Identification of Molecular Subtypes of Breast Cancer Based on Multimodal Deep Learning

Abstract

The identification of breast cancer subtypes plays a key role in the prognosis of breast cancer. In recent years, deep learning (DL) has shown good performance in intelligent identification of breast cancer subtypes. However, most of the traditional DL models use single-mode data, and the extracted features are limited, so the association between patient characteristics and breast cancer subtypes cannot be established stably. In order to improve the effect of recognition, this study proposes a multimodal fusion deep learning (MFDL) model. This model combined with the breast cancer gene modal data and image modal data established a multilayer perceptron network and the depth of the convolution neural network for feature extraction, and then based on the idea of weighted aggregation on the output of the two characteristics of the network integration. Finally, the fusion features were used to identify breast cancer subtypes. The experimental results show that compared with other models in AUC value, accuracy and other indicators, the MFDL model proposed in this study is more accurate and efficient in the identification of breast cancer subtypes.