Abstract
BackgroundThe purpose of this work was to evaluate computable Breast Imaging Reporting and Data System (BI-RADS) radiomic features to classify breast masses on ultrasound B-mode images.MethodsThe database consisted of 206 consecutive lesions (144 benign and 62 malignant) proved by percutaneous biopsy in a prospective study approved by the local ethical committee. A radiologist manually delineated the contour of the lesions on greyscale images. We extracted the main ten radiomic features based on the BI-RADS lexicon and classified the lesions as benign or malignant using a bottom-up approach for five machine learning (ML) methods: multilayer perceptron (MLP), decision tree (DT), linear discriminant analysis (LDA), random forest (RF), and support vector machine (SVM). We performed a 10-fold cross validation for training and testing of all classifiers. Receiver operating characteristic (ROC) analysis was used for providing the area under the curve with 95% confidence intervals (CI).ResultsThe classifier with the highest AUC at ROC analysis was SVM (AUC = 0.840, 95% CI 0.6667–0.9762), with 71.4% sensitivity (95% CI 0.6479–0.8616) and 76.9% specificity (95% CI 0.6148–0.8228). The best AUC for each method was 0.744 (95% CI 0.677–0.774) for DT, 0.818 (95% CI 0.6667–0.9444) for LDA, 0.811 (95% CI 0.710–0.892) for RF, and 0.806 (95% CI 0.677–0.839) for MLP.Lesion margin and orientation were the optimal features for all the machine learning methods.ConclusionsML can aid the distinction between benign and malignant breast lesion on ultrasound images using quantified BI-RADS descriptors. SVM provided the highest ROC-AUC (0.840).
Highlights
The purpose of this work was to evaluate computable Breast Imaging Reporting and Data System (BI-RADS) radiomic features to classify breast masses on ultrasound B-mode images
Since 2003, the American College of Radiology developed the Breast Imaging and Reporting Data System (BI-RADS) ultrasound lexicon that provides standard terminology to describe the findings in relation with the probability of malignancy [3, 4]
Statistical analysis We evaluated the different combinations of input features for each machine learning approach in order to select the one with the best classification performance
Summary
The purpose of this work was to evaluate computable Breast Imaging Reporting and Data System (BI-RADS) radiomic features to classify breast masses on ultrasound B-mode images. It is useful to detect and distinguish benign from malignant masses with high accuracy, reducing the number of unnecessary biopsies [1, 2]. Since 2003, the American College of Radiology developed the Breast Imaging and Reporting Data System (BI-RADS) ultrasound lexicon that provides standard terminology to describe the findings in relation with the probability of malignancy [3, 4]. One of the aims of radiomics is to extract, process, and classify a number of imaging features in order to determine the phenotypic characteristics of a lesion that helps to differentiate malignant from benign lesions. Radiomics can be used for any imaging method, including ultrasound scan [7]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have