Semi-supervised GAN-based Radiomics Model for Data Augmentation in Breast Ultrasound Mass Classification

Ting Pang, Jeannie Hsiu Ding Wong, Wei Lin Ng, Chee Seng Chan

Abstract: Highlights•Perform data augmentation for deep learning radiomics in a semi-supervised manner.•It develops a semi-supervised GAN model to augment the breast ultrasound images and the synthesized images are subsequently used to classify breast lesions using CNN.•It reduces the burden of annotation and generates high-quality of breast ultrasound masses.•It achieves more advanced breast mass classification results.