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 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.

Keywords: Breast cancer; Deep learning; Multimodal prediction; Neoadjuvant treatment.

Fig. 1

Flow diagram of preferred reporting items for systematic reviews and meta-analyses (PRISMA). DL, deep learning

Fig. 2

Sankey diagram showing the distribution of primary, secondary and tertiary modalities among the 51 studies included in this review. The left column indicates each study’s primary data modality, the middle column its secondary data modality, and the right column its tertiary data modality. Flow widths are proportional to the number of studies integrating a data modality level with the next. MRI, Magnetic Resonance Imaging; DP, Digital pathology; US, Ultrasonography (Ultrasound); CT, Computed tomography; MG, Mammography; PET, Positron emission tomography; RNA, RNA Sequencing data; Clinical: Clinical data; None, No additional data modality. Numbers in parentheses denote study counts (n) for each modality at the given level

Fig. 3

Bubble plot displaying the median Area Under the Receiver Operating Characteristic Curve (AUC) of studies grouped based on the deep learning (DL) architecture utilized. Each circle represents a set of studies, with relative dimension representing the number of studies included. CNN, Convolutional neural network; CNN + , Convolutional neural network augmented with additional modules like Attention mechanisms, etc.; TRA, Transformer architecture; CML, Classical machine learning