Deep learning in breast cancer risk prediction: a review of recent applications in full-field digital mammography

Abstract

Breast Cancer (BC) remains one of the most commonly diagnosed cancers worldwide. Even though standard screening procedures have made positive impacts on disease burden, their accuracy remains limited. Personalized screening, based on individual risk, offers the potential to improve disease outcomes. While traditional risk models based on well-established factors, such as age and family history, are widely used, their discriminatory power is still insufficient. Artificial Intelligence (AI), already playing a role in breast cancer diagnosis, has the potential to make an impact on the field of risk prediction. AI models that utilize imaging biomarkers could help create more personalized risk profiles, enabling clinicians to adapt screening either in terms of imaging modality used or periodicity. Moreover, it also enables women to make changes to their lifestyle in order to diminish their risk of BC development. Therefore, this review fills a gap in the literature by exploring recent advancements in AI risk prediction using imaging biomarkers from Full-Field Digital Mammography. Moreover, this work also addresses challenges that must be overcome before clinical implementation.

Keywords: artificial intelligence; breast cancer; deep learning; digital mammography; risk prediction.

Figure 1

Screening process for paper inclusion on this review. First, duplicates were removed. Then, through title assessment, papers non-related to the research questions were removed. After that, non-original research papers were removed. Finally, the abstract of the 46 papers that remained were screened for relevance, resulting in 23 papers included in this review.

Figure 2

Distribution of papers by the year they were published.