CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume PC12038 > Article
Presentation
4 April 2022 Ultrasound tomography as a gauge invariant fully connected convolutional neural network: repercussions
James W. Wiskin
Author Affiliations +
Proceedings Volume PC12038, Medical Imaging 2022: Ultrasonic Imaging and Tomography; PC1203806 (2022) https://doi.org/10.1117/12.2610822
Event: SPIE Medical Imaging, 2022, San Diego, California, United States
Abstract
Full wave 3D ultrasound tomography (3D-UT) is shown to be exactly congruent and ‘dual’ to training a gauge equivariant convolutional deep neural network (cDNN) with Lie group SO(2)xR applied to the weights (not feature vectors) and unusual ‘activation functions’. This explains high efficiency on NIVIDIA GPUs and indicates cross application of techniques from 3D-UT to cDNN and vice versa. ‘Backpropagation’ in both arenas is mathematically similar and the weights of the cDNN are the resulting image in 3D-UT. Data acquisition (DA) scenarios are interpreted as mappings from the Lie group manifold, and the 2-sphere, to the N-torus, with ramifications.
Conference Presentation
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
James W. Wiskin "Ultrasound tomography as a gauge invariant fully connected convolutional neural network: repercussions", Proc. SPIE PC12038, Medical Imaging 2022: Ultrasonic Imaging and Tomography, PC1203806 (4 April 2022); https://doi.org/10.1117/12.2610822
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
;
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 PRESENTATION
WATCH
PRESENTATION SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
KEYWORDS
Ultrasound tomography
Convolutional neural networks
3D imaging standards
Evolutionary algorithms
Image transmission
Neural networks
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top