Računalom potpomognuto učenje u internoj medicini zasnovano na digitalnoj obradi slike

scientific master's theses

• Title (english): Computer aided learning in internal medicine based on digital image processing
• Author: Marko Šamšalović; VIAF: 305655240
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Sven Lončarić (predsjednik povjerenstva)
• Committee member: Zoran Kalafatić (član povjerenstva)
• Committee member: Željko Hocenski (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Electronics, Microelectronics, Computer and Intelligent Systems); Zagreb
• Defense date and country: 2008-11-27, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing; Data Processing
• Universal decimal classification (UDC): 004 - Computer science and technology. Computing. Data processing ; 61 - Medical sciences

Abstract

Jedan od većih problema kod ultrazvučne dijagnostike je u tome što dijagnostičar mora imati dosta iskustva za tumačenje ultrazvučnih slika. Ovaj magistarski rad bavi se načinima kako pomoći mladim liječnicima i studentima medicine u bržem svladavanju tog problema. Predloženi algoritmi za pomoć pri učenju pronalaženja granica u ultrazvucima su morfološki gradijent (s dva različita strukturna elementa), Sobelov operator i Cannyjev algoritam. Za svaki od algoritama je razvijena i priprema slike radi dobivanja što boljih rezultata. Parametri za algoritme i odgovarajuće pripreme slika određeni su na grupi ultrazvučnih slika štitnjače. Nakon toga su testirani na velikoj testnoj skupini ultrazvučnih slika i određen je najbolji algoritam. Na kraju su svi algoritmi ugrađeni u program za podršku učenju u internoj medicini i određene su buduće faze u razvoju dotičnog programa.

Abstract (english)

One of the biggest problems in ultrasound diagnostics is the fact that the person who is doing the diagnostics must have big experience to be able to interpret it correctly. These theses are about ways to aid young doctors and medicine students in faster acquiring of that experience. Following algorithms are proposed: morphological gradient (with two different structuring elements), Sobel operator and Canny algorithm. Image preparation for better results is developed for each of those algorithms. Parameters for those algorithms and image preparations are calculated on a group of thyroid gland ultrasounds. Algorithms were later tested on a large test group of ultrasounds and the best algorithm was found. All of the algorithms were later implemented in software for aid in learning in internal medicine. Next phases of software development were established.

• Keywords: ultrazvuk; matematička morfologija; Sobelov operator; Cannyjev algoritam; računalom potpomognuto učenje
• Keywords (english): ultrasound; mathematical morphology; Sobel operator; Canny algorithm; computer based learning
• Language: croatian
• URN:NBN: urn:nbn:hr:168:047426
• Study programme: Title: Postgraduate master programe in computing; Study programme type: university; Study level: postgraduate; Academic / professional title: magistar inženjer računarstva (magistar inženjer računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2020-06-05 06:34:33