🤖 AI Summary
This study proposes an integrated approach combining radiomics and the ConvNeXt deep learning model to improve the accuracy of early breast cancer diagnosis from mammographic images. The method uniquely integrates radiomic features with the ConvNeXtV1-small architecture and incorporates a prediction calibration strategy, achieving robust cross-dataset performance on two independent cohorts—RSNA and TecSalud. Experimental results demonstrate that the ensemble model attains an AUC of 0.87 on testing data, significantly outperforming standalone ConvNeXt (AUC: 0.83) and radiomics-based models (AUC: 0.80). These findings underscore the efficacy and generalizability of multimodal fusion in enhancing breast cancer screening.
📝 Abstract
Early diagnosis of breast cancer is crucial for improving survival rates. Radiomics and deep learning (DL) have shown significant potential in assisting radiologists with early cancer detection. This paper aims to critically assess the performance of radiomics, DL, and ensemble techniques in detecting cancer from screening mammograms. Two independent datasets were used: the RSNA 2023 Breast Cancer Detection Challenge (11,913 patients) and a Mexican cohort from the TecSalud dataset (19,400 patients). The ConvNeXtV1-small DL model was trained on the RSNA dataset and validated on the TecSalud dataset, while radiomics models were developed using the TecSalud dataset and validated with a leave-one-year-out approach. The ensemble method consistently combined and calibrated predictions using the same methodology. Results showed that the ensemble approach achieved the highest area under the curve (AUC) of 0.87, compared to 0.83 for ConvNeXtV1small and 0.80 for radiomics. In conclusion, ensemble methods combining DL and radiomics predictions significantly enhance breast cancer diagnosis from mammograms.