TISSUE FEATURE-BASED AND SEGMENTED DEFORMABLE IMAGE REGISTRATION

TISSUE FEATURE-BASED AND SEGMENTED DEFORMABLE IMAGE REGISTRATION

ID:40984206

大小:1.11 MB

页数:10页

时间:2019-08-12

TISSUE FEATURE-BASED AND SEGMENTED DEFORMABLE IMAGE REGISTRATION_第1页
TISSUE FEATURE-BASED AND SEGMENTED DEFORMABLE IMAGE REGISTRATION_第2页
TISSUE FEATURE-BASED AND SEGMENTED DEFORMABLE IMAGE REGISTRATION_第3页
TISSUE FEATURE-BASED AND SEGMENTED DEFORMABLE IMAGE REGISTRATION_第4页
TISSUE FEATURE-BASED AND SEGMENTED DEFORMABLE IMAGE REGISTRATION_第5页
资源描述:

《TISSUE FEATURE-BASED AND SEGMENTED DEFORMABLE IMAGE REGISTRATION》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、Int.J.RadiationOncologyBiol.Phys.,Vol.74,No.4,pp.12561265,2009CopyrightÓ2009ElsevierInc.PrintedintheUSA.Allrightsreserved0360-3016/09/$seefrontmatterdoi:10.1016/j.ijrobp.2009.02.023PHYSICSCONTRIBUTIONTISSUEFEATURE-BASEDANDSEGMENTEDDEFORMABLEIMAGEREGISTRATIONFORIMPROVEDMODELI

2、NGOFSHEARMOVEMENTOFLUNGSyYAOQINXIE,PH.D.,*MINGCHAO,PH.D.,*ANDLEIXING,PH.D.**DepartmentofRadiationOncology,StanfordUniversitySchoolofMedicine,Stanford,CA;andyBeijingCityKeyLaboratoryofMedicalPhysicsandEngineering,PekingUniversity,Beijing,PeoplesRepublicofChinaPurpose:Toreport

3、atissuefeature-basedimageregistrationstrategywithexplicitinclusionofthedifferentialmo-tionsofthoracicstructures.MethodsandMaterials:Theproposedtechniquestartedwithauto-identificationofanumberofcorrespondingpointswithdistincttissuefeatures.Thetissuefeaturepointswerefoundbyusin

4、gthescale-invariantfeaturetrans-formmethod.Thecontrolpointpairswerethensortedintodifferent‘‘colors’’accordingtotheorgansinwhichtheyresidedandusedtomodeltheinvolvedorgansindividually.Athin-platesplinemethodwasusedtoregisterastructurecharacterizedbythecontrolpointswithagiven‘‘

5、color.’’Theproposedtechniquewasappliedtostudyadigitalphantomcaseand3lungand3livercancerpatients.Results:Forthephantomcase,acomparisonwiththeconventionalthin-platesplinemethodshowedthatthereg-istrationaccuracywasmarkedlyimprovedwhenthedifferentialmotionsofthelungandchestwallw

6、eretakenintoaccount.Onaverage,theregistrationerrorandstandarddeviationofthe15pointsagainsttheknowngroundtruthwerereducedfrom3.0to0.5mmandfrom1.5to0.2mm,respectively,whenthenewmethodwasused.Asimilarlevelofimprovementwasachievedfortheclinicalcases.Conclusion:Theresultsofourstu

7、dyhaveshownthatthesegmenteddeformableapproachprovidesanaturalandlogicalsolutiontomodelthediscontinuousorganmotionsandgreatlyimprovestheaccuracyandrobustnessofdeformableregistration.Ó2009ElsevierInc.Image-guidedradiotherapy,deformableimageregistration,segmentation.INTRODUCTIO

8、Nconsistofvarioustissues,suchasthetrachea,bronchia,andalveoli,whichcanhardl

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。