Title

Deep Neural Network for Golay-coded excitation Ultrasound Imaging without frame rate reduction

Alternative Title

프레임 율 저하가 없는 골레이-코드화 여기 초음파 이미징을 위한 심층 신경망

DGIST Authors

Sun Tae Hwang ; Jin Ho Chang ; Kyong Hwan Jin

Advisor

장진호

Co-Advisor(s)

Kyong Hwan Jin

Issued Date

2022

Awarded Date

2022/08

Citation

Sun Tae Hwang. (2022). Deep Neural Network for Golay-coded excitation Ultrasound Imaging without frame rate reduction. doi: 10.22677/thesis.200000628638

Type

Thesis

Subject

Deep neural network, Coded excitation, Golay code, Inverse problem, Ultrasound, Signal reconstruction

Description

Deep neural network, Coded excitation, Golay code, Inverse problem, Ultrasound, Signal reconstruction

Abstract

더보기

Table Of Contents

i. INTRODUCTION 1
1.1 Ultrasound characteristics 1
1.2 Limitations of short pulse ultrasound imaging 1
1.3 Coded excitation methods 2
1.4 Deep neural network for Golay coded excitation base ultrasound imaging 2
1.5 Organization of the paper 3
ii. Ultrasound imaging device 3
2.1 Configuration diagram of ultrasound imaging device 3
2.2 B-mode imaging method 5
2.3 Coded excitation 5
iii. Neural network with encoder-decoder structure 11
3.1 Autoencoder 11
3.2 U-Net 12
3.3 Inverse problem with deep neural network 13
iV. A method of generating a Golay coded excitation signal using deep learning 13
4.1 Network architecture 14
4.2 Data acquisition 15
4.3 Training 16
V. Performance evaluation and results 16
5.1 Comparison of conventional ultrasound image and Golay coded excitation image 17
5.2 U-Net-based deep neural network results 18
Vi. Conclusion and future work 22

URI

http://dgist.dcollection.net/common/orgView/200000628638
http://hdl.handle.net/20.500.11750/16783

DOI

10.22677/thesis.200000628638

Degree

Master

Department

Department of Electrical Engineering and Computer Science

Publisher

DGIST

Show Full Item Record