预览加载中，请您耐心等待几秒...

基于快速Hessian矩阵的MSCT图像血管增强（英文）.docx

预览
1/2
2/2

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

基于快速Hessian矩阵的MSCT图像血管增强（英文） Introduction Computedtomography(CT)hasbecomeanimportanttoolforthediagnosisofvariousdiseases.However,theconventionalCTimageslackthecontrastrequiredforprecisediagnosis,especiallyinthecaseofsmallbloodvessels.Therefore,itisessentialtoenhancethecontrastofbloodvesselsforaccuratediagnosis.Inthispaper,weproposeamethodforenhancingbloodvesselsusingthemaximumsymmetricsurround(MSS)filterbasedonthefastHessianmatrix. Methodology TheproposedmethodstartsbyacquiringCTimagesofthepatientunderconsideration.TheseimagesarethenpreprocessedtoremoveanynoiseusingfilterslikeGaussianfilter.TheMSSfilteristhenappliedtothepreprocessedimagestoenhancethebloodvessels.TheMSSfilterisdesignedtoenhancethecontrastofcircularstructuressuchasbloodvesselswhilesuppressingotherstructures.MSSfilterisbasedonthefastHessianmatrixtodetectsymmetricstructures. Hessianmatrixisusedtofindtheeigenvectorsandeigenvaluesoftheimage.Inthecaseofa2Dimage,Hessianmatrixisa2x2matrix,wheretheeigenvaluescorrespondtothetwoprincipalcurvaturesateachpoint.Theseprincipalcurvaturesprovideinformationaboutthelocalshapeoftheimage.TheHessianmatrixcanbecalculatedefficientlyusingtheDifferenceofGaussian(DoG)filter.TheDoGfilterisaband-passfilterthatemphasizesstructuresinaparticularsizerange. AftercalculatingtheHessianmatrix,MSSfilterisappliedtotheimage.Thefilterworksbycomputingthemaximumandminimumintensityvaluesinacircularneighborhoodaroundeachpixel.Thisisdoneinallpossibleorientations,andthemaximumsymmetricsurroundischosenastheoutput.TheMSSfilter,therefore,suppressesunlikelysymmetricstructuresandenhancessymmetricstructures. Results TheproposedmethodwasevaluatedonclinicalCTdatasets.Theresultsshowedthatourmethodsuccessfullyenhancedthecontrastofbloodvesselsandremovedunwantedstructures.Theenhancedimageswerequantitativelycomparedwiththeoriginalimagesusingmetricslikecontrast,signal-to-noiseratio(SNR),andtheareaunderthereceiveroperatingcharacteristic(ROC)curve.Theresultsshowedasignificantimprovementinallthesemetrics,validati