脑影像智能分析与脑疾病早期诊断

脑影像智能分析与脑疾病早期诊断张道强南京航空航天大学BrainProjects美国“脑活动图谱”计划欧盟“人类脑计划”中国脑计划BrainImaging(Neuroimaging)•Neuroimagingincludestheuseofvarioustechniquestoeitherdirectlyorindirectlyimagethestructureorfunctionofthebrain•TwobroadcategoriesStructuralneuroimagingdealswiththestructureofthebrainFunctionalneuroimagingisusedtoindirectlymeasurebrainfunctionsNeuroimaging-basedClassification(S.Lemm,etal.,Neuroimage,2011)Example:BrainDecoding(NatureFeatureNews,2013)(T.Mitchelletal.,Science,2008)RecoveryMoviesOutlineSummary123BackgroundsonAlzheimer’sDiseaseBrain-imagingbasedAnalysisBrain-networkbasedAnalysis4HistoryofAD•ADwasfirstdescribedbyGermanpsychiatristandneuropathologistAloisAlzheimerin1906andwasnamedafterhim•The51y.o.woman(AugusteDeter)caredbyDr.Alzheimeruntilherdeathin1906.Hedidanautopsy,examinedherbrain&describedthetypicalabnormalitiesofwhatwouldbecalledlaterAlzheimer’sDiseaseWhatIsAD?•Itisthemostcommonformofdementia•Thereisnocureforthedisease,whichworsensasitprogresses,andeventuallyleadstodeath•Mostoften,ADisdiagnosedinpeopleover65yearsofage•In2006,therewere26.6millionsufferersworldwide,anditispredictedtoaffect1in85peoplegloballyby2050不同年代我国痴呆和AD患者的人数【Lancet.2013】1.“三高”：患病率高、致残率高、负担重2.“三低”：就诊率低、诊断率低、治疗率低目前我国AD的患病率【Alzheimer's&Dementia.2013】我国AD现状:CelebritieswithADNormalvs.ADBrain•Inthenormalbrainthereisalotofhealthybraintissueinthelanguagearea.IntheADaffectedbrainthereislittleinthatarea•Therearemanydifferencesbetweenthetwobrainsincludingthememory,sulcus,gyrus,ventricle,andlanguageareas.IntheADbrain,theseareeithershrunkenorstretchedouttounhealthymeasuresNormalvs.ADBrain•FormsabnormalclumpscalledamyloidplaquesandtangledbundlesoffiberscalledneurofibrillarytanglesinthebrainAD自画像1967（早年）1996（患病第2年）1997（患病第3年）199819992000Normalordiseased?(S.Crutch,etal.,LancetNeurology,2012)Normalordiseased?(S.Crutch,etal.,LancetNeurology,2012)ADProgression•ADatrophyprogresses▫StartsinthemedialtemporalandlimbicareasHippocampusandentorhinalcortex▫Subsequentlyspreadingtoparietalassociationareas▫FinallytofrontalandprimarycorticesADBiomarkers•BiomarkersforearlydiagnosisofAD▫Magneticresonanceimaging(MRI)▫Positronemissiontomography(PET)▫Cerebrospinalfluid(CSF)---Aβ42,t-tauandp-tau▫…MRIPETCSFBiomarkersOutlineSummary123BackgroundsonAlzheimer’sDiseaseBrain-imagingbasedAnalysisBrain-networkbasedAnalysis4MultimodalClassification•Motivation▫SeveralmodalitiesofbiomarkershavebeenprovedtobesensitivetoAD,oritsprodromalstage,i.e.,mildcognitiveimpairment(MCI)▫Differentbiomarkersprovidecomplementaryinformation,whichmaybeusefulfordiagnosisofADorMCIwhenusedtogether•Question:Howcanweeffectivelycombinebothimagingdata(MRIandPET)andnon-imagingdata(CSF)formulti-modalitybasedclassification?FlowchartTemplateMRIdataPETdataCSFdata68,131,21,42,……FeatureextractionFeatureextractionFeatureselectionCalculatekernelmatrixCalculatekernelmatrixCalculatekernelmatrixSVMoptionalKKeerrnneellccoommbbiinnaattiioonn(D.Zhang,etal.Neuroimage,2011)Materials•202subjectsfromADNI,including51ADpatients,99MCIand52healthycontrols▫43MCIconverterswhohadconvertedtoADwithin18monthsand56MCInon-converterswhohadnotconverted▫OnlybaselinedataofMRI,CSFandPETareusedAD(n=51;18F/33M)MCI(n=99;32F/67M)HC(n=52;8F/34M)MeanSDRangeMeanSDRangeMeanSDRangeAge75.27.459-8875.37.055-8975.35.262-85Education14.73.64-2015.92.98-2015.83.28-20MMSE23.82.020-2627.11.724-30291.225-30CDR0.70.30.5-10.50.00.5-0.500.00-0ResultsADvs.HCMCIvs.HCMethodsACC(%)SEN(%)SPE(%)ACC(%)SEN(%)SPE(%)MRI86.2(82.9-89.0)86(82.7-88.7)86.3(83.1-89.1)72.0(68.4-74.7)78.5(75.6-80.6)59.6(55.1-63.7)CSF82.1(80-84.9)81.9(80-84.7)82.3(80-85.1)71.4(68.2-73.3)78(75.6-79.4)58.8(54.3-61.7)PET86.5(82.9-90.5)86.3(82.7-90.3)86.6(83.1-90.6)71.6(67.4-74.7)78.2(75-80.6)59.3(52.9-63.7)Combined93.2(89.0-96.5)93(88.7-96.3)93.3(89.1-96.6)76.4(73.5-79.7)81.8(79.4-84.4)66.0(62.6-70.3)Baseline91.5(88.5-96.5)91.4(88.3-96.3)91.6(88.6-96.6)74.5(71.9-78.2)80.4(78.3-83.3)63.3(59.7-68.3)Comparisonofperformanceofsingle-modalandmultimodalclassificationmethods(D.Zhang,etal.Neuroimage,2011)Multi-ModalMulti-TaskLearning•Motivation▫Besidesclassification,therealsoexistregressiontaskswhichestimatecontinuousclinicalscorestoevaluatethestageofADpathologyandpredictfutureprogression▫Bothregressionandclassificationtasksareessentiallyrelatedduetothesameunderlyingpathology•Question:Howcanwejointlypredictmultipleregressionandclassificationvariablesfrommulti-modalitydata?AD/MCI/HCMMSEADAS-Cog(D.Zhang,D.Shen.Neuroimage,2012)FlowchartTemplateMRIdataPETdataCSFdataFeatureextractionFeatureextractionSVM(Regression/Classification)68,131,21,42,……ClinicalscoresMMSE；ADAS-CogClassLabelsCalculatekernelmatrixSVM(Regression/Classification)Multi-modelSVMKKeerrnneellcombinationCalculatekkeerrnneellmmaattrriixxCCaallccuullaatteekernelmatrixMTFSMulti-taskfeatureselectionMTFS(D.Zhang,D.Shen.Neuroimage,2012)Materials•ADNISubjects▫186subjects(45AD,91MCIand50HCs),onlybaselinedata,3modalities(MRI,CSFandPET)deviatiExperiments•Experiment1▫Estimatingclinicalstages▫MMSE,ADAS-Cog,andclasslabel(AD/MCI/HC)•Experiment2▫Predicting2-yea