2000 character limit reached
Neural Born Series Operator for Biomedical Ultrasound Computed Tomography (2312.15575v1)
Published 25 Dec 2023 in eess.IV, cs.CV, and cs.LG
Abstract: Ultrasound Computed Tomography (USCT) provides a radiation-free option for high-resolution clinical imaging. Despite its potential, the computationally intensive Full Waveform Inversion (FWI) required for tissue property reconstruction limits its clinical utility. This paper introduces the Neural Born Series Operator (NBSO), a novel technique designed to speed up wave simulations, thereby facilitating a more efficient USCT image reconstruction process through an NBSO-based FWI pipeline. Thoroughly validated on comprehensive brain and breast datasets, simulated under experimental USCT conditions, the NBSO proves to be accurate and efficient in both forward simulation and image reconstruction. This advancement demonstrates the potential of neural operators in facilitating near real-time USCT reconstruction, making the clinical application of USCT increasingly viable and promising.
- fastMRI: An open dataset and benchmarks for accelerated MRI. arXiv, 2019.
- Source encoding for viscoacoustic ultrasound computed tomography. The Journal of the Acoustical Society of America, 147(5):3221--3235, 2020.
- Ultrasonic computed tomography based on full-waveform inversion for bone quantitative imaging. Physics in Medicine and Biology, 62(17):7011--7035, 2017.
- DeepM&mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks. Journal of Computational Physics, 436:110296, 2021.
- Spatial response identification enables robust experimental ultrasound computed tomography. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 69(1):27--37, 2022.
- Neural Operator Learning for Ultrasound Tomography Inversion. arXiv, 2023.
- DeepONet prediction of linear instability waves in high-speed boundary layers. arXiv, 2021.
- Quantitative sound speed imaging of cortical bone and soft tissue: Results from observational data sets. IEEE Transactions on Medical Imaging, 41(3):502--514, 2022.
- Full-waveform inversion imaging of the human brain. npj Digital Medicine, 3(1):28, 2020.
- Adaptive fourier neural operators: Efficient token mixers for transformers. arXiv, 2022.
- Elastic vertically transversely isotropic full-waveform inversion: From synthetic to field data. Geophysics, 88(3):1MJ--V289, 2023.
- Breast ultrasound waveform tomography: using both transmission and reflection data, and numerical virtual point sources. In Medical Imaging 2014: Ultrasonic Imaging and Tomography, pages 187--198. SPIE, 2014.
- Segment anything. arXiv, 2023.
- Convergent born series improves the accuracy of numerical solution of timeindependent photoacoustic wave equation. 67(9):849–--855, 2020.
- Neural Operator: Learning Maps Between Function Spaces. arXiv, 2021.
- Inverse problem solver for multiple light scattering using modified born series. Optica, 9(2):177--182, 2022.
- 3-d stochastic numerical breast phantoms for enabling virtual imaging trials of ultrasound computed tomography. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 69(1):135--146, 2022.
- Quantitative ultrasound brain imaging with multiscale deconvolutional waveform inversion. Chinese Physics B, 32(1), 2023.
- Neural operator: Graph kernel network for partial differential equations. arXiv, 2020.
- Fourier neural operator for parametric partial differential equations. In ICLR, 2021.
- Operator learning for predicting multiscale bubble growth dynamics. J Chem Phys, 154(10):104118, 2021.
- Acoustic- and elastic-waveform inversion using a modified total-variation regularization scheme. Geophysical Journal International, 200(1):489--502, 2014.
- Learned Full Waveform Inversion Incorporating Task Information for Ultrasound Computed Tomography. arXiv, 2023.
- DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators. arXiv, 2019.
- Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators. Nature Machine Intelligence, 3, 2021.
- Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators. Computer Methods in Applied Mechanics and Engineering, 393, 2022a.
- Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transport. Phys. Rev. Res., 4(2):023210, 2022b. Publisher: American Physical Society.
- High resolution 3d ultrasonic breast imaging by time-domain full waveform inversion. Inverse Problems, 38(2):025008, 2021.
- DeepM&mnet for hypersonics: Predicting the coupled flow and finite-rate chemistry behind a normal shock using neural-network approximation of operators. Journal of Computational Physics, 447:110698, 2021.
- 3-d wave-equation-based finite-frequency tomography for ultrasound computed tomography. IEEE Trans. Ultrason., Ferroelect., Freq. Contr., 67(7):1332--1343, 2020.
- A convergent born series for solving the inhomogeneous helmholtz equation in arbitrarily large media. Journal of Computational Physics, 322:113--124, 2016.
- FourCastNet: A global data-driven high-resolution weather model using adaptive fourier neural operators. arXiv, 2022.
- Time domain reconstruction of sound speed and attenuation in ultrasound computed tomography using full wave inversion. J Acoust Soc Am, 141(3):1595, 2017.
- U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention--MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pages 234--241. Springer, 2015.
- A learned born series for highly-scattering media. JASA Express Letters, 3(5), 2023.
- An overview of full-waveform inversion in exploration geophysics. Geophysics, 74(6):WCC1--WCC26, 2009.
- Intelligent designs in nanophotonics: from optimization towards inverse creation. PhotoniX, 2(1):1--35, 2021a.
- Fast PDE-constrained optimization via self-supervised operator learning. 2021b.
- U-FNO—an enhanced fourier neural operator-based deep-learning model for multiphase flow. Advances in Water Resources, 163:104180, 2022.
- 3-d nonlinear acoustic inverse scattering: Algorithm and quantitative results. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 64(8):1161--1174, 2017.
- Ultrasound computed tomography based on full waveform inversion with source directivity calibration. Ultrasonics, 132:107004, 2023.
- Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv, 2017.
- Point cloud-based high-dimensional optimal transport for full waveform inversion. IEEE Transactions on Geoscience and Remote Sensing, 60:1--10, 2022.
- Rapid seismic waveform modeling and inversion with neural operators. IEEE Transactions on Geoscience and Remote Sensing, 61:1--12, 2023.
- Optimization of reconstruction time of ultrasound computed tomography with a piecewise homogeneous region-based refract-ray model. Ultrasonics, 127:106837, 2023.
- InversionNet3d: Efficient and scalable learning for 3-d full-waveform inversion. IEEE Transactions on Geoscience and Remote Sensing, 60:1--16, 2022.
- Efficient implementation of ultrasound waveform tomography using source encoding. In Medical Imaging 2012: Ultrasonic Imaging, Tomography, and Therapy, pages 22--31. SPIE, 2012.
- Deep born operator learning for reflection tomographic imaging. In ICASSP, 2023.
- Frequency-domain full-waveform inversion-based musculoskeletal ultrasound computed tomography. The Journal of the Acoustical Society of America, 154(1):279--294, 2023.
- Fourier-DeepONet: Fourier-enhanced deep operator networks for full waveform inversion with improved accuracy, generalizability, and robustness. Computer Methods in Applied Mechanics and Engineering, 416:116300, 2023.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.