Registracija bilateralnih mamograma i analiza lezija iz vremenski odmaknutih digitalnih mamograma

doctoral thesis

• Title (english): Bilateral Mammogram Registration and Temporal Analysis of Lesions in Digital Mammograms
• Author: Jelena Božek
• Mentor: Mislav Grgić (mentor)
• Committee member: Mislav Grgić (predsjednik povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Communication and Space Technologies); Zagreb
• Defense date and country: 2013-06-05, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Universal decimal classification (UDC): 621.3 - Electrical engineering ; 004 - Computer science and technology. Computing. Data processing

Abstract

U doktorskom radu provedeno je vrednovanje postupka neprilagodljive registracije nad mamografskim slikama. Nadalje, uspoređeni su različiti interpolacijski postupci i njihov utjecaj na mamograme s ciljem određivanja optimalnog interpolacijskog postupka za registraciju i usporedbu mamografskih slika u svrhu određivanja asimetrije dojki. U radu je predložen algoritam za detekciju i klasifikaciju lezija u vremenski odmaknutim digitalnim mamogramima. Predložene su volumetrijske značajke čija primjena je ostvarila bolju učinkovitost u odnosu na primjenu značajke dobivene iz informacije o površini lezije. Nadalje, vremenske značajke dobivene kao relativna razlika značajki iz trenutnog i prethodnog mamograma značajno su unaprijedile učinkovitost klasifikacije benignih i malignih lezija u odnosu na korištenje samo značajki iz trenutnog pregleda.

Abstract (english)

The thesis presents the evaluation of rigid registration of left and right mammogram. Furthermore, different interpolation methods were compared and their influence on mammograms was evaluated in order to define the optimal interpolation method for registration and comparison of mammograms. The thesis proposes the algorithm for detection and classification of lesions in temporal digital mammogram pairs. The use of volume as a feature was compared to the area as a feature for determining lesion size. Moreover, additional volumetric features have been extracted from lesions visible in current and prior mammograms and their use achieved better classification performance compared to the area feature. Furthermore, volumetric features from temporal mammogram pairs combined with features from the single exam significantly improved discrimination of benign and malignant lesions in digital mammograms compared to using only single exam features.

• Keywords: mamografija; digitalni mamogrami; registracija mamograma; interpolacija; vremenska analiza mamograma; volumetrijske značajke; klasifikacija lezija
• Keywords (english): mammography; digital mammograms; mammogram registration; interpolation; temporal analysis of mammograms; volumetric features; lesion classification
• Language: croatian
• URN:NBN: urn:nbn:hr:168:687772
• Project: Number: 036-0361630-1635; Title: Upravljanje kvalitetom slike u radiodifuziji digitalnog videosignala; Leader: Sonja Grgić; Jurisdiction: Croatia; Funder: MZOS; Funding stream: ZP
• Project: Number: 036-0982560-1643; Title: Inteligentno određivanje značajki slike u sustavima za otkrivanje znanja; Leader: Mislav Grgić; Jurisdiction: Croatia; Funder: MZOS; Funding stream: ZP
• Study programme: Title: Doctoral study programme "Electrical Engineering and Computing"; Study programme type: university; Study level: postgraduate; Academic / professional title: doktor/doktorica znanosti, po-dručje tehničkih znanosti (doktor/doktorica znanosti, po-dručje tehničkih znanosti)
• Catalog URL: http://lib.fer.hr/cgi-bin/koha/opac-detail.pl?biblionumber=41291
• Type of resource: Text
• Extent: 129 str. ; 30 cm.
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-11-28 12:32:33