Wave equation based transmission tomography

Gemmeke, H.; Althaus, Lea; Dongen, Koen W. A. van; Egger, Herbert; Hesser, Jürgen; Mayer, Jana; Ruiter, Nicole V.; Zapf, Michael; Hopp, Torsten

doi:10.1109/ultsym.2016.7728829

Cited by 9 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare mWnet 1 and mWnet 4 with three neural networks: Automap, UNet, and FC-DenseNet, and two other traditional reconstruction algorithms that use different optimization methods: Gauss Newton CG [14] and L-BFGS [13] on a laptop with CPU Intel Core i5 8400 2.80GHz and GPU Nvidia GeForce RTX 2070. All the algorithms are tested with their optimal default settings, where the maximum iteration numbers for Gauss Newton CG and L-BFGS are 500 and 100, respectively.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Ultrasound transmission tomography image reconstruction with a fully convolutional neural network

Zhao¹,

Wang²,

Gemmeke³

et al. 2020

Phys. Med. Biol.

Self Cite

View full text Add to dashboard Cite

Image reconstruction of ultrasound computed tomography based on wave equation is able to show much more structural details than simpler ray-based image reconstruction methods. However, to invert the wave-based forward model is computationally demanding. To address this problem, we develop an efficient fully learned image reconstruction method based on a convolutional neural network. The image is reconstructed via one forward propagation of the network given input sensor data, which is much faster than the reconstruction using conventional iterative optimization methods. To transform the ultrasound measured data in the sensor domain into the reconstructed image in the image domain, we apply multiple downscaling and up-scaling convolutional units to efficiently increase the number of hidden layers with a large receptive and projective field that can cover all elements in inputs and outputs, respectively. For dataset generation, a paraxial approximation forward model is used to simulate ultrasound measurement data. The neural network is trained with a dataset derived from natural images in ImageNet and tested with a dataset derived from medical images in OA-Breast Phantom dataset. Test results show the superior efficiency of the proposed neural network to other reconstruction algorithms including popular neural networks. When compared with conventional iterative optimization algorithms, our neural network can reconstruct a 110 × 86 image more than 20 times faster on CPU and 1000 times faster on GPU with comparable image quality and is also more robust to noise.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Recently, this approximation method has been combined with various optimization methods to accelerate the reconstruction (Wang et al 2019). However, this iterative optimization reconstruction strategy is sensitive to noise and needs regularization (Gemmeke et al 2016).…”

Section: Introductionmentioning

confidence: 99%