The analysis of microscopy images of corneal endothelium is quite important to assess cornea health state and quality. Clinicians are interested in determining clinical parameters as indicators of corneal pathologies. This thesis is part of a broader research work, aimed at developing an algorithm that can automatically segment images of corneal endothelial specular microscopy and than can be used for the automatic estimation of clinical parameters that allow the physician to determine corneal endothelial health status of the patient and formulate a diagnosis. Starting point are the images acquired with the corneal endothelial specular microscopy technique. An algorithm for endothelial cell segmentation has been developed for these images.

Segmentazione automatica di cellule endoteliali in immagini della cornea da microscopia speculare

Giudiceandrea, Arianna
2011/2012

Abstract

The analysis of microscopy images of corneal endothelium is quite important to assess cornea health state and quality. Clinicians are interested in determining clinical parameters as indicators of corneal pathologies. This thesis is part of a broader research work, aimed at developing an algorithm that can automatically segment images of corneal endothelial specular microscopy and than can be used for the automatic estimation of clinical parameters that allow the physician to determine corneal endothelial health status of the patient and formulate a diagnosis. Starting point are the images acquired with the corneal endothelial specular microscopy technique. An algorithm for endothelial cell segmentation has been developed for these images.
2011-12-05
111
segmentazione, identificazione contorni, rete neurale, endotelio corneale, cornea, pattern recognition
File in questo prodotto:
File Dimensione Formato  
Tesi-Arianna_Giudiceandrea.pdf

accesso aperto

Dimensione 9.64 MB
Formato Adobe PDF
9.64 MB Adobe PDF Visualizza/Apri

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/15396