Deep Learning for Contrast Enhanced Mammography - a Systematic Review

Abstract

Background/Aim: Contrast-enhanced mammography (CEM) is a relatively novel imaging technique that enables both anatomical and functional breast imaging, with improved diagnostic performance compared to standard 2D mammography. The aim of this study is to systematically review the literature on deep learning (DL) applications for CEM, exploring how these models can further enhance CEM diagnostic potential. Methods: This systematic review was reported according to the PRISMA guidelines. We searched for studies published up to April 2024. MEDLINE, Scopus and Google Scholar were used as search databases. Two reviewers independently implemented the search strategy. Results: Sixteen relevant studies published between 2018 and 2024 were identified. All studies but one used convolutional neural network models. All studies evaluated DL algorithms for classification of lesions at CEM, while six studies also assessed lesion detection or segmentation. In three studies segmentation was performed manually, two studies evaluated both manual and automatic segmentation, and ten studies automatically segmented the lesions. Conclusion: While still at an early research stage, DL can improve CEM diagnostic precision. However, there is a relatively small number of studies evaluating different DL algorithms, and most studies are retrospective. Further prospective testing to assess performance of applications at actual clinical setting is warranted.