Multimodal data integration in early-stage breast cancer

Abstract

Deep learning; Multi-omics; Multimodal data integration

Aprenentatge profund; Multiòmica; Integració de dades multimodal

Aprendizaje profundo; Multiómica; Integración de datos multimodales

The use of biomarkers in breast cancer has significantly improved patient outcomes through targeted therapies, such as hormone therapy anti-Her2 therapy and CDK4/6 or PARP inhibitors. However, existing knowledge does not fully encompass the diverse nature of breast cancer, particularly in triple-negative tumors. The integration of multi-omics and multimodal data has the potential to provide new insights into biological processes, to improve breast cancer patient stratification, enhance prognosis and response prediction, and identify new biomarkers. This review presents a comprehensive overview of the state-of-the-art multimodal (including molecular and image) data integration algorithms developed and with applicability to breast cancer stratification, prognosis, or biomarker identification. We examined the primary challenges and opportunities of these multimodal data integration algorithms, including their advantages, limitations, and critical considerations for future research. We aimed to describe models that are not only academically and preclinically relevant, but also applicable to clinical settings.

This work was supported by Spanish Ministry of Science, Innovation and Universities [FPU22/03520] (to MB), Programa Talentos Fundació Catalunya La Pedrera (to VB), AEI grants, including the Severo OchoaCenter of Excellence (FPI PRE2021-096930 (to ALB)); CMS2022-135428, RYC2019-026576-I, PID2020-115097RA-I00, FERO Breast Cancer Award, ISCIII grant (FORT23/00034); and Fundacion “la Caixa” (to JAS).