Poster Abstract: Improving image reconstruction quality in ultrasonic tomography using deep neural networks

被引：0

作者：

Kulisz, Monika ^{[1
]}

Klosowski, Grzegorz ^{[1
]}

Rymarczyk, Tomasz ^{[2
]}

Niderla, Konrad ^{[3
]}

Bednarczuk, Piotr ^{[3
]}

机构：

[1] Lublin Univ Technol, Fac Management, Lublin, Poland

[2] WSEI Univ, Inst Comp Sci & Innovat Technol, Ctr Res & Dev, Netrix SA, Lublin, Poland

[3] WSEI Univ, Inst Comp Sci & Innovat Technol, Lublin, Poland

来源：

PROCEEDINGS OF THE 21ST ACM CONFERENCE ON EMBEDDED NETWORKED SENSOR SYSTEMS, SENSYS 2023 | 2023年

关键词：

ultrasound tomography; deep learning; image reconstruction; process tomography;

D O I：

10.1145/3625687.3628389

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

This study aims to improve the resolution of reconstructed images from industrial ultrasonic tomography (UST) by determining the most effective neural network structure for solving the inverse problem based on the measurements taken. The study analyzed three types of neural networks: Artificial Neural Networks, Convolutional Neural Networks (CNNs) and a hybrid of CNNs and Long Short-Term Memory networks (LSTM). After evaluating the reconstructions and quality indicators, the CNN-LSTM combination provided the most accurate image reconstructions of the industrial ultrasound tomography, highlighting the importance of selecting an appropriate neural network to improve the resolution of the reconstructed images.

引用

页码：520 / 521

页数：2

共 50 条

[1] Image Reconstruction in Electrical Capacitance Tomography Based on Deep Neural Networks
Deabes, Wael
Khayyat, Khalid M. Jamil
IEEE SENSORS JOURNAL, 2021, 21 (22) : 25818 - 25830
[2] IMAGE RECONSTRUCTION FOR QUANTA IMAGE SENSORS USING DEEP NEURAL NETWORKS
Choi, Joon Hee
Elgendy, Omar A.
Chan, Stanley H.
2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 6543 - 6547
[3] Neural networks applied to ultrasonic tomographic image reconstruction
Pardoe, AC
Hutchins, DA
Mottram, JT
Hines, EL
NEURAL COMPUTING & APPLICATIONS, 1997, 5 (02): : 106 - 123
[4] Neural networks applied to ultrasonic tomographic image reconstruction
A. C. Pardoe
D. A. Hutchins
J. T. Mottram
E. L. Hines
Neural Computing & Applications, 1997, 5 : 106 - 123
[5] Echocardiographic Image Quality Assessment Using Deep Neural Networks
Labs, Robert B.
Zolgharni, Massoud
Loo, Jonathan P.
MEDICAL IMAGE UNDERSTANDING AND ANALYSIS (MIUA 2021), 2021, 12722 : 488 - 502
[6] Spike Camera Image Reconstruction Using Deep Spiking Neural Networks
Zhao, Rui
Xiong, Ruiqin
Zhang, Jian
Yu, Zhaofei
Zhu, Shuyuan
Ma, Lei
Huang, Tiejun
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (06) : 5207 - 5212
[7] Poster Abstract : On Electrical Load Disaggregation using Recurrent Neural Networks
Gopu, Rajasekhar
Gudimallam, Anusha
Vishnu, B.
Thokala, Naveen
Chandra, M. Girish
BUILDSYS'19: PROCEEDINGS OF THE 6TH ACM INTERNATIONAL CONFERENCE ON SYSTEMS FOR ENERGY-EFFICIENT BUILDINGS, CITIES, AND TRANSPORTATION, 2019, : 364 - 365
[8] Anatomically aided PET image reconstruction using deep neural networks
Xie, Zhaoheng
Li, Tiantian
Zhang, Xuezhu
Qi, Wenyuan
Asma, Evren
Qi, Jinyi
MEDICAL PHYSICS, 2021, 48 (09) : 5244 - 5258
[9] Poster abstract: Investigating occupancy profiles using convolutional neural networks
Park, June Young
Chen, Jianli
Jin, Xin
Nagy, Zoltan
BUILDSYS'19: PROCEEDINGS OF THE 6TH ACM INTERNATIONAL CONFERENCE ON SYSTEMS FOR ENERGY-EFFICIENT BUILDINGS, CITIES, AND TRANSPORTATION, 2019, : 338 - 339
[10] Image Reconstruction for Ultrasonic Tomography using Multi-channel Convolutional Neural Network
Lyu, Jiashuo
Tan, Chao
Dong, Feng
PROCEEDINGS OF THE 39TH CHINESE CONTROL CONFERENCE, 2020, : 7304 - 7309

← 1 2 3 4 5 →