Multi-Tasking U-Shaped Network for Benign and Malignant Classification of Breast Masses

Abstract

The benign and malignant (BM) classification of breast masses based on mammography is a key step in the diagnosis of early breast cancer and an effective way to improve the survival rate of patients. Nevertheless, due to the differences in size, shape and texture of breast masses and the visual similarity between masses of the same category, it is difficult to obtain a robust classification model using conventional deep learning methods. To address this problem, we proposed a Multi-Tasking U-shaped Network (MT-UNet), which contains three key ideas: 1) the U-shaped classification architecture constructed can well adapt to the heterogeneity of breast masses; 2) the combination of the proposed truncated normalization method and adaptive histogram equalization method can enhance the contrast of image; 3) training with label smoothing method can alleviate the problem of convergence difficulty caused by insufficient training data. The performance of the proposed scheme is evaluated on the public dataset of DDSM and INbreast. On the DDSM dataset, the Area Under Curve (AUC) and accuracy (ACC) reached 0.9963 and 0.9817, respectively. On the INbreast dataset, the AUC and ACC reached 0.9767 and 0.9391, respectively. Experimental results show that the proposed method can obtain a competitive performance.