摘要
Pulmonaryvesselsextractionisachallengingtaskinclinicalmedicine.Manypulmonarydiseasesareaccompaniedbythechangesofvesseldiameters.Thevesselsandtheirbranches,whichexhibitmuchvariability,aremostimportantinperformingdiagnosisandplanningthefollow-uptherapies.Inthispaper,weproposeanefficientapproachtopulmonaryvesselsextractionbasedonthecurveevolution.Thisapproachmodelsthevesselsasmonotonicallymarchingfrontunderthespeedfieldintegratingboththeregionandtheedgeinformationwhereanewregionspeedfunctionisdesignedandintegratedwiththeedgebasedspeedfunction.Duetotheregionbasedspeedterm,thefrontcouldevenpropagateinsmallnarrowvesselbranches.Tofurtherimprovethesegmentationresults,amulti-initialfastmarchingalgorithmisdevelopedtofastimplementthenumericalsolution,whichmayavoidthemonotonicallymarchingfrontleakingoutoftheweakboundarytooearlierandalsoreducethecomputationalcost.ThevalidityofourapproachisdemonstratedbyCTpulmonaryvesselsextraction.Experimentsshowthatthesegmentationresultsbyourapproach,especiallyonthenarrowthinvesselbranchesextraction,aremoreprecisethanthatoftheexistingmethod.
出版日期
2004年01月11日(中国Betway体育网页登陆平台首次上网日期,不代表论文的发表时间)