Sciact
  • EN
  • RU

Convolutional neural networks of recovering acoustic absorption in ultrasound tomography from gradient data Full article

Journal Journal of Mathematical Sciences (United States)
ISSN: 1072-3374 , E-ISSN: 1573-8795
Output data Year: 2025, DOI: 10.1007/s10958-025-08064-w
Tags CNN, 2D coefficient inverse problem, acoustic tomograpy, ultrasound
Authors Savchenko Nikita 1 , Novikov Nikita 1 , Shishlenin Maxim 1
Affiliations
1 Sobolev Institute of Mathematics, pr. Koptyuga, 4, Novosibirsk, 630090, Russia

Funding (1)

1 Russian Science Foundation 24-41-04004

Abstract: In this work, a method for reconstructing acoustic absorption from the measured pressure in sensors around the body under study is implemented. We develop a neural network architecture based on CNN that uses not only pressure data, but also the gradient of functional which is used to solve the inverse problem.We use the distribution of the gradient with respect to space variables as an input of the neural network and obtain the target image of the absorption as an output.
Cite: Savchenko N. , Novikov N. , Shishlenin M.
Convolutional neural networks of recovering acoustic absorption in ultrasound tomography from gradient data
Journal of Mathematical Sciences (United States). 2025. DOI: 10.1007/s10958-025-08064-w Scopus OpenAlex
Dates:
Submitted: Aug 4, 2025
Accepted: Nov 10, 2025
Published print: Dec 6, 2025
Published online: Dec 6, 2025
Identifiers:
Scopus: 2-s2.0-105024197989
OpenAlex: W4417071482
Citing: Пока нет цитирований
Altmetrics: