Non-Ionic Deep Learning-Driven IR-UWB Multiantenna Scheme for Breast Tumor Localization

This research proposes a deep learning-driven impulse radio ultra-wideband (IR-UWB) multiantenna scheme for non-ionic breast tumor localization. The structure of the multiantenna scheme consists of one side slot Vivaldi transmitting (Tx) and nine side slot Vivaldi receiving (Rx₁ – Rx₉) antennas. To mitigate the attenuation and improve the diagnostic accuracy, the multiantenna scheme is rotated clockwise in 90° increments around the breast, with the angular position of the Tx antenna of 0°, 90°, 180°, and 270°. The deep learning algorithm is utilized to detect and localize the breast tumor, with 17 classification outputs, consisting of classifications 1 – 16 which correspond to 16 vertically discretized segments of the breast and classification 17 for cancer-free. Experiments were carried out using heterogenous breast replicas with a tumor of 1 cm in diameter, and the breast replicas possess the dielectric property and Hounsfield units (HU) similar to those of human breasts. The experimental results were compared with the computed tomography (CT) scan images. The results reveal that the multiantenna scheme could efficiently detect and accurately localize the breast tumor for nearly all classifications, with the total accuracy (average of F1 scores) of 99.11 %. Specifically, the novelty of this research lies in the use of deep learning with the IR-UWB technology to effectively localize breast tumors.