SpeckleGAN: a generative adversarial network with an adaptive speckle layer to augment limited training data for ultrasound image processing

Purpose In the field of medical image analysis, deep learning methods gained huge attention over the last years. This can be explained by their often improved performance compared to classic explicit algorithms. In order to work well, they need large amounts of annotated data for supervised learning, but these are often not available in the case of medical image data. One way to overcome this limitation is to generate synthetic training data, e.g., by performing simulations to artificially augment the dataset. However, simulations require domain knowledge and are limited by the complexity of the underlying physical model. Another method to perform data augmentation is the generation of images by means of neural networks. Methods We developed a new algorithm for generation of synthetic medical images exhibiting speckle noise via generative adversarial networks (GANs). Key ingredient is a speckle layer, which can be incorporated into a neural network in order to add realistic and domain-dependent speckle. We call the resulting GAN architecture SpeckleGAN. Results We compared our new approach to an equivalent GAN without speckle layer. SpeckleGAN was able to generate ultrasound images with very crisp speckle patterns in contrast to the baseline GAN, even for small datasets of 50 images. SpeckleGAN outperformed the baseline GAN by up to 165 % with respect to the Fréchet Inception distance. For artery layer and lumen segmentation, a performance improvement of up to 4 % was obtained for small datasets, when these were augmented with images by SpeckleGAN. Conclusion SpeckleGAN facilitates the generation of realistic synthetic ultrasound images to augment small training sets for deep learning based image processing. Its application is not restricted to ultrasound images but could be used for every imaging methodology that produces images with speckle such as optical coherence tomography or radar.

[1]  J. Goodman.  Introduction to Fourier optics , 1969 .

[2]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[3]  Pabitra Mitra,et al.  Segmentation of Lumen and External Elastic Laminae in Intravascular Ultrasound Images Using Ultrasonic Backscattering Physics Initialized Multiscale Random Walks , 2016, ICVGIP Workshops.

[4]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  E. Gerardo Mendizabal-Ruiz,et al.  Computerized Medical Imaging and Graphics , 2022 .

[6]  Taesung Park,et al.  Semantic Image Synthesis With Spatially-Adaptive Normalization , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Anil K. Jain,et al.  A modified Hausdorff distance for object matching , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[8]  Anup Basu,et al.  Robust segmentation of arterial walls in intravascular ultrasound images using Dual Path U-Net. , 2019, Ultrasonics.

[9]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[11]  Marius Erdt,et al.  Synthesis of Medical Images Using GANs , 2019, UNSURE/CLIP@MICCAI.

[12]  J. Goodman.  Speckle Phenomena in Optics: Theory and Applications , 2020 .

[13]  Sotirios A. Tsaftaris,et al.  Medical Image Computing and Computer Assisted Intervention , 2017 .

[14]  Nagiza F. Samatova,et al.  Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data , 2016, IEEE Transactions on Knowledge and Data Engineering.

[15]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[16]  Taghi M. Khoshgoftaar,et al.  A survey on Image Data Augmentation for Deep Learning , 2019, Journal of Big Data.

[17]  C. Burckhardt.  Speckle in ultrasound B-mode scans , 1978, IEEE Transactions on Sonics and Ultrasonics.

[18]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[19]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[20]  B. Norrving,et al.  Global atlas on cardiovascular disease prevention and control. , 2011 .

[21]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[22]  Heinz Handels,et al.  Multi-scale GANs for Memory-efficient Generation of High Resolution Medical Images , 2019, MICCAI.

[23]  Debdoot Sheet,et al.  Simulating patho-realistic ultrasound images using deep generative networks with adversarial learning , 2017, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).