PURPOSE: To use features extracted from magnetic resonance (MR) images and a machine-learning method to assist in differentiating breast cancer molecular subtypes. MATERIALS AND METHODS: This retrospective Health Insurance Portability and Accountability Act (HIPAA)-compliant study received Institutional Review Board (IRB) approval. We identified 178 breast cancer patients between 2006-2011 with: 1) ERPR + (n = 95, 53.4%), ERPR-/HER2 + (n = 35, 19.6%), or triple negative (TN, n = 48, 27.0%) invasive ductal carcinoma (IDC), and 2) preoperative breast MRI at 1.5T or 3.0T. Shape, texture, and histogram-based features were extracted from each tumor contoured on pre- and three postcontrast MR images using in-house software. Clinical and pathologic features were also collected. Machine-learning-based (support vector machines) models were used to identify significant imaging features and to build models that predict IDC subtype. Leave-one-out cross-validation (LOOCV) was used to avoid model overfitting. Statistical significance was determined using the Kruskal-Wallis test. RESULTS: Each support vector machine fit in the LOOCV process generated a model with varying features. Eleven out of the top 20 ranked features were significantly different between IDC subtypes with P < 0.05. When the top nine pathologic and imaging features were incorporated, the predictive model distinguished IDC subtypes with an overall accuracy on LOOCV of 83.4%. The combined pathologic and imaging model's accuracy for each subtype was 89.2% (ERPR+), 63.6% (ERPR-/HER2+), and 82.5% (TN). When only the top nine imaging features were incorporated, the predictive model distinguished IDC subtypes with an overall accuracy on LOOCV of 71.2%. The combined pathologic and imaging model's accuracy for each subtype was 69.9% (ERPR+), 62.9% (ERPR-/HER2+), and 81.0% (TN). CONCLUSION: We developed a machine-learning-based predictive model using features extracted from MRI that can distinguish IDC subtypes with significant predictive power. J. Magn. Reson. Imaging 2016;44:122-129.
PURPOSE: To use features extracted from magnetic resonance (MR) images and a machine-learning method to assist in differentiating breast cancer molecular subtypes. MATERIALS AND METHODS: This retrospective Health Insurance Portability and Accountability Act (HIPAA)-compliant study received Institutional Review Board (IRB) approval. We identified 178 breast cancerpatients between 2006-2011 with: 1) ERPR + (n = 95, 53.4%), ERPR-/HER2 + (n = 35, 19.6%), or triple negative (TN, n = 48, 27.0%) invasive ductal carcinoma (IDC), and 2) preoperative breast MRI at 1.5T or 3.0T. Shape, texture, and histogram-based features were extracted from each tumor contoured on pre- and three postcontrast MR images using in-house software. Clinical and pathologic features were also collected. Machine-learning-based (support vector machines) models were used to identify significant imaging features and to build models that predict IDC subtype. Leave-one-out cross-validation (LOOCV) was used to avoid model overfitting. Statistical significance was determined using the Kruskal-Wallis test. RESULTS: Each support vector machine fit in the LOOCV process generated a model with varying features. Eleven out of the top 20 ranked features were significantly different between IDC subtypes with P < 0.05. When the top nine pathologic and imaging features were incorporated, the predictive model distinguished IDC subtypes with an overall accuracy on LOOCV of 83.4%. The combined pathologic and imaging model's accuracy for each subtype was 89.2% (ERPR+), 63.6% (ERPR-/HER2+), and 82.5% (TN). When only the top nine imaging features were incorporated, the predictive model distinguished IDC subtypes with an overall accuracy on LOOCV of 71.2%. The combined pathologic and imaging model's accuracy for each subtype was 69.9% (ERPR+), 62.9% (ERPR-/HER2+), and 81.0% (TN). CONCLUSION: We developed a machine-learning-based predictive model using features extracted from MRI that can distinguish IDC subtypes with significant predictive power. J. Magn. Reson. Imaging 2016;44:122-129.
Authors: Elizabeth J Sutton; Jung Hun Oh; Brittany Z Dashevsky; Harini Veeraraghavan; Aditya P Apte; Sunitha B Thakur; Joseph O Deasy; Elizabeth A Morris Journal: J Magn Reson Imaging Date: 2015-04-07 Impact factor: 4.813
Authors: Constance D Lehman; Jeffrey D Blume; Wendy B DeMartini; Nola M Hylton; Benjamin Herman; Mitchell D Schnall Journal: AJR Am J Roentgenol Date: 2013-06 Impact factor: 3.959
Authors: Monique D Dorrius; Marijke C Jansen-van der Weide; Peter M A van Ooijen; Ruud M Pijnappel; Matthijs Oudkerk Journal: Eur Radiol Date: 2011-03-15 Impact factor: 5.315
Authors: Rita A Mukhtar; Christina Yau; Mark Rosen; Vickram J Tandon; Nola Hylton; Laura J Esserman Journal: Ann Surg Oncol Date: 2013-06-19 Impact factor: 5.344
Authors: Maciej A Mazurowski; Ashirbani Saha; Michael R Harowicz; Elizabeth Hope Cain; Jeffrey R Marks; P Kelly Marcom Journal: J Magn Reson Imaging Date: 2019-01-22 Impact factor: 4.813
Authors: D Leithner; G J Wengert; T H Helbich; S Thakur; R E Ochoa-Albiztegui; E A Morris; K Pinker Journal: Clin Radiol Date: 2017-12-09 Impact factor: 2.350
Authors: Katja Pinker; Fuki Shitano; Evis Sala; Richard K Do; Robert J Young; Andreas G Wibmer; Hedvig Hricak; Elizabeth J Sutton; Elizabeth A Morris Journal: J Magn Reson Imaging Date: 2017-11-02 Impact factor: 4.813
Authors: Michael R Folkert; Jeremy Setton; Aditya P Apte; Milan Grkovski; Robert J Young; Heiko Schöder; Wade L Thorstad; Nancy Y Lee; Joseph O Deasy; Jung Hun Oh Journal: Phys Med Biol Date: 2017-06-12 Impact factor: 3.609