8. Department of Imaging, ASL 3 Genovese, Genoa, Italy. 9. Sydney School of Public Health, Sydney Medical School, University of Sydney, Sydney, Australia. 10. Breast Radiology, Policlinico San Martino, Genoa, Italy.
Abstract
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.
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.
Authors: Marco Caballo; Domenico R Pangallo; Wendelien Sanderink; Andrew M Hernandez; Su Hyun Lyu; Filippo Molinari; John M Boone; Ritse M Mann; Ioannis Sechopoulos Journal: Med Phys Date: 2020-12-10 Impact factor: 4.071