基于DSA圖像的腦血管瘤輔助診斷研究.pdf

1、蘇州大學(xué)碩士學(xué)位論文基于DSA圖像的腦血管瘤輔助診斷研究姓名：孫曉平申請(qǐng)學(xué)位級(jí)別：碩士專(zhuān)業(yè)：計(jì)算機(jī)應(yīng)用技術(shù)指導(dǎo)教師：崔志明20090501AbstractWiththerapiddevelopmentofcomputertechnologyandthesuccessfulapplicationofmedicalimaginginclinicaldiagnosis，thecomputeraideddiagnostictechniqueis

2、growingfastItisstilltodiagnosecerebralaneurysmaccordingtoobservingangiographyimagesbyclinician，whosedisadvantageispooraccuracyandobjectivityAtpresent，computeraideddiagnosisforcerebralaneurysmtechnologyisstillatresearchst

3、age，SOthereisnoclinicalapplicationThispapersummarizesthecurrentwidelyusedcomputeraideddiagnosissystemsinclinicaldiagnosis，themajorcomputeraidedtechniquesandmethodsandpresentsasetofcomputeraideddiagnosisforcerebralaneurys

4、mscheme，includinglocatingthesuspectedcerebralaneurysmlesionareasandstatisticalclassificationbasedoncharacteristicsofcerebralaneurysmFirstlythispaperdoesresearchonbasicknowledgesuchascerebralaneurysmandDSAimagingprinciple

5、andSOon；analyzestheprocessesandmethodsofcerebralaneurysmdiagnosisbycliniciansOnthisbasis，thispaperpresentsthesuspectedlesionareaslocatingmethodbasedontheskeletoncharacteristics，whichCanbeusedtotargetthelocationofsuspecte

6、dlensionarea，andprovideimportantdetailsofDSAimagetodoctors，whosemeaningistoavoidneglectingdetailsofDSAimagesduetodoctorsthemselves，andassistdoctorsincerebralaneurysmsdiagnosisAtthesametime，thispaperanalyzesthecharacteris

7、ticsofcerebralbloodvesselsDSAimages，anddoesfastboundarytrackingaccordingtothedirectionofmemoryobtainsthegeometryinformationofborderandextractsthecharacteristicshapeofcerebralaneurysmSecondlythispaperpresentstheidentifica

8、tionmethodofcerebralaneurysmbasedonstatisticalclassificationalgorithm，whichusesRBFneuralnetwork，supportvectormachine(SVM)algorithmandBayesianalgorithmtoclassifytheshapefeaturesofcerebralaneurysm；analyzesandcomparestheres