Distinction between benign and malignant breast masses at breast ultrasound using deep learning method with convolutional neural network
We aimed to use deep learning with convolutional neural network (CNN) to discriminate between benign and malignant breast mass images from ultrasound.
Materials and Methods
We retrospectively gathered 480 images of 96 benign masses and 467 images of 144 malignant masses for training data. Deep learning model was constructed using CNN architecture GoogLeNet and analyzed test data: 48 benign masses, 72 malignant masses. Three radiologists interpreted these test data. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) were calculated.
The CNN model and radiologists had a sensitivity of 0.958 and 0.583–0.917, specificity of 0.925 and 0.604–0.771, and accuracy of 0.925 and 0.658–0.792, respectively. The CNN model had equal or better diagnostic performance compared to radiologists (AUC = 0.913 and 0.728–0.845, p = 0.01–0.14).
Deep learning with CNN shows high diagnostic performance to discriminate between benign and malignant breast masses on ultrasound.
KeywordsBreast imaging Ultrasound Deep learning Convolutional neural network Artificial intelligence
For this study, Kazunori Kubota and Tomoyuki Fujioka received grant (KAKENHI-PROJECT-16K10270; https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-16K10270/).
Kazunori Kubota and Tomoyuki Fujioka received grant (KAKENHI-PROJECT-16K10270; https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-16K10270/).
Compliance with ethical standards
Conflict of interest
All the authors and their institution have no conflicts of interest.
All procedures used in this research were approved by the Ethical Committee of Tokyo Medical and Dental University, Medical Hospital.
- 4.D’Orsi C, Sickles E, Mendelson E, Morris E. Breast imaging reporting and data system. 5th ed. Reston: American College of Radiology; 2013.Google Scholar
- 6.Youk JH, Son EJ, Gweon HM, Kim H, Park YJ, Kim JA. Comparison of strain and shear wave elastography for the differentiation of benign from malignant breast lesions, combined with B-mode ultrasonography: qualitative and quantitative assessments. Ultrasound Med Biol. 2014;40:2336–44.CrossRefGoogle Scholar
- 12.Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. In: Proceeding of IEEE international conference on computer vision pattern recognition; 2015. p. 1–9.Google Scholar
- 13.Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167 (2015).
- 18.Huang Q, Zhang F, Li X. Machine learning in ultrasound computer-aided diagnostic systems: a survey. Biomed Res Int. 2018;4(2018):5137904.Google Scholar
- 23.M Claesen, B De Moor. Hyperparameter search in machine learning. arXiv:1502.02127 (2015).