Deep Neural Network for Golay-coded excitation Ultrasound Imaging without frame rate reduction
- 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
- Author(s)
- Sun Tae Hwang
- 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
- Type
- Thesis
- Description
- Deep neural network, Coded excitation, Golay code, Inverse problem, Ultrasound, Signal reconstruction
- Abstract
- 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
- Degree
- Master
- Publisher
- DGIST
- Related Researcher
-
-
Chang, Jin Ho
- Research Interests Biomedical Imaging; Signal and Image Processing; Ultrasound Imaging System; Ultrasound Transducer; Photoacoustic Imaging
-
- Files in This Item:
-
There are no files associated with this item.
- Appears in Collections:
- Department of Electrical Engineering and Computer Science Theses Master
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.