Segmentacija križanja i grananja krvnih žila u slikama očne pozadine

master's thesis

• Title (english): Segmentation of crossings and branchings of blood vessels from fundus images
• Author: Kristina Topčić
• Mentor: Marko Subašić (mentor)
• Committee member: Marko Subašić (predsjednik povjerenstva)
• Committee member: Sven Lončarić (član povjerenstva)
• Committee member: Tomislav Pribanić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Pravovremeno liječenje dijabetičke retinopatije vrlo je važno za sprječavanje razvoja sljepoće kod dijabetičara. Retinopatiju karakteriziraju neovaskularizacije i krvarenja u mrežnici te ih je potrebno pratiti od ranih stadija bolesti. U ovom istraživačkom radu opisan je postupak segmentacije križanja i grananja krvnih žila. Algoritam je razvijen za dva poprečna presjeka krvnih žila – pravokutni i Gaussov. Detektira se središte grananja i križanja žila traženjem i analizom lokalnih ekstrema vlastitih vrijednosti Hessianove matrice u smjeru najznačajnijeg vlastitog vektora.

Abstract (english)

Early treatment of diabetic retinopathy is very important in prevention of blindness development for diabetic patients. Retinopathy is characterized by neovascularization and bleeding in the retina, and must be monitored from the early stages of the disease. This paper describes segmentation of blood vessel crossing and branching. The algorithm is developed for two cross sections of blood vessels - rectangular and Gaussian. The center of vessel branching and crossing is detected by estimating and analysing local extremes of eigenvalues of Hessian matrix in the direction of the most significant eigenvector.

• Keywords: dijabetička retinopatija; krvne žile; grananje žila; križanje žila; konvolucija; Gaussova funkcija; Hessianova matrica; vlastite vrijednosti; vlastiti vektori
• Keywords (english): diabetic retinopathy; blood vessels; vessel branching; vessel crossing; convolution; Gaussian function; Hessian matrix; eigenvalues; eigenvectors
• Language: croatian
• URN:NBN: urn:nbn:hr:168:917311
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 14:09:08