Hypersensitivity Diagnosis. Development of an Automatic and Quantitative IgE Concentration Detection Algorithm

Table of Contents

CHAPTER-1 Background

1.1 Introduction

1.2 Diagnosis of Allergic Diseases

1.3 Research Status

1.4 In-vitro Allergy Test Products

CHAPTER 2 In-Vitro Allergen Testing Device

2.1 Preparation of Reagent

2.2 Experimental Device

2.3 System Assembly

Chapter 3 Verification of System Stability and Grayscale Image Analysis

3.1 Introduction

3.2 Color calibration of the imaging system by intensity ratio analysis

3.3 Gray Value Analysis of Colored Reaction Product

CHAPTER 4 COLOR MODELS AND IMAGE ANALYSIS

4.1 Introduction

4.2 Color Models

5. Polynomial Regression

5.1 Background

5.2 Null hypothesis

5.3 Experiment Motive

5.4 Procedure Details

6. Summary and Future Work

7. References

Research Objectives and Themes

This thesis aims to develop an automatic and quantitative IgE concentration detection algorithm for use in a self-designed allergen disease diagnosis system. By utilizing image processing techniques on ELISA reagent strips, the research seeks to create a cost-effective, sensitive, and reproducible method for allergy diagnosis that overcomes the limitations of manual qualitative assessments.

• Development of an automated quantitative image analysis method for IgE concentration.
• Evaluation of various color models (RGB, YUV, YCbCr, HSV, HSL) for image feature extraction.
• Implementation of polynomial regression models to define the relationship between IgE levels and image features.
• Mitigation of environmental noise and system errors in image acquisition.

Excerpt from the Book

Summary of Chapters

CHAPTER-1 Background: This chapter provides an overview of allergic diseases, their global prevalence, and current diagnostic methodologies including Skin Prick Tests and ELISA.

CHAPTER 2 In-Vitro Allergen Testing Device: This section details the experimental design, including the preparation of reagent strips and the assembly of the imaging system.

Chapter 3 Verification of System Stability and Grayscale Image Analysis: This chapter covers the calibration of the imaging setup to ensure system stability and introduces the processing of grayscale images for data collection.

CHAPTER 4 COLOR MODELS AND IMAGE ANALYSIS: This chapter investigates various color models such as RGB, YUV, and YCbCr to identify optimal features for quantifying IgE concentration.

5. Polynomial Regression: This chapter discusses the use of polynomial regression models to establish a reliable relationship between independent IgE concentration variables and dependent image feature responses.

6. Summary and Future Work: This chapter concludes the research by summarizing the developed methods and proposing directions for future improvements in automated allergy diagnostics.

Keywords

Allergic disease, Automatic Diagnosis, IgE, ELISA, Quantitative Detection, Image Processing, Color Models, Polynomial Regression, Reagent Strip, Allergen, Multispectral Imaging, G Channel, Machine Vision, Sensitivity, Immunoassay.

Frequently Asked Questions

What is the primary focus of this research?

The research focuses on developing an automatic and quantitative tool for measuring IgE concentration to improve the diagnosis of allergic diseases using image processing.

What diagnostic technique is central to this study?

The study utilizes the Enzyme-linked Immuno-Sorbent Assay (ELISA) technique performed on paper reagent strips as the basis for color-based detection.

What is the main objective of using image processing here?

The objective is to replace manual qualitative observation with an accurate, quantitative, and reproducible automated system for analyzing IgE-induced color intensity.

Which scientific methodology is applied for data analysis?

The research employs multispectral imaging, image feature extraction from various color models, and polynomial regression to map image features to IgE concentration levels.

What does the main body of the work cover?

It covers the experimental hardware setup, calibration procedures, the evaluation of different color spaces, and the development of regression curves to quantify serum IgE.

What are the characterizing keywords of the work?

Key terms include Allergic disease, Automatic Diagnosis, IgE, ELISA, Quantitative Detection, Image Processing, and Polynomial Regression.

How does the system account for system environment variables?

The study investigates the impact of wet versus dry conditions on color intensity and explores image features and algorithms to compensate for these environmental differences.

Why are multiple color models evaluated in the study?

Different color models are analyzed to find an image feature that is monotonic, sensitive, and stable across various environmental conditions to ensure reliable quantification.