Semi-supervised GAN-based Radiomics Model for Data Augmentation in Breast Ultrasound Mass Classification. (May 2021)

• Record Type: Journal Article
• Authors: Pang, Ting; Wong, Jeannie Hsiu Ding; Ng, Wei Lin; Chan, Chee Seng
• Is Part Of: Computer methods and programs in biomedicine. Volume 203(2021)
• Publication Date: 2021-05
• Subjects: Deep learning radiomics -- Semi-supervised learning -- Generative adversarial network -- Data augmentation -- Breast cancer classification -- Ultrasound imaging; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106018
• Languages: English
• ISSNs: 0169-2607

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. Abstract: Background and Objective: The capability of deep learning radiomics (DLR) to extract high-level medical imaging features has promoted the use of computer-aided diagnosis of breast mass detected on ultrasound. Recently, generative adversarial network (GAN) has aided in tackling a general issue in DLR, i.e., obtaining a sufficient number of medical images. However, GAN methods require a pair of input and labeled images, which require an exhaustive human annotation process that is very time-consuming. The aim of this paper is to develop a radiomics model based on a semi-supervised GAN method to perform data augmentation in breast ultrasound images. Methods: A total of 1447 ultrasound images, including 767 benign masses and 680 malignant masses were acquired from a tertiary hospital. A semi-supervised GAN model was developed to augment the breast ultrasound images. The synthesized images were subsequently used to classify breast masses using a convolutional neural network (CNN). The model was validated using a 5-fold cross-validation method. Results: The proposed GAN architecture generated high-quality breast ultrasound images, verified by two experienced radiologists. The improved performance of semi-supervised learning increased the quality of the synthetic data produced in comparison to the baseline method. We achieved more accurate breast mass classification results (accuracy 90.41%, sensitivity 87.94%, specificity 85.86%) with our synthetic data augmentation compared to other state-of-the-art methods. Conclusion: The proposed radiomics model has demonstrated a promising potential to synthesize and classify breast masses on ultrasound in a semi-supervised manner.