Evaluation of color space transformations in separating anemia vs control subjects Pubblico

Abstract

Anemia detection requires invasive blood testing with the gold standard hemoglobin level by a complete blood count (CBC). This procedure involves phlebotomy, which could lead to certain adverse effects. We consider a recently proposed non-invasive method for monitoring anemia with a fingernail image taken from patients [1]. Non-invasive anemia detection involves procedure of extracting color data from patients’ fingernail bed smartphone images. Usually, color data are extracted in RGB (Red,Green,Blue) color space. Since it is unknown that which color space transformation is most useful in discriminating anemia population vs healthy population, our work focused on determining which transformation of RGB (Red,Green,Blue) data would produce the best separation among anemic and control subjects. Several metrics are used to access the separation between anemia and healthy groups based on within sum of squares and between sum of squares Metric 1:Ratio of within to between variation). It is shown that HSI (Hue,Saturation,Intensity) color space perform the best in comparison to all other color spaces (Metric 1: 1.02 (0.82-1.35) for HSI, Metric 1: 0.76 (0.56-1.05) for RGB). The HSI color space also produced the least mean squared errors in predicting anemia status using Lasso Regression method - (MSE for HSI: 0.085).

We conclude the HSI color space has the best discriminative power in separating anemia vs control and the future prediction models or clustering models should focus on the analysis with HSI color space. 

Table of Contents

1 Introduction 1

2 Methodology 4

2.1 Data Sources 4

2.2.1 Univariate Case 5

2.2.2 Multivariate Case 6

2.2.3 Color Space Transformation 9

2.2.4 Statistical Analysis 11

3 Results 15

4 Discussion 21

Reference 22

Appendix 25

About this Master's Thesis

Rights statement

• Permission granted by the author to include this thesis or dissertation in this repository. All rights reserved by the author. Please contact the author for information regarding the reproduction and use of this thesis or dissertation.

School	Rollins School of Public Health
Department	Biostatistics
Subfield / Discipline	Biostatistics - MPH & MSPH
Degree	M.S.
Submission	Master's Thesis
Language	English
Research Field	Biology, Biostatistics
Parola chiave	cluster method color space transformation better separation Non-invasive anemia detection
Committee Chair / Thesis Advisor	Amita Manatunga, Emory University
Committee Members	Jeong Hoon Jang, Indiana University

Ultima modifica

Primary PDF

Thumbnail	Title	Date Uploaded	Actions
	Evaluation of color space transformations in separating anemia vs control subjects ()	2021-04-25 23:08:10 -0400	Press to Select an action Download

Supplemental Files

Thumbnail	Title	Date Uploaded	Actions