Convolutional neural networks of recovering acoustic absorption in ultrasound tomography from gradient data | Sciact - Система учета научной деятельности ИМ СО РАН

Convolutional neural networks of recovering acoustic absorption in ultrasound tomography from gradient data Научная публикация

Журнал

Journal of Mathematical Sciences (United States)
ISSN: 1072-3374 , E-ISSN: 1573-8795

Вых. Данные

Год: 2025, DOI: 10.1007/s10958-025-08064-w

Ключевые слова

CNN, 2D coefficient inverse problem, acoustic tomograpy, ultrasound

Авторы

Savchenko Nikita ¹ , Novikov Nikita ¹ , Shishlenin Maxim ¹

Организации

1	Sobolev Institute of Mathematics, pr. Koptyuga, 4, Novosibirsk, 630090, Russia

Информация о финансировании (1)

Российский научный фонд

24-41-04004

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.

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

Поступила в редакцию:	4 авг. 2025 г.
Принята к публикации:	10 нояб. 2025 г.
Опубликована в печати:	6 дек. 2025 г.
Опубликована online:	6 дек. 2025 г.

Scopus:	2-s2.0-105024197989
OpenAlex:	W4417071482

Пока нет цитирований