Automatic classification of breast lesions usingTransfer Learning
Rafael Pedro da Silva Neto, Antônio Oseas de Carvalho Filho · IEEE Latin America Transactions · 2019
Breast lesions are one of the most common types of lesions among women in Brazil and worldwide, accounting forabout 28% of new cases each year. These lesions may have Benignor Malignant behaviors. In this work, a computational method-ology for image classification was developed to differentiate malignant and benign lesions breast, aiming at low computational cost and good efficiency. In our approach, different Convolutional Neural Networks architectures and several classifiers were tested. Transfer Learning was employed to deal with the limitation of the small number of images in the database, reaching an accuracy of 81.73%, a sensitivity of 85.66%, a specificity of 78.40%, Kappa of 0.63 and ROC curve of 0.82. Finally, it is believed that theproposed methodology can integrate a CAD tool acting as patient screening or providing a second opinion to the specialist.