Institutional Repository of Vilnius University
Investigation of eye fundus blood vessel segmentation using autoencoders /
Abstract
dc:descriptionProgress of compact high definition digital retinal cameras allowed us to reveal structural and functional information about the human retina in a harmless and non-invasive way. Eye diseases cause noticeable pathological changes, so segmentation of vessels in fundus images is of great importance. In this research work I developed a new retinal vessel segmentation method that achieves state-of-the-art performance in several metrics and with threshold optimization the model showed comparable results to well researched methods on cross datasets experiments on the segmentation task.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Shirvinskii, Aleksandr,
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- eng
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD192965587&prefLang=en_US