AI-based Strategies in Breast Mass ≤ 2cm classification with Mammography and Tomosynthesis: A Retrospective Evaluation

Abstract

Abstract Purpose To evaluate the efficiency of digital mammography (DM) and combined digital breast tomosynthesis (DBT) on AI-based strategies for breast mass ≤ 2cm classification. Methods DM and DBT images in 483 patients including 512 breast masses were acquired from November 2018 to November 2019. The radiomics and deep learning methods were employed to extract the breast mass features in images and finally for benign and malignant classification. The DM and combined DBT (DM+DBT) images were fed into radiomics and deep learning models to construct corresponding models, respectively. The area under the receiver operating characteristic curve (AUC) was estimated models performance. A comprehensive comparison of the subgroups AUCs of the best optimal model was calculated on age, tumor size, and breast density category. Results In the testing dataset, the AUC of DM combined DBT by radiomics and deep learning models were 0.869 and 0.908, respectively. Compared with the DM model, the combined DBT models based on radiomics and deep learning both showed statistically significant higher AUCs (0.869 vs. 0.810, P<0.001, by radiomics; 0.908 vs. 0.867, P<0.001, by deep learning). The deep learning models present superior than the radiomics models in the experiments with only DM (P<0.001) and DM+DBT (P<0.003). The advantage of the deep learning model is especially prominent in patients with small masses less than 1cm, 20 to 40 years old, and dense breast. Conclusions Deep learning model based on DM+DBT has a best diagnostic efficiency. AI-based stragies will play a major role in detecting early breast cancer in screening.