Correspondence Transfer for the Registration of Multimodal Images(10)

rather

parisonwithMutualInformation:(top)warping

andregistrationusingmutualinformation,and(bottom)usingourapproach.Noticethatthedarkregioninthetemplateismappedinahighlyirregularfashiontothetarget,andtheitsgeometricstructureisnotpreserved.Ourcombinedmodel,displayedinthebottompartoftheimage,showsamoreplau-sibledeformation eld,withunilateralregionsbeingsmoothlymappedintotheanatomicaltemplate,andbilateralregionscor-rectlydeformed.

irregular,andinparticularthedarkregionoftheleftbe-comes“turbulent”inawaythatisnotcompatiblewithhigh-levelknowledgeofanatomy.Ourapproach(bot-tom),ontheotherhand,showsthatunilateralregionsaremappedsmoothlywhilebilateralfeaturesaredeformedconsistently.AdditionalexamplesondifferenttestdataarereportedinFig.4.

InFig.5weshowsomerepresentativeexperimentswhereourapproachfailstoyieldameaningfulcorre-spondence.Asitcanbeseen,thetemplateisdeformedlocally,sothefoldvisibleinthetargetisnotcorrectlymapped.Thiskindofbehavioristobeexpectedsinceouralgorithmisbasedonadatadiscrepancytermalone,whichencodesbottom-up,low-levelinformationandisoblivioustoanyknowledgeoftheanatomyorphysicsoftheunderlyingstructures.Thiscanbeobviatedbytakinghigh-levelpriorinformationintoaccount,anissuethatisbeyondourscopeinthispaper,whereconsiderableef-fortsareundergoinginthemedicalimagingcommunity.

搜索“diyifanwen.net”或“第一范文网”即可找到本站免费阅读全部范文。收藏本站方便下次阅读，第一范文网，提供最新外语学习Correspondence Transfer for the Registration of Multimodal Images(10)全文阅读和word下载服务。