Maria Adele Marino1,2, Katja Pinker1,3, Doris Leithner1,4, Janice Sung1, Daly Avendano1,5, Elizabeth A Morris1, Maxine Jochelson6. 1. Department of Radiology, Breast Imaging Service, Memorial Sloan Kettering Cancer Center, 300 E 66th Street, New York, NY, 10065, USA. 2. Department of Biomedical Sciences and Morphologic and Functional Imaging, University of Messina, Messina, Italy. 3. Department of Biomedical Imaging and Image-guided Therapy, Division of Molecular and Gender Imaging, Medical University Vienna, Vienna, Austria. 4. Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt, Germany. 5. Department of Breast Imaging, Breast Cancer Center TecSalud, ITESM Monterrey, Monterrey, Nuevo Leon, Mexico. 6. Department of Radiology, Breast Imaging Service, Memorial Sloan Kettering Cancer Center, 300 E 66th Street, New York, NY, 10065, USA. jochelsm@mskcc.org.
Abstract
PURPOSE: To investigate the potential of contrast-enhanced mammography (CEM) and radiomics analysis for the noninvasive differentiation of breast cancer invasiveness, hormone receptor status, and tumor grade. PROCEDURES: This retrospective study included 100 patients with 103 breast cancers who underwent pretreatment CEM. Radiomics analysis was performed using MAZDA software. Lesions were manually segmented. Radiomic features were derived from first-order histogram (HIS), co-occurrence matrix (COM), run length matrix (RLM), absolute gradient, autoregressive model, the discrete Haar wavelet transform (WAV), and lesion geometry. Fisher, probability of error and average correlation (POE+ACC), and mutual information (MI) coefficients informed feature selection. Linear discriminant analysis followed by k-nearest neighbor classification (with leave-one-out cross-validation) was used for pairwise texture-based separation of tumor invasiveness and hormone receptor status using histopathology as the standard of reference. RESULTS: Radiomics analysis achieved the highest accuracies of 87.4 % for differentiating invasive from noninvasive cancers based on COM+HIS/MI, 78.4 % for differentiating HR positive from HR negative cancers based on COM+HIS/Fisher, 97.2 % for differentiating human epidermal growth factor receptor 2 (HER2)-positive/HR-negative from HER2-negative/HR-positive cancers based on RLM+WAV/MI, 100 % for differentiating triple-negative from triple-positive breast cancers mainly based on COM+WAV+HIS/POE+ACC, and 82.1 % for differentiating triple-negative from HR-positive cancers mainly based on WAV+HIS/Fisher. Accuracies for differentiating grade 1 vs. grades 2 and 3 cancers were 90 % for invasive cancers (based on COM/MI) and 100 % for noninvasive cancers (almost entirely based on COM/MI). CONCLUSIONS: Radiomics analysis with CEM has potential for noninvasive differentiation of tumors with different degrees of invasiveness, hormone receptor status, and tumor grade.
PURPOSE: To investigate the potential of contrast-enhanced mammography (CEM) and radiomics analysis for the noninvasive differentiation of breast cancer invasiveness, hormone receptor status, and tumor grade. PROCEDURES: This retrospective study included 100 patients with 103 breast cancers who underwent pretreatment CEM. Radiomics analysis was performed using MAZDA software. Lesions were manually segmented. Radiomic features were derived from first-order histogram (HIS), co-occurrence matrix (COM), run length matrix (RLM), absolute gradient, autoregressive model, the discrete Haar wavelet transform (WAV), and lesion geometry. Fisher, probability of error and average correlation (POE+ACC), and mutual information (MI) coefficients informed feature selection. Linear discriminant analysis followed by k-nearest neighbor classification (with leave-one-out cross-validation) was used for pairwise texture-based separation of tumor invasiveness and hormone receptor status using histopathology as the standard of reference. RESULTS: Radiomics analysis achieved the highest accuracies of 87.4 % for differentiating invasive from noninvasive cancers based on COM+HIS/MI, 78.4 % for differentiating HR positive from HR negative cancers based on COM+HIS/Fisher, 97.2 % for differentiating humanepidermal growth factor receptor 2 (HER2)-positive/HR-negative from HER2-negative/HR-positive cancers based on RLM+WAV/MI, 100 % for differentiating triple-negative from triple-positive breast cancers mainly based on COM+WAV+HIS/POE+ACC, and 82.1 % for differentiating triple-negative from HR-positive cancers mainly based on WAV+HIS/Fisher. Accuracies for differentiating grade 1 vs. grades 2 and 3 cancers were 90 % for invasive cancers (based on COM/MI) and 100 % for noninvasive cancers (almost entirely based on COM/MI). CONCLUSIONS: Radiomics analysis with CEM has potential for noninvasive differentiation of tumors with different degrees of invasiveness, hormone receptor status, and tumor grade.
Entities:
Keywords:
Biomarkers; Breast cancer; Contrast media; Mammography; Tumors
Authors: Piotr M Szczypiński; Michał Strzelecki; Andrzej Materka; Artur Klepaczko Journal: Comput Methods Programs Biomed Date: 2008-10-14 Impact factor: 5.428
Authors: E M Fallenberg; C Dromain; F Diekmann; F Engelken; M Krohn; J M Singh; B Ingold-Heppner; K J Winzer; U Bick; D M Renz Journal: Eur Radiol Date: 2013-09-19 Impact factor: 5.315
Authors: Julia Fruehwald-Pallamar; Christian Czerny; Laura Holzer-Fruehwald; Stefan F Nemec; Christina Mueller-Mang; Michael Weber; Marius E Mayerhoefer Journal: NMR Biomed Date: 2013-05-23 Impact factor: 4.044
Authors: Marc B I Lobbes; Ulrich Lalji; Janneke Houwers; Estelle C Nijssen; Patty J Nelemans; Lori van Roozendaal; Marjolein L Smidt; Esther Heuts; Joachim E Wildberger Journal: Eur Radiol Date: 2014-04-03 Impact factor: 5.315
Authors: Ruben T H M Larue; Gilles Defraene; Dirk De Ruysscher; Philippe Lambin; Wouter van Elmpt Journal: Br J Radiol Date: 2016-12-12 Impact factor: 3.039
Authors: Andrea Cozzi; Simone Schiaffino; Marianna Fanizza; Veronica Magni; Laura Menicagli; Cristian Giuseppe Monaco; Adrienn Benedek; Diana Spinelli; Giovanni Di Leo; Giuseppe Di Giulio; Francesco Sardanelli Journal: Eur Radiol Date: 2022-06-01 Impact factor: 7.034
Authors: Roberta Fusco; Adele Piccirillo; Mario Sansone; Vincenza Granata; Maria Rosaria Rubulotta; Teresa Petrosino; Maria Luisa Barretta; Paolo Vallone; Raimondo Di Giacomo; Emanuela Esposito; Maurizio Di Bonito; Antonella Petrillo Journal: Diagnostics (Basel) Date: 2021-04-30