Cited time in webofscience Cited time in scopus

Dual-frequency Capsule Type Ultrasound Endoscopic System for Deep Learning-based High-resolution In-depth Imaging

Title
Dual-frequency Capsule Type Ultrasound Endoscopic System for Deep Learning-based High-resolution In-depth Imaging
Author(s)
Kim, Jae Seong
DGIST Authors
Kim, Jae SeongHwang, Jae YounIm, Sunghoon
Advisor
황재윤
Co-Advisor(s)
Im, Sunghoon
Issued Date
2022
Awarded Date
2022/02
Type
Thesis
Subject
Ultrasound capsule endoscope, Ultrasound imaging, Dual-frequency, Deep learning
Description
Ultrasound capsule endoscope, Ultrasound imaging, Dual-frequency, Deep learning
Table Of Contents
I. Introduction 1
1.1 Motivation 1
1.2 Backgrounds 3
1.2.1 Basic principles of ultrasound 3
1.2.2 Ultrasound B-mode imaging 7
1.2.3 Image enhancement in ultrasound imaging 8
II. Materials and Methods 12
2.1 System configuration 12
2.2 Capsule design 15
2.3 Ultrasound transducer fabrication 17
2.4 Ultrasound imaging 20
2.5 Deep learning network 21
2.6 Quantitative analysis and Evaluation method 25
III. Results and Discussions 29
3.1 Evaluation of the proposed system 29
3.1.1 Penetration depth according to the center frequency 30
3.1.2 Spatial resolution 32
3.1.3 Quality improvement 33
3.1.4 Structural similarity index 36
IV. Conclusion 38
V. Reference 40
요 약 문 43
URI
http://dgist.dcollection.net/common/orgView/200000591941

http://hdl.handle.net/20.500.11750/16274
DOI
10.22677/thesis.200000591941
Degree
Master
Department
Information and Communication Engineering
Publisher
DGIST
Related Researcher
  • 황재윤 Hwang, Jae Youn 전기전자컴퓨터공학과
  • Research Interests Multimodal Imaging; High-Frequency Ultrasound Microbeam; Ultrasound Imaging and Analysis; 스마트 헬스케어; Biomedical optical system
Files in This Item:

There are no files associated with this item.

Appears in Collections:
Department of Electrical Engineering and Computer Science Theses Master

qrcode

  • twitter
  • facebook
  • mendeley

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE