RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication
Artículo científico (JournalArticle)
Ultrasound breast images denoising using generative adversarial networks (GANs)
[EN] Ultrasound in conjunction with mammography imaging, plays a vital role in the early detection and diagnosis of breast cancer. However, speckle noise affects medical ultrasound images and degrades visual radiological interpretation.
Speckle carries information about the interactions of the ultrasound pulse with the tissue microstructure, which generally causes
several difficulties in identifying malignant and benign regions. The application of deep learning in image denoising has gained
more attention in recent years. The main objective of this work is to reduce speckle noise while preserving features and details in breast
ultrasound images using GAN models.
We proposed two GANs models (Conditional GAN and Wasserstein GAN) for speckle-denoising public breast
ultrasound databases: BUSI, DATASET A, AND UDIAT (DATASET B). The Conditional GAN model was trained using the
Unet architecture, and the WGAN model was trained using the Resnet architecture. The image quality results in both algorithms
were measured by Peak Signal to Noise Ratio (PSNR, 35¿40 dB) and Structural Similarity Index (SSIM, 0.90¿0.95) standard
values.
The experimental analysis clearly shows that the Conditional GAN model achieves better breast ultrasound despeckling performance over the datasets in terms of PSNR = 38.18 dB and SSIM = 0.96 with respect to the WGAN model
(PSNR = 33.0068 dB and SSIM = 0.91) on the small ultrasound training datasets.
CONCLUSIONS: The observed performance differences between CGAN and WGAN will help to better implement new tasks
in a computer-aided detection/diagnosis (CAD) system. In future work, these data can be used as CAD input training for image
classification, reducing overfitting and improving the performance and accuracy of deep convolutional algorithms., This project has been co-financed by the Spanish Government Grant Deepbreast PID2019-107790RBC22 funded by MCIN/AEI/10.13039/501100011033.