Transfer Learning for Data Fusion for Electromagnetic and Ultrasound Breast Imaging

Abstract

Aiming at improved breast imaging, this contribution explores several scenarios for segmenting and estimating the distribution of electromagnetic (EM) and/or ultrasonic (US) parameters within breast tissue. A two-fold approach is adopted, leveraging Transfer Learning (TL) through Bayesian Neural Networks (BNN); the first objective is to consistently enhance imaging results, and the second is to establish a novel framework for data fusion transfer learning. The methodological approach is tailored for Artificial, Convolutional, and Bayesian Neural Networks, showcasing its effectiveness through the analysis of electromagnetic (EM) and ultrasonic (US) datasets computed in reliable scenarios, with a focus on heterogeneously dense and extremely dense breasts. Furthermore, a novel transfer learning Bayesian data fusion framework incorporating multi-frequency data exploits the complementary nature of EM low-resolution and US high-resolution imaging. By enhancing the fusion of EM and US data, this framework leads to better-contrasted zones in the images and is shown to outperform the most common transfer learning approaches.