Classification of anemia severity from real-life conjunctival images

Once anemia has been identified in a patient, its severity is a significant factor in planning treatment. Images of the palpebral conjunctiva have been shown to be accurate in assessing a patient’s hemoglobin concentration without the need to draw blood. In this work, we aim to demonstrate the efficacy of these methods in assessment in real conditions, using consumer-grade equipment. We apply vessel segmentation methods and a linear color mixing model to estimate the color of blood, and, then, use that color to classify anemia severity. Our results indicate that these methods can classify anemia severity at a similar level to human clinicians using a color scale on drawn blood, using images taken in a real-life hospital setting. Additionally, we review conditions and limitations unique to the task of assessing the severity of anemia.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2023

Author dc:creator

• Huang, Bryan

Contributors dc:contributor

• Ahuja, Narendra

• Image Processing
• Conjunctiva
• Anemia

Statement dc:rights

• Copyright 2023 Bryan Huang

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/122115

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F122115