An Approach to BI-RADS Uncertainty Levels Classification Via Deep Learning with Transfer Learning Technique

• Published in: 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS) pp. 603 - 608
• Main Authors: Medeiros, Aldisio, Ohata, Elene F., Silva, Francisco H. S., Rego, Paulo A. L., Reboucas Filho, Pedro Pedrosa
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-07-2020
• Subjects: BI RADS; Cancer; Classification; Feature extraction; Health of Things; Lesions; Mammography; Medical diagnostic imaging; Support vector machines; Transfer Learning
• ISSN: 2372-9198
• DOI: 10.1109/CBMS49503.2020.00119

This work combines the transfer learning technique with Convolutional Neural Networks (CNN) to classify the pathology within BI-RADS levels 3 and 4 for malignancy of breast masses. These BI-RADS levels represent the zone of the uncertainty of the degree of malignancy of the found mass, making it difficult for the human experts in classifying as malignant or benign. Eleven CNN architectures were used as feature extractors and combined with four traditional classification models: Bayes, Multilayer Perceptron (MLP), Support Vector Machines, and Random Forest. The combination DenseNet201-MLP achieved an accuracy higher than 63%, surpassing the performance of a human expert by 9.0%.