Real-time simulator for intravascular ultrasound (IVUS)

Abkai, Ciamak; Becherer, Nico; Hesser, Jürgen; Männer, Reinhard

doi:10.1117/12.709115

Cited by 6 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…-Generative image-based simulators: simulated images are created from existing images obtained from other modalities [6], such as MRI or CT; the output is heavily dependent on the simulation method. Images are normally not very realistic because MRI or CT images are maps of different physical properties [7], and some structures that are visible in ultrasound are just not captured with MRI or CT. -Generative model-based simulators: this category includes two classes: first, physics-based simulators, where a physics simulator is used to produce ultrasound images from a virtual tissue model of anatomy with ultrasoundrelevant properties (elasticity, density, etc) [8,9,10,11]. Non-linear modelling of ultrasound propagation through medium is a computationally expensive process and these methods need to trade-off between accuracy and realtimeness, hence are typically not suitable for interactive simulations.…”

Section: Related Workmentioning

confidence: 99%

Deep Generative Models to Simulate 2D Patient-Specific Ultrasound Images in Real Time

Magnetti¹,

Zimmer²,

Ghavami³

et al. 2020

Preprint

View full text Add to dashboard Cite

We present a computational method for real-time, patientspecific simulation of 2D ultrasound (US) images. The method uses a large number of tracked ultrasound images to learn a function that maps position and orientation of the transducer to ultrasound images. This is a first step towards realistic patient-specific simulations that will enable improved training and retrospective examination of complex cases. Our models can simulate a 2D image in under 4ms (well within real-time constraints), and produce simulated images that preserve the content (anatomical structures and artefacts) of real ultrasound images.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Generative Models to Simulate 2D Patient-Specific Ultrasound Images in Real Time

Magnetti¹,

Zimmer²,

Ghavami³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Numerical modeling based approaches have employed ray-based model to simulate ultrasound from volumetric CT scans [4], and with the Born approximation [5] have also simulated images using histopathology based digital phantoms employing wave equations [6,7,8]. Further Rayleigh scattering model [9], physical reflection, transmission and absorption have also been included in simulation [10]. Commercially available solutions like Field II simulator 2 have used a finite element model for the purpose.…”

Section: Prior Artmentioning

confidence: 99%

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

Tom

Sheet

2018

2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)

View full text Add to dashboard Cite

Ultrasound imaging makes use of backscattering of waves during their interaction with scatterers present in biological tissues. Simulation of synthetic ultrasound images is a challenging problem on account of inability to accurately model various factors of which some include intra-/inter scanline interference, transducer to surface coupling, artifacts on transducer elements, inhomogeneous shadowing and nonlinear attenuation. Current approaches typically solve wave space equations making them computationally expensive and slow to operate. We propose a generative adversarial network (GAN) inspired approach for fast simulation of patho-realistic ultrasound images. We apply the framework to intravascular ultrasound (IVUS) simulation. A stage 0 simulation performed using pseudo B-mode ultrasound image simulator yields speckle mapping of a digitally defined phantom. The stage I GAN subsequently refines them to preserve tissue specific speckle intensities. The stage II GAN further refines them to generate high resolution images with patho-realistic speckle profiles. We evaluate patho-realism of simulated images with a visual Turing test indicating an equivocal confusion in discriminating simulated from real. We also quantify the shift in tissue specific intensity distributions of the real and simulated images to prove their similarity.Index Terms-Adversarial learning, deep convolutional neural network, generative adversarial network, intravascular ultrasound, ultrasound simulation.

show abstract

“…For example in [1], the Born approximation and a scatterer model were used and in [2] a ray-tracing algorithm on histopathology was deployed. Authors in [3] included Rayleigh scattering, physical reflection, transmission and absorption to realize a real-time simulation. In [4], a finite element model was combined with speckles incorporated by Field II.…”

Section: Introductionmentioning

confidence: 99%

Full-Wave Intravascular Ultrasound Simulation from Histology

Kraft

Conjeti

Noël

et al. 2014

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014

View full text Add to dashboard Cite

In this paper, we introduce a framework for simulating intravascular ultrasound (IVUS) images and radiofrequency (RF) signals from histology image counterparts. We modeled the wave propagation through the Westervelt equation, which is solved explicitly with a finite differences scheme in polar coordinates by taking into account attenuation and non-linear effects. Our results demonstrate good correlation for textural and spectral information driven from simulated IVUS data in contrast to real data, acquired with single-element mechanically rotating 40 MHz transducer, as ground truth.

show abstract

Real-time simulator for intravascular ultrasound (IVUS)

Cited by 6 publications

References 0 publications

Deep Generative Models to Simulate 2D Patient-Specific Ultrasound Images in Real Time

Deep Generative Models to Simulate 2D Patient-Specific Ultrasound Images in Real Time

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

Full-Wave Intravascular Ultrasound Simulation from Histology

Contact Info

Product

Resources

About