TY - GEN
T1 - DL-UCT
T2 - 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022
AU - Prasad, Sumukha
AU - Almekkawy, Mohamed
N1 - Funding Information:
The authors would like to thank Fu Li and Dr. Mark Anastasio from the Computational Imaging Science Laboratory, Bioengineering Department at University of Illinois Urbana- Champaign for their support in the reconstruction of the phantoms using the FWI method described in [6].
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Ultrasound Computed Tomography (UCT) is a non-invasive, inexpensive, radiation-free medical imaging technique that is capable of resolving soft-tissue structures in the body. Waveform inversion methods frequently employed in UCT, though very successful, are computationally expensive and struggle when dealing with high contrasts between tissue types without a good initial model. This can be attributed to the large-scale optimization scheme used to solve for UCT in the presence of high contrast phantoms. In this work, we propose to leverage the promise of Deep Learning (DL) to perform high contrast UCT. The proposed deep Convolutional Neural Network (CNN) is developed using an encoder-decoder architecture which reconstructs the acoustic property distribution from the recorded ultrasound data in a fraction of a second. The DL-UCT method reconstructs highly accurate acoustic images on a synthetic dataset, which is simulated to mimic high contrast organs. This is compared against the state-of-the-art waveform inversion method. The DL-UCT model outperforms the waveform inversion technique both qualitatively and quantitatively.
AB - Ultrasound Computed Tomography (UCT) is a non-invasive, inexpensive, radiation-free medical imaging technique that is capable of resolving soft-tissue structures in the body. Waveform inversion methods frequently employed in UCT, though very successful, are computationally expensive and struggle when dealing with high contrasts between tissue types without a good initial model. This can be attributed to the large-scale optimization scheme used to solve for UCT in the presence of high contrast phantoms. In this work, we propose to leverage the promise of Deep Learning (DL) to perform high contrast UCT. The proposed deep Convolutional Neural Network (CNN) is developed using an encoder-decoder architecture which reconstructs the acoustic property distribution from the recorded ultrasound data in a fraction of a second. The DL-UCT method reconstructs highly accurate acoustic images on a synthetic dataset, which is simulated to mimic high contrast organs. This is compared against the state-of-the-art waveform inversion method. The DL-UCT model outperforms the waveform inversion technique both qualitatively and quantitatively.
UR - http://www.scopus.com/inward/record.url?scp=85129688833&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129688833&partnerID=8YFLogxK
U2 - 10.1109/ISBI52829.2022.9761660
DO - 10.1109/ISBI52829.2022.9761660
M3 - Conference contribution
AN - SCOPUS:85129688833
T3 - Proceedings - International Symposium on Biomedical Imaging
BT - ISBI 2022 - Proceedings
PB - IEEE Computer Society
Y2 - 28 March 2022 through 31 March 2022
ER -