An Ultra-Fast Method for Simulation of Realistic Ultrasound Images

@article{Sharifzadeh2021AnUM,
  title={An Ultra-Fast Method for Simulation of Realistic Ultrasound Images},
  author={M. Sharifzadeh and Habib Benali and Hassan Rivaz},
  journal={2021 IEEE International Ultrasonics Symposium (IUS)},
  year={2021},
  pages={1-4}
}
Convolutional neural networks (CNNs) have attracted a rapidly growing interest in a variety of different processing tasks in the medical ultrasound community. However, the performance of CNNs is highly reliant on both the amount and fidelity of the training data. Therefore, scarce data is almost always a concern, particularly in the medical field, where clinical data is not easily accessible. The utilization of synthetic data is a popular approach to address this challenge. However, simulating… 

Figures and Tables from this paper

A Disentanglement and Fusion Data Augmentation Approach for Echocardiography Segmentation

The feasibility of the proposed data augmentation approach in overcoming the shortage of labeled medical image dataset is demonstrated on the task of left ventricle (LV) segmentation in echocardiography.

References

SHOWING 1-10 OF 22 REFERENCES

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Freehand Ultrasound Image Simulation with Spatially-Conditioned Generative Adversarial Networks

This paper introduces a novel neural network architecture that can sample anatomically accurate images conditionally on spatial position of the (real or mock) freehand ultrasound probe, based on conditional generative adversarial networks (GANs), and presents what it believes are state-of-the-art visually realistic ultrasound images simulated by the proposed GAN architecture.

Realistic synthesis of brain tumor resection ultrasound images with a generative adversarial network

This paper simulated intraoperative US images of the brain after tumor resection surgery with a Generative Adversarial Networks and found that these synthesized images are hardly distinguishable from real post-resection US images.

Ultrasound image simulation with generative adversarial network

Generative adversarial networks appear to be a promising method of simulating realistic ultrasound images from crosssectional anatomical label-maps by evaluating the realism of kidney ultrasound images generated using adversarial Networks.

Simulating patho-realistic ultrasound images using deep generative networks with adversarial learning

  • Francis TomD. Sheet
  • Computer Science
    2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
  • 2018
A generative adversarial network (GAN) inspired approach for fast simulation of patho-realistic ultrasound images with a visual Turing test indicating an equivocal confusion in discriminating simulated from real is proposed.

Real-Time GPU-Based Ultrasound Simulation Using Deformable Mesh Models

The main focus of the simulator is to synthesize realistic looking ultrasound images in real-time including artifacts, which are essential for the interpretation of this data, based on a convolution-enhanced ray-tracing approach and uses a deformable mesh model.

Automated Breast Ultrasound Lesions Detection Using Convolutional Neural Networks

This paper proposes the use of deep learning approaches for breast ultrasound lesion detection and investigates three different methods: a Patch-based LeNet, a U-Net, and a transfer learning approach with a pretrained FCN-AlexNet.

Synthesis and Edition of Ultrasound Images via Sketch Guided Progressive Growing GANS

By synthesizing ovary and follicle US images, the extensive perceptual evaluation, user study and segmentation results prove the promising efficacy and efficiency of the proposed PGSgan.

Deep Network for Scatterer Distribution Estimation for Ultrasound Image Simulation

A convolutional neural network approach for probabilistic scatterer estimation from observed US data is demonstrated and it is demonstrated that the synthesized images from scatterers representations estimated with this approach closely match the observations with varying acquisition parameters such as compression and rotation of the imaged domain.

Paper presented at the 10th Nordic-Baltic Conference on Biomedical Imaging: Field: A Program for Simulating Ultrasound Systems

A program for the simulation of ultrasound systems is presented. It is based on the Tupholme-Stepanishen method, and is fast because of the use of a fareld approximation. Any kind of transducer