Cristina Gallego-Ortiz1, Anne L Martel1. 1. From the Department of Medical Biophysics, University of Toronto, 2075 Bayview Ave, M6-623e, Toronto, ON, Canada M4N 3M5; and Department of Imaging Research, Sunnybrook Research Institute, Toronto, Ont, Canada.
Abstract
PURPOSE: To determine suitable features and optimal classifier design for a computer-aided diagnosis (CAD) system to differentiate among mass and nonmass enhancements during dynamic contrast material-enhanced magnetic resonance (MR) imaging of the breast. MATERIALS AND METHODS: Two hundred eighty histologically proved mass lesions and 129 histologically proved nonmass lesions from MR imaging studies were retrospectively collected. The institutional research ethics board approved this study and waived informed consent. Breast Imaging Reporting and Data System classification of mass and nonmass enhancement was obtained from radiologic reports. Image data from dynamic contrast-enhanced MR imaging were extracted and analyzed by using feature selection techniques and binary, multiclass, and cascade classifiers. Performance was assessed by measuring the area under the receiver operating characteristics curve (AUC), sensitivity, and specificity. Bootstrap cross validation was used to predict the best classifier for the classification task of mass and nonmass benign and malignant breast lesions. RESULTS: A total of 176 features were extracted. Feature relevance ranking indicated unequal importance of kinetic, texture, and morphologic features for mass and nonmass lesions. The best classifier performance was a two-stage cascade classifier (mass vs nonmass followed by malignant vs benign classification) (AUC, 0.91; 95% confidence interval (CI): 0.88, 0.94) compared with one-shot classifier (ie, all benign vs malignant classification) (AUC, 0.89; 95% CI: 0.85, 0.92). The AUC was 2% higher for cascade (median percent difference obtained by using paired bootstrapped samples) and was significant (P = .0027). Our proposed two-stage cascade classifier decreases the overall misclassification rate by 12%, with 72 of 409 missed diagnoses with cascade versus 82 of 409 missed diagnoses with one-shot classifier. CONCLUSION: Separately optimizing feature selection and training classifiers for mass and nonmass lesions improves the accuracy of CAD for breast MR imaging. By cascading classifiers, we achieved a significant improvement in performance with respect to the use of a one-shot classifier. Our cascaded classifier may provide an advantage for screening women at high risk for breast cancer, in whom the ability to diagnose cancers at an early stage is of primary importance.
PURPOSE: To determine suitable features and optimal classifier design for a computer-aided diagnosis (CAD) system to differentiate among mass and nonmass enhancements during dynamic contrast material-enhanced magnetic resonance (MR) imaging of the breast. MATERIALS AND METHODS: Two hundred eighty histologically proved mass lesions and 129 histologically proved nonmass lesions from MR imaging studies were retrospectively collected. The institutional research ethics board approved this study and waived informed consent. Breast Imaging Reporting and Data System classification of mass and nonmass enhancement was obtained from radiologic reports. Image data from dynamic contrast-enhanced MR imaging were extracted and analyzed by using feature selection techniques and binary, multiclass, and cascade classifiers. Performance was assessed by measuring the area under the receiver operating characteristics curve (AUC), sensitivity, and specificity. Bootstrap cross validation was used to predict the best classifier for the classification task of mass and nonmass benign and malignant breast lesions. RESULTS: A total of 176 features were extracted. Feature relevance ranking indicated unequal importance of kinetic, texture, and morphologic features for mass and nonmass lesions. The best classifier performance was a two-stage cascade classifier (mass vs nonmass followed by malignant vs benign classification) (AUC, 0.91; 95% confidence interval (CI): 0.88, 0.94) compared with one-shot classifier (ie, all benign vs malignant classification) (AUC, 0.89; 95% CI: 0.85, 0.92). The AUC was 2% higher for cascade (median percent difference obtained by using paired bootstrapped samples) and was significant (P = .0027). Our proposed two-stage cascade classifier decreases the overall misclassification rate by 12%, with 72 of 409 missed diagnoses with cascade versus 82 of 409 missed diagnoses with one-shot classifier. CONCLUSION: Separately optimizing feature selection and training classifiers for mass and nonmass lesions improves the accuracy of CAD for breast MR imaging. By cascading classifiers, we achieved a significant improvement in performance with respect to the use of a one-shot classifier. Our cascaded classifier may provide an advantage for screening women at high risk for breast cancer, in whom the ability to diagnose cancers at an early stage is of primary importance.
Authors: Nicole Schwendener; Christian Jackowski; Frederick Schuster; Anders Persson; Marcel J Warntjes; Wolf -Dieter Zech Journal: Int J Legal Med Date: 2017-06-17 Impact factor: 2.686
Authors: Ning Lang; Yang Zhang; Enlong Zhang; Jiahui Zhang; Daniel Chow; Peter Chang; Hon J Yu; Huishu Yuan; Min-Ying Su Journal: Magn Reson Imaging Date: 2019-02-28 Impact factor: 2.546
Authors: L Losurdo; T M A Basile; A Fanizzi; R Bellotti; U Bottigli; R Carbonara; R Dentamaro; D Diacono; V Didonna; A Lombardi; F Giotta; C Guaragnella; A Mangia; R Massafra; P Tamborra; S Tangaro; D La Forgia Journal: Biomed Res Int Date: 2018-05-16 Impact factor: 3.411