Ting Pang1, Jeannie Hsiu Ding Wong2, Wei Lin Ng3, Chee Seng Chan4. 1. Center of Image and Signal Processing, Faculty of Computer Science and Infomation Technology, University of Malaya, Kuala Lumpur, 50603, Malaysia; Center of Network and Information, Xinxiang Medical University, Xinxiang, 453000, PR China. 2. Department of Biomedical Imaging, Faculty of Medicine, University of Malaya, Kuala Lumpur, 50603, Malaysia. Electronic address: jeannie.wong@ummc.edu.my. 3. Department of Biomedical Imaging, Faculty of Medicine, University of Malaya, Kuala Lumpur, 50603, Malaysia. 4. Center of Image and Signal Processing, Faculty of Computer Science and Infomation Technology, University of Malaya, Kuala Lumpur, 50603, Malaysia.
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.
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.
Keywords:
Breast cancer classification; Data augmentation; Deep learning radiomics; Generative adversarial network; Semi-supervised learning; Ultrasound imaging
Authors: Elisa Moya-Sáez; Rafael Navarro-González; Santiago Cepeda; Ángel Pérez-Núñez; Rodrigo de Luis-García; Santiago Aja-Fernández; Carlos Alberola-López Journal: NMR Biomed Date: 2022-05-21 Impact factor: 4.478