Multimodal deep learning for predicting neoadjuvant treatment outcomes in breast cancer: a systematic review

Multimodal deep learning for predicting neoadjuvant treatment outcomes in breast cancer: a systematic review

Abstract Background Pathological complete response (pCR) to neoadjuvant systemic therapy (NAST) is an established prognostic marker in breast cancer (BC). Multimodal deep learning (DL), integrating diverse data sources (radiology, pathology, omics, clinical), holds promise for improving pCR predicti...

Full description

Saved in:
Bibliographic Details
Main Authors: Eriseld Krasniqi, Lorena Filomeno, Teresa Arcuri, Gianluigi Ferretti, Simona Gasparro, Alberto Fulvi, Arianna Roselli, Loretta D’Onofrio, Laura Pizzuti, Maddalena Barba, Marcello Maugeri-Saccà, Claudio Botti, Franco Graziano, Ilaria Puccica, Sonia Cappelli, Fabio Pelle, Flavia Cavicchi, Amedeo Villanucci, Ida Paris, Fabio Calabrò, Sandra Rea, Maurizio Costantini, Letizia Perracchio, Giuseppe Sanguineti, Silvia Takanen, Laura Marucci, Laura Greco, Rami Kayal, Luca Moscetti, Elisa Marchesini, Nicola Calonaci, Giovanni Blandino, Giulio Caravagna, Patrizia Vici
Format: Article
Language:English
Published: BMC 2025-06-01
Series:Biology Direct
Subjects:
Breast cancer
Neoadjuvant treatment
Deep learning
Multimodal prediction
Online Access:https://doi.org/10.1186/s13062-025-00661-8
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract Background Pathological complete response (pCR) to neoadjuvant systemic therapy (NAST) is an established prognostic marker in breast cancer (BC). Multimodal deep learning (DL), integrating diverse data sources (radiology, pathology, omics, clinical), holds promise for improving pCR prediction accuracy. This systematic review synthesizes evidence on multimodal DL for pCR prediction and compares its performance against unimodal DL. Methods Following PRISMA, we searched PubMed, Embase, and Web of Science (January 2015–April 2025) for studies applying DL to predict pCR in BC patients receiving NAST, using data from radiology, digital pathology (DP), multi-omics, and/or clinical records, and reporting AUC. Data on study design, DL architectures, and performance (AUC) were extracted. A narrative synthesis was conducted due to heterogeneity. Results Fifty-one studies, mostly retrospective (90.2%, median cohort 281), were included. Magnetic resonance imaging and DP were common primary modalities. Multimodal approaches were used in 52.9% of studies, often combining imaging with clinical data. Convolutional neural networks were the dominant architecture (88.2%). Longitudinal imaging improved prediction over baseline-only (median AUC 0.91 vs. 0.82). Overall, the median AUC across studies was 0.88, with 35.3% achieving AUC ≥ 0.90. Multimodal models showed a modest but consistent improvement over unimodal approaches (median AUC 0.88 vs. 0.83). Omics and clinical text were rarely primary DL inputs. Conclusion DL models demonstrate promising accuracy for pCR prediction, especially when integrating multiple modalities and longitudinal imaging. However, significant methodological heterogeneity, reliance on retrospective data, and limited external validation hinder clinical translation. Future research should prioritize prospective validation, integration underutilized data (multi-omics, clinical), and explainable AI to advance DL predictors to the clinical setting.
ISSN:1745-6150

Similar Items