Automated Quantification of Macular Vasculature Changes from OCTA Images of Hematologic Patients

Astrid Margareta Elisabet Engberg, Abdullah Amini, Anne Willerslev, Michael Larsen, Birgit Sander, Line Kessel, Anders Bjørholm Dahl, Vedrana Andersen Dahl

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

78 Downloads (Pure)

Abstract

Abnormal blood compositions can lead to abnormal blood flow which can influence the macular vasculature. Optical coherence tomography angiography (OCTA) makes it possible to study the macular vasculature and potential vascular abnormalities induced by hematological disorders. Here, we investigate vascular changes in control subjects and in hematologic patients before and after treatment. Since these changes are small, they are difficult to notice in the OCTA images. To quantify vascular changes, we propose a method for combined capillary registration, dictionary-based segmentation and local density estimation. Using this method, we investigate three patients and five controls, and our results show that we can detect small changes in the vasculature in patients with large changes in blood composition.
Original languageEnglish
Title of host publicationProceedings of 17th IEEE International Symposium on Biomedical Imaging
PublisherIEEE
Publication date2020
Pages1987-1991
Article number9098441
ISBN (Print)9781538693308
DOIs
Publication statusPublished - 2020
Event IEEE International Symposium on Biomedical Imaging - Coralville Marriott Hotel & Conference Center, Iowa City, United States
Duration: 2 Apr 20207 Apr 2020

Conference

Conference IEEE International Symposium on Biomedical Imaging
LocationCoralville Marriott Hotel & Conference Center
CountryUnited States
CityIowa City
Period02/04/202007/04/2020

Keywords

  • OCTA
  • Quantification
  • Microvasculature

Fingerprint Dive into the research topics of 'Automated Quantification of Macular Vasculature Changes from OCTA Images of Hematologic Patients'. Together they form a unique fingerprint.

Cite this