Breast Tumor Classification With Attention Model Enhancement Network
Xiao Kang, Shaohua Wang, Fei Dong, Xingbo Liu · 2023
Breast tumor classification remains challenging due to its inter-class ambiguity and intra-class variability. Existing deep learning-based methods typically adopt convolutional neural networks and complex nonlinear projections to extract global features from entire images. However, they usually neglect some local features that may be crucial in improving classification accuracy. To this end, we propose a novel breast tumor classification method, named Attention Model Enhancement Network (AMEN), which is formulated in a multi-branch iterative fashion. In each branch, we design the flexible and adaptive attention mechanism for generating pixel-wise weights; thereafter, the inputs in the next branch are enhanced by this weight information for obtaining more discriminative features. Meanwhile, a boosting strategy is designed to fuse multi-branch classification results for better performance. Experiments conducted on three benchmark datasets demonstrate the superiority of the proposed method under various scenarios.