RAE-Net: a multi-modal neural network based on feature fusion and evidential deep learning algorithm in predicting breast cancer subtypes on DCE-MRI

Objectives Accurate identification of molecular subtypes in breast cancer is critical for personalized treatment. This study introduces a novel neural network model, RAE-Net, based on Multimodal Feature Fusion (MFF) and the Evidential Deep Learning Algorithm (EDLA) to improve breast cancer subtype prediction using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Methods A dataset of 344 patients with histologically confirmed breast cancer was divided into training (n = 200), validation (n = 60), and testing (n = 62) cohorts. RAE-Net, built on ResNet-50 with Multi-Head Attention (MHA) fusion and Multi-Layer Perceptron (MLP) mechanisms, combines radiomic and deep learning features for subtype prediction. The EDLA module adds uncertainty estimation to enhance classification reliability. Results The RAE-Net model incorporating the MFF module demonstrated superior performance, achieving a mean accuracy of 0.83 and a Macro-F1 score of 0.78, surpassing traditional radiomics models (accuracy: 0.79, Macro-F1: 0.75) and standalone deep learning models (accuracy: 0.80, Macro-F1: 0.76). When an EDLA uncertainty threshold of 0.2 was applied, the performance significantly improved, with accuracy reaching 0.97 and Macro-F1 increasing to 0.92. Additionally, RAE-Net outperformed two recent deep learning networks, ResGANet and HIFUSE. Specifically, RAE-Net showed a 0.5% improvement in accuracy and a higher AUC compared to ResGANet. In comparison to HIFUSE, RAE-Net reduced both the number of parameters and computational cost by 90% while only increasing computation time by 5.7%. Conclusions RAE-Net integrates feature fusion and uncertainty estimation to predict breast cancer subtypes from DCE-MRI. The model achieves high accuracy while maintaining computational efficiency, demonstrating its potential for clinical use as a reliable and resource-efficient diagnostic tool.