Deep Multiinstance Mammogram Classification With Region Label Assignment Strategy and Metric-Based Optimization

Abstract

Mammography is one of the most widely used and effective ways to screen early breast cancer. Convolutional-neural-network-based methods have obtained promising results for automatic mammography diagnosis. However, most of those approaches ignore the relationship between global and local characteristics of mammograms and lose sight of the relationship between different views of a patient. This study designs a novel region label assignment strategy, which takes advantage of all regions in each mammogram from a patient by assigning different labels to different regions and calculating the loss for each region separately. This approach enables the classifier to distinguish variable and tiny lesions in complex global conditions better. Only one case-level classification label is needed for diagnosing one patient (case). Moreover, the categories of mammogram data sets are always imbalanced. To address this problem, this study designs an area under the receiver operating characteristic curve (AUC)-based optimization method on minibatch strategy. Experimental results on a constructed data set and two publicly available data sets demonstrate that the proposed method performs satisfactorily compared with state-of-the-art mammogram classifiers. Visualization results show the proposed method can find out mammograms containing malignant lesions and illustrate the rough location of lesions.