Automatic classification of breast lesions usingTransfer Learning

• Published in: Revista IEEE América Latina Vol. 17; no. 12; pp. 1964 - 1969
• Main Authors: Pedro da Silva Neto, Rafael, Oseas de Carvalho Filho, Antonio
• Format: Journal Article
• Language: English
• Published: Los Alamitos IEEE 01-12-2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Biopsy; Breast; Breast Lesions; Computational modeling; Computing costs; Deep learning; Delta-sigma modulation; Digital Image Processing; Image classification; Learning; Lesions; Support vector machines; Trans-fer Learning
• ISSN: 1548-0992; 1548-0992
• DOI: 10.1109/TLA.2019.9011540

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.