Your new experience awaits. Try the new design now and help us make it even better

REVIEW article

Front. Oncol.

Sec. Cancer Imaging and Image-directed Interventions

Volume 15 - 2025 | doi: 10.3389/fonc.2025.1656842

Deep Learning in Breast Cancer Risk Prediction: A Review of Recent Applications in Full-Field Digital Mammography

Provisionally accepted
João MendesJoão Mendes1,2Bernardo OliveiraBernardo Oliveira3Carolina AraújoCarolina Araújo3Joana GalrãoJoana Galrão3Ana Margarida MotaAna Margarida Mota2*Nuno C. GarciaNuno C. Garcia1Nuno MatelaNuno Matela2
  • 1LASIGE Laboratorio de Sistemas Informaticos de Grande Escala, Lisbon, Portugal
  • 2Instituto de Biofísica e Engenharia Biomédica, Faculdade de Ciências, Universidade de Lisboa, Lisbon, Portugal
  • 3Departamento de Física, Faculdade de Ciências, Universidade de Lisboa, Lisbon, Portugal

The final, formatted version of the article will be published soon.

Select one of your emails

You have multiple emails registered with Frontiers:

Notify me on publication

Please enter your email address:

If you already have an account, please login

You don't have a Frontiers account ? You can register here

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, risk prediction, Digital Mammography, deep learning

Received: 30 Jun 2025; Accepted: 18 Aug 2025.

Copyright: © 2025 Mendes, Oliveira, Araújo, Galrão, Mota, Garcia and Matela. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Ana Margarida Mota, Instituto de Biofísica e Engenharia Biomédica, Faculdade de Ciências, Universidade de Lisboa, Lisbon, Portugal

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

Supplementary Material