TY - GEN
T1 - Full Wave Inversion For Ultrasound Tomography Using Physics Based Deep Neural Network
AU - Liu, Xilun
AU - Almekkawy, Mohamed
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Ultrasound Computed Tomography (USCT) is a promising imaging modality for reconstructing tissue properties. Full-wave inversion (FWI) provides an enhanced contrast image. In this paper, we introduce an optimized Physics-Informed Neural Network (PINN) architecture to solve the inverse problems of FWI. PINNs are neural networks that can approximate universal functions using partial differential equations that govern the physics of the system. When training the network, the deep neural network can converge to learn the solutions of the wave equation by minimizing the loss function. The results showed that our proposed networks can retrieve the Speed of Sound (SoS) information and significantly decrease the computational cost via the transfer learning technique.
AB - Ultrasound Computed Tomography (USCT) is a promising imaging modality for reconstructing tissue properties. Full-wave inversion (FWI) provides an enhanced contrast image. In this paper, we introduce an optimized Physics-Informed Neural Network (PINN) architecture to solve the inverse problems of FWI. PINNs are neural networks that can approximate universal functions using partial differential equations that govern the physics of the system. When training the network, the deep neural network can converge to learn the solutions of the wave equation by minimizing the loss function. The results showed that our proposed networks can retrieve the Speed of Sound (SoS) information and significantly decrease the computational cost via the transfer learning technique.
UR - http://www.scopus.com/inward/record.url?scp=85172104307&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85172104307&partnerID=8YFLogxK
U2 - 10.1109/ISBI53787.2023.10230537
DO - 10.1109/ISBI53787.2023.10230537
M3 - Conference contribution
AN - SCOPUS:85172104307
T3 - Proceedings - International Symposium on Biomedical Imaging
BT - 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023
PB - IEEE Computer Society
T2 - 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023
Y2 - 18 April 2023 through 21 April 2023
ER -