Segmenting breast ultrasound scans using a generative adversarial network embedding U-Net

Breast ultrasound imaging, due to its noninvasive nature and cost-effectiveness, has become an indispensable instrument in the early detection of breast cancer, highlighting the importance of early detection of lesions for timely intervention. In this study, we discuss possible problems deriving from using deep learning techniques on such images and propose novel solutions towards achieving a segmentation tool based on a generative adversarial network architecture. As a proof-of-concept, we build on existing methods to develop our system by modifying a U-Net known as Residual-Dilated-Attention-Gate with the addition of skip modules and dilated convolutional neural networks after the decoder stage. Compared with other state-of-the-art methods in established evaluation metrics, the results indicate that the proposed model achieves the highest accuracy of 98.11%, despite being trained on a limited number of epochs. However, it still requires further tuning and optimisation to enhance precision, ensuring that it is more balanced, robust, and thus competitive with the state-of-the-art.