Abstract
The potential of ultrasound tomography has been noticed to quantify the tissue acoustic properties for advanced clinical diagnosis. However, the location of most of the human anatomies limits the tomography for a few angles that leads the reconstruction as a more challenging problem. In this work, a deep convolutional neural networks- based technique is presented to estimate the speed of sound of tissue from a limited angle projection data. The underlying concept is based on filtered back projection technique, where the convolutional neural network is used to model the high-pass filter before the back projection. Moreover, we use a post convolutional neural network to suppress the artifacts generated due to the limited angle tomography. We train the network from a set of simulation experiments; on the test set consisting of 1,750 simulation experiments, we achieve an average mean absolute error of 2.1% in predicting the speed of sound map.
Original language | English (US) |
---|---|
Title of host publication | Medical Imaging 2019 |
Subtitle of host publication | Ultrasonic Imaging and Tomography |
Editors | Brett C. Byram, Nicole V. Ruiter |
Publisher | SPIE |
ISBN (Electronic) | 9781510625570 |
DOIs | |
State | Published - Jan 1 2019 |
Event | Medical Imaging 2019: Ultrasonic Imaging and Tomography - San Diego, United States Duration: Feb 17 2019 → Feb 18 2019 |
Publication series
Name | Progress in Biomedical Optics and Imaging - Proceedings of SPIE |
---|---|
Volume | 10955 |
ISSN (Print) | 1605-7422 |
Conference
Conference | Medical Imaging 2019: Ultrasonic Imaging and Tomography |
---|---|
Country | United States |
City | San Diego |
Period | 2/17/19 → 2/18/19 |
Fingerprint
Keywords
- Altered back-projection
- Convolutional neural networks
- Speed of sound
- Ultrasound tomography
ASJC Scopus subject areas
- Electronic, Optical and Magnetic Materials
- Atomic and Molecular Physics, and Optics
- Biomaterials
- Radiology Nuclear Medicine and imaging
Cite this
CNN and back-projection : Limited angle ultrasound tomography for speed of sound estimation. / Anas, Emran Mohammad Abu; Cheng, Alexis; Seifabadi, Reza; Wu, Yixuan; Aalamifar, Fereshteh; Wood, Bradford; Rahmim, Arman; Boctor, Emad.
Medical Imaging 2019: Ultrasonic Imaging and Tomography. ed. / Brett C. Byram; Nicole V. Ruiter. SPIE, 2019. 109550M (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10955).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - CNN and back-projection
T2 - Limited angle ultrasound tomography for speed of sound estimation
AU - Anas, Emran Mohammad Abu
AU - Cheng, Alexis
AU - Seifabadi, Reza
AU - Wu, Yixuan
AU - Aalamifar, Fereshteh
AU - Wood, Bradford
AU - Rahmim, Arman
AU - Boctor, Emad
PY - 2019/1/1
Y1 - 2019/1/1
N2 - The potential of ultrasound tomography has been noticed to quantify the tissue acoustic properties for advanced clinical diagnosis. However, the location of most of the human anatomies limits the tomography for a few angles that leads the reconstruction as a more challenging problem. In this work, a deep convolutional neural networks- based technique is presented to estimate the speed of sound of tissue from a limited angle projection data. The underlying concept is based on filtered back projection technique, where the convolutional neural network is used to model the high-pass filter before the back projection. Moreover, we use a post convolutional neural network to suppress the artifacts generated due to the limited angle tomography. We train the network from a set of simulation experiments; on the test set consisting of 1,750 simulation experiments, we achieve an average mean absolute error of 2.1% in predicting the speed of sound map.
AB - The potential of ultrasound tomography has been noticed to quantify the tissue acoustic properties for advanced clinical diagnosis. However, the location of most of the human anatomies limits the tomography for a few angles that leads the reconstruction as a more challenging problem. In this work, a deep convolutional neural networks- based technique is presented to estimate the speed of sound of tissue from a limited angle projection data. The underlying concept is based on filtered back projection technique, where the convolutional neural network is used to model the high-pass filter before the back projection. Moreover, we use a post convolutional neural network to suppress the artifacts generated due to the limited angle tomography. We train the network from a set of simulation experiments; on the test set consisting of 1,750 simulation experiments, we achieve an average mean absolute error of 2.1% in predicting the speed of sound map.
KW - Altered back-projection
KW - Convolutional neural networks
KW - Speed of sound
KW - Ultrasound tomography
UR - http://www.scopus.com/inward/record.url?scp=85066628161&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85066628161&partnerID=8YFLogxK
U2 - 10.1117/12.2513043
DO - 10.1117/12.2513043
M3 - Conference contribution
AN - SCOPUS:85066628161
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2019
A2 - Byram, Brett C.
A2 - Ruiter, Nicole V.
PB - SPIE
ER -