Cited time in webofscience Cited time in scopus

Mobile Multimode Imaging System and Machine Learning Analysis for Diagnosis of Skin Diseases

Title
Mobile Multimode Imaging System and Machine Learning Analysis for Diagnosis of Skin Diseases
Alternative Title
피부질환 진단을 위한 모바일 다중모드 이미징 및 머신러닝 분석
Author(s)
Sewoong Kim
DGIST Authors
Sewoong KimJae Youn HwangKijoon Lee
Advisor
황재윤
Co-Advisor(s)
Kijoon Lee
Issued Date
2023
Awarded Date
2023-08-01
Type
Thesis
Description
Multimodal Imaging and Analysis System; Machine Learning; Multispectral Imaging System; Fluorescent Imaging System. Polarization Imaging System
Table Of Contents
1. INTRODUCTION 1
1.1 Motivation 1
1.1.1 Skin 1
1.1.2 Acne 2
1.1.3 Rosacea 3
1.1.4 Seborrheic dermatitis 3
1.1.5 Psoriasis 3
1.2 Optical Imaging System 5
1.2.1 Spectral Imaging 5
1.2.2 Fluorescence Imaging 7
1.2.3 Polarization Imaging 9
1.2.4 Mobile Imaging 11
1.3 Machine Learning 13
1.3.1 Artificial Neural Networks 13
1.3.2 Convolutional Neural Network 14
1.3.3 Applications of machine learning in dermoscopy 16
1.4 Structure of Thesis 17
2. Smartphone-based Multispectral Imaging: System Development and Potential for Mobile Skin Diagnosis 18
2.1 Introduction 18
2.2 Methods and Results 21
2.2.1 Smartphone-attached multispectral imaging system 21
2.2.2 Miniaturization of a multispectral imaging system 22
2.2.3 Interface circuit for synchronization between the multispectral imaging system and the smartphone 24
2.2.4 Platform for skin diagnosis/management 25
2.2.5 Evaluation of the performance of the smartphone-based multispectral imaging system 29
2.2.6 Multispectral imaging and analysis of a nevus region 33
2.2.7 Ratiometric multispectral imaging and analysis to monitor acne regions 34
2.3 Discussion 37
2.4 Conclusion 41
3. Smartphone-based multispectral imaging and machine-learning based analysis for discrimination between seborrheic dermatitis and psoriasis on the scalp 42
3.1 Introduction 42
3.2 Methods 45
3.2.1 Spectral classification using conventional linear distance measures and machine learning techniques 48
3.2.2 Clinical trial for multispectral imaging and analysis 51
3.2.3 Quantitative analysis for discriminating between seborrheic dermatitis and psoriasis using multispectral imaging and analysis 51
3.2.4 Evaluation of the smartphone-based multispectral imaging system 52
3.3 Results 55
3.3.1 Discrimination between seborrheic dermatitis and psoriasis regions on the scalp via multispectral imaging and analysis 55
3.3.2 Discrimination between seborrheic dermatitis/psoriasis and normal regions on the scalp 56
3.4 Discussion 61
3.5 Conclusions 64
4. Smartphone-based Multimodal Optical Imaging System with Deep Learning Classification Techniques for Discrimination between Seborrheic Dermatitis and Psoriasis 65
4.1 Introduction 65
4.2 Method and Results 68
4.2.1 Smartphone-attached multimodal optical imaging system 68
4.2.2 Evaluation of the smartphone-based multimodal optical imaging system 71
4.2.3 Clinical trial for multimodal optical imaging and analysis 72
4.2.4 Classification models using conventional machine learning and deep learning based techniques 74
4.2.5 Discrimination between seborrheic dermatitis and psoriasis regions via multimodal optical imaging system and analysis 75
4.3 Conclusion 78
5. CONCLUSION 79
BIBLIOGRAPHY 81
URI
http://hdl.handle.net/20.500.11750/46411

http://dgist.dcollection.net/common/orgView/200000688542
DOI
10.22677/THESIS.200000688542
Degree
Doctor
Department
Department of Electrical Engineering and Computer Science
Publisher
DGIST
Related Researcher
  • 황재윤 Hwang, Jae Youn
  • 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 Ph.D.

qrcode

  • twitter
  • facebook
  • mendeley

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

BROWSE