Back to search

University of Waterloo

New method to improve the diagnostic utility of OCTA images in retinal disease

Abstract

dc:description.abstract

Purpose: Diagnosing medical images necessitates years of experience to ensure accurate diagnoses. However, the current workforce available for this task falls significantly short compared to the volume of images requiring assessment. This places a considerable burden on the medical system during diagnosis. Additionally, medical images often contain artifacts, further complicating and prolonging the diagnostic process. This thesis serves as a solution to expedite diagnosis by enhancing the image quality of Optical Coherence Tomography Angiography (OCTA) images, thereby alleviating the strain on the system. Aims: 1. Method 1 (Chapter 2): Removal of motion artifacts from OCTA images. It is one of the toughest artifacts to be removed from an image. 2. Method 2 (Chapter 3): Super-Resolution of OCTA image. Increasing the dimensions of the image and enhancing the quality to make diagnosis process efficient. Conclusion: This work allows the removal of motion artifacts from the OCTA image and then enhance the quality of the image using super-resolution. In chapter 4 we show that the scatterplots were used to compare the correlations of the most commonly used parameters, Foveal Avascular Zone (FAZ) area, perimeter, and circularity index, between before and after super-resolution at ×2 and ×3 magnification. A p-value < 0.05 was considered significant for all statistical tests. Thus, making the diagnosis process simpler and better for medical practitioners.

Degree

thesis:*
Grantor dc:publisher
University of Waterloo
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • BHARDWAJ, RISHAV
Advisor dc:contributor.advisor
  • BHARDWAJ, RISHAV

Subjects

dc:subject × 4

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/10012/20588

Chain of custody

source
Harvested from
University of Waterloo
Base URL
dspacemainprd01.lib.uwaterloo.ca/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

BHARDWAJ, RISHAV. New method to improve the diagnostic utility of OCTA images in retinal disease. University of Waterloo, 2024. http://hdl.handle.net/10012/20588