Cargando…

3D Ultrasonic Brain Imaging with Deep Learning Based on Fully Convolutional Networks

Compared to magnetic resonance imaging (MRI) and X-ray computed tomography (CT), ultrasound imaging is safer, faster, and more widely applicable. However, the use of conventional ultrasound in transcranial brain imaging for adults is predominantly hindered by the high acoustic impedance contrast bet...

Descripción completa

Detalles Bibliográficos
Autores principales: Ren, Jiahao, Wang, Xiaocen, Liu, Chang, Sun, He, Tong, Junkai, Lin, Min, Li, Jian, Liang, Lin, Yin, Feng, Xie, Mengying, Liu, Yang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10575417/
https://www.ncbi.nlm.nih.gov/pubmed/37837171
http://dx.doi.org/10.3390/s23198341
_version_ 1785120917117992960
author Ren, Jiahao
Wang, Xiaocen
Liu, Chang
Sun, He
Tong, Junkai
Lin, Min
Li, Jian
Liang, Lin
Yin, Feng
Xie, Mengying
Liu, Yang
author_facet Ren, Jiahao
Wang, Xiaocen
Liu, Chang
Sun, He
Tong, Junkai
Lin, Min
Li, Jian
Liang, Lin
Yin, Feng
Xie, Mengying
Liu, Yang
author_sort Ren, Jiahao
collection PubMed
description Compared to magnetic resonance imaging (MRI) and X-ray computed tomography (CT), ultrasound imaging is safer, faster, and more widely applicable. However, the use of conventional ultrasound in transcranial brain imaging for adults is predominantly hindered by the high acoustic impedance contrast between the skull and soft tissue. This study introduces a 3D AI algorithm, Brain Imaging Full Convolution Network (BIFCN), combining waveform modeling and deep learning for precise brain ultrasound reconstruction. We constructed a network comprising one input layer, four convolution layers, and one pooling layer to train our algorithm. In the simulation experiment, the Pearson correlation coefficient between the reconstructed and true images was exceptionally high. In the laboratory, the results showed a slightly lower but still impressive coincidence degree for 3D reconstruction, with pure water serving as the initial model and no prior information required. The 3D network can be trained in 8 h, and 10 samples can be reconstructed in just 12.67 s. The proposed 3D BIFCN algorithm provides a highly accurate and efficient solution for mapping wavefield frequency domain data to 3D brain models, enabling fast and precise brain tissue imaging. Moreover, the frequency shift phenomenon of blood may become a hallmark of BIFCN learning, offering valuable quantitative information for whole-brain blood imaging.
format Online
Article
Text
id pubmed-10575417
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-105754172023-10-14 3D Ultrasonic Brain Imaging with Deep Learning Based on Fully Convolutional Networks Ren, Jiahao Wang, Xiaocen Liu, Chang Sun, He Tong, Junkai Lin, Min Li, Jian Liang, Lin Yin, Feng Xie, Mengying Liu, Yang Sensors (Basel) Article Compared to magnetic resonance imaging (MRI) and X-ray computed tomography (CT), ultrasound imaging is safer, faster, and more widely applicable. However, the use of conventional ultrasound in transcranial brain imaging for adults is predominantly hindered by the high acoustic impedance contrast between the skull and soft tissue. This study introduces a 3D AI algorithm, Brain Imaging Full Convolution Network (BIFCN), combining waveform modeling and deep learning for precise brain ultrasound reconstruction. We constructed a network comprising one input layer, four convolution layers, and one pooling layer to train our algorithm. In the simulation experiment, the Pearson correlation coefficient between the reconstructed and true images was exceptionally high. In the laboratory, the results showed a slightly lower but still impressive coincidence degree for 3D reconstruction, with pure water serving as the initial model and no prior information required. The 3D network can be trained in 8 h, and 10 samples can be reconstructed in just 12.67 s. The proposed 3D BIFCN algorithm provides a highly accurate and efficient solution for mapping wavefield frequency domain data to 3D brain models, enabling fast and precise brain tissue imaging. Moreover, the frequency shift phenomenon of blood may become a hallmark of BIFCN learning, offering valuable quantitative information for whole-brain blood imaging. MDPI 2023-10-09 /pmc/articles/PMC10575417/ /pubmed/37837171 http://dx.doi.org/10.3390/s23198341 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ren, Jiahao
Wang, Xiaocen
Liu, Chang
Sun, He
Tong, Junkai
Lin, Min
Li, Jian
Liang, Lin
Yin, Feng
Xie, Mengying
Liu, Yang
3D Ultrasonic Brain Imaging with Deep Learning Based on Fully Convolutional Networks
title 3D Ultrasonic Brain Imaging with Deep Learning Based on Fully Convolutional Networks
title_full 3D Ultrasonic Brain Imaging with Deep Learning Based on Fully Convolutional Networks
title_fullStr 3D Ultrasonic Brain Imaging with Deep Learning Based on Fully Convolutional Networks
title_full_unstemmed 3D Ultrasonic Brain Imaging with Deep Learning Based on Fully Convolutional Networks
title_short 3D Ultrasonic Brain Imaging with Deep Learning Based on Fully Convolutional Networks
title_sort 3d ultrasonic brain imaging with deep learning based on fully convolutional networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10575417/
https://www.ncbi.nlm.nih.gov/pubmed/37837171
http://dx.doi.org/10.3390/s23198341
work_keys_str_mv AT renjiahao 3dultrasonicbrainimagingwithdeeplearningbasedonfullyconvolutionalnetworks
AT wangxiaocen 3dultrasonicbrainimagingwithdeeplearningbasedonfullyconvolutionalnetworks
AT liuchang 3dultrasonicbrainimagingwithdeeplearningbasedonfullyconvolutionalnetworks
AT sunhe 3dultrasonicbrainimagingwithdeeplearningbasedonfullyconvolutionalnetworks
AT tongjunkai 3dultrasonicbrainimagingwithdeeplearningbasedonfullyconvolutionalnetworks
AT linmin 3dultrasonicbrainimagingwithdeeplearningbasedonfullyconvolutionalnetworks
AT lijian 3dultrasonicbrainimagingwithdeeplearningbasedonfullyconvolutionalnetworks
AT lianglin 3dultrasonicbrainimagingwithdeeplearningbasedonfullyconvolutionalnetworks
AT yinfeng 3dultrasonicbrainimagingwithdeeplearningbasedonfullyconvolutionalnetworks
AT xiemengying 3dultrasonicbrainimagingwithdeeplearningbasedonfullyconvolutionalnetworks
AT liuyang 3dultrasonicbrainimagingwithdeeplearningbasedonfullyconvolutionalnetworks