A Vision Transformer Network With Wavelet-Based Features for Breast Ultrasound Classification

Abstract

Breast cancer is a prominent contributor to mortality associated with cancer in the female population on a global scale. The timely identification and precise categorization of breast cancer are of utmost importance in enhancing patient prognosis. Nevertheless, the task of precisely categorizing breast cancer based on ultrasound imaging continues to present difficulties, primarily due to the presence of dense breast tissues and their inherent heterogeneity. This study presents a unique approach for breast cancer categorization utilizing the wavelet based vision transformer network. To enhance the neural network’s receptive fields, we have incorporated the discrete wavelet transform (DWT) into the network input. This technique enables the capture of significant features in the frequency domain. The proposed model exhibits the capability to effectively capture intricate characteristics of breast tissue, hence enabling correct classification of breast cancer with a notable degree of precision and efficiency. We utilized two breast tumor ultrasound datasets, including 780 cases from Baheya hospital in Egypt and 267 patients from the UDIAT Diagnostic Centre of Sabadell in Spain. The findings of our study indicate that the proposed transformer network achieves exceptional performance in breast cancerclassification. With an AUC rate of 0.984 and 0.968 on both datasets, our approach surpasses conventional deep learning techniques, establishing itself as the leading method in this domain. This study signifies a noteworthy advancement in the diagnosis and categorization of breast cancer, showcasing the potential of the proposed transformer networks to enhance the efficacy of medical imaging analysis.