1、ISOInternationa1.StandardISozIEC35322Firstedition2024-02Informationtechno1.ogyMedica1.image-basedmode1.1.ingfor3Dprinting一F台的格ntationTechno1.ogiesde!informationMode1.isationmedica1.edbasedimagespour!impression3DPartie2:SegmentationReferencenumberISO/IEC3532-22024(en)COPYRIGHTPROTECTEDDOCUMENTISO/IEC
2、2024Wintdcddu1.fk*jdOthenviseCbyqwipMrtiW1.eombXttrCniwkjhrtRkkCTrtWpm9HtUSXnPyiP脾11匕mienmaytheinternetoranintranet,withoutpriorwrittenpermission.PermissiononberequestedfromeitherISOatthebe1.oworISOsmemberbodyinthecountryoftherequester.b,Vyfrfiandonnet8CH-1214Vcmicr,GenevaPhoae:*41227490111聊独te:薪括嬴O
3、QrgPub1.ishedinSwitzer1.andContentsPageForewordIntroductionScopeNormativereferencesTermsanddefinitionsAbbreviatedtermsObjectiveofsegmentation5.1 Background5.2 TypesofsegmentationmethodsOvera1.1.segmentationprocessStep1.jdatapreparationSteP2：耙瑞再做5桶HgforsegmentationStep4：se1.ectionofsegmentationnehvor
4、kmode1.Step5:performanceeva1.uation7Datapreparation7.1Genera1.667.2Medica1.image67.2.267.3Preparationsteps7怔魂局CqUiWtion787.3.3ImagereconstructionPreprocessingforsegmentation78.1Genera1.789Annotation99.1Data1.abe1.1.ing99.2Preprocessingforannotation910Se1.ectionofnetworkmode1.10101.Genera1.*.*-.a.a.a
5、s.*121213 Dep1.oymentandrunning13Post-processingforsegmentation14Annex A (informative)CTscanningconditionsfororbita1.bonesegmentation15Annex B (informative)Characteristicsoforbita1.bonesegmentationfromCT16Annex C (informative)Deep1.earningtechniques18Annex D (informative)Considerationsforovera1.1.s
6、egmentationperformance19Bib1.iography24ForewordISO(theInternationa1.OrganizationforStandardization)andIEC(theInternationa1.E1.ectrotechnica1.GtHmhiEotUamon圈SPadiIHPe出邠tbmfdewvmMidkdh的nd11bahUon.沁Idin旅H岫mghtechniocommitteesestab1.ishedbytherespectiveorganizationtodea1.withparticu1.arfie1.dsoftechnica
7、1.activity.ISOandIECmitteesco1.1.aborateinfie1.dsofmutua1.interest.Otherinternationa1.organizations.governmenta1.andnon-governmenta1.,in1.iaisonwithISOandIEC,a1.sotakepartinthework.Theproceduresusedtodeve1.opthisdocumentandthoseintendedforitsfurthermaintenancearedescribedintheISO/IECDirectives,Part1
8、Inparticu1.ar,thedifferentapprova1.criterianeededforthedifferenttypes岷雌s,s出斯R削副WjI麻蝴中*略皿4“碳国呻W浦用5科g*MFiiIHoftheISO/ISOandIECdrawattentiontothepossibi1.itythattheimp1.ementationofthisdocumentmayinvo1.vethe暗用d（八）patent配曲即跳雌林加品依屏RfngPUbI四ioneW掘谑W立以喊9两0躺fR踮anyreceivednoticeo11a)patent(三)whichmayberequi
9、redtoimp1.ementthisdocument.However,Imp1.ementersarecautionedthatthismayn4叩皿1.h1.atestinformation,whichmaybeobtainedfromthepatenthft1.ei1.ab1.eidtifyinW,uw.1.Vjypateni1.1.t-httpd.ISOandIECsha1.1.notbehe1.dnytradenameusedinthisdocumentisinformationgivenfortheconvenienceofusersanddoesnotconstituteanen
10、dorsement.Foranexp1.anationofthevo1.untarynatureofstandards,themeaningofISOspecifictermsandexpressionsre1.atedtoconformityassessment,aswe1.1.asinformationaboutISO*sadherencetotheWor1.dTradeb1.陟6Sfi活nWTrade(TBT)seewwwriofoFewoFdJum1.ThisdocumentwaspreparedbyJointTechnica1.CommitteeISO/IECJTC1,Informa
11、tiontechno1.ogy.A1.istofa1.1.partsintheISO/IEC3532seriescanbefoundontheISOandIECwebsites.Anyfeedbackorquestionsonthisdocumentshou1.dbedirectedtothebody.Acomp1.ete1.istingofthesebodiescanbefoundatvrrw.iso.orgmembers.htm1.andIntroductionThisdocumentwasdeve1.opedinresponsetotheneedforcustomizationof3Dp
12、rintingtechno1.ogyinthemedica1.industrythroughtheuseofinformationandcommunicationtechno1.ogy(ICT).Therearemanypointswheretheexistingstandardsforadditivemanufacturing(AM)donotmatchtherequirementsofthemedica1.industry.Frommedica1.imagesto3Dprinting,medica1.devicedeve1.opmentisquiteacomp1.exjourneysvit
13、hcomp1.icatedmanagementofmu1.tip1.epiecesofsoftware.Withtheemergingmarkettormedica1.3Dprintedparts,therearemanypointsrequiringstandardization.Meis理抨M9%ndard网蚓s1.W卸岫虫W例桃颂三84va1.idationpr蜘(蔗的他6%Formedica1.3Dprinting,segmentationtechniquesshou1.dbeoptimizedandcombinedaccordingtothecharacteristicsofthem
14、edica1.imagesandcorrespondingbodypartstogetanoptima1.3Dmode1.Inparticu1.ar,duringmedica1.imagesegmentation,identificationofthepixe1.soforgansor1.esionsfromrawdatasuchascomputedtomography(CT)ormagneticresonance(MR)images,isoneofthemostcha1.1.engingana1.ysistasks.Forexamp1.e,segmentationoftheorbita1.b
15、oneisnecessaryfororbita1.wa1.1.reconstructionincranio-maxi1.1.ofacia1.surgerytosupporttheeyeg1.obepositionandrestorethevo1.umeandshapeoftheorbit.丽ever,inW制IWn电arPH做玳捆丽诉股腌施他2中第1如附框nsit痴苦,郎碓则出CortiCa1.bonewithaThehumanboneisde1.ineatedandextractedbysegmentationtechniques,anda3Dske1.eta1.mode1.isbui1.t
16、isfE阴赛盘三t稀JMra除用摘ZatiO晶d囹擀用duringthissegmentation哭硼蛹姗般迎Sin翻痕beforeproceeding.械肥内rates格跟婕BAgXtati相盟曲MXeSP如t同欷,ever,co的所恐&册y(nds掴NruesoAMoUte)PeratOE茯。Ptedminimizationoferrorsduringthisjob,operatorsshou1.dknowwhichsegmentationtechniqueismostusedintheirimagingsoftwareandpossessthenecessaryski1.1.sforth
17、attechnique.QP脚枷I1.edSMk1.掰丽喇卅瞰ft好TB悭媚entatim丽刑砒MyTheprob1.emisusua1.1.yunder-segmentation.However,over-segmentationwi1.1.a1.sobeprob1.ematicforfurtherdesigningprocesses,especia1.1.yforsurgica1.imp1.ants.Varioustechniqueshavebeensuggestedtoreducehumanerrorandimproveperformanceandconsistencyforsegmen
18、tationissues同Thisdocumentproposesastandardizedprocessfortheoptimizationofsegmentation.Informationtechno1.ogyMedica1.image-basedmode1.1.ingfor3Dprinting一ggntation1ScopeThisdocumentprovidesanoverviewofthesegmentationprocessformedica1.image-basedmode1.1.ingOfhumanbone.Segmentation.Thisdocumentspecifies
19、astandardizedprocesstoimprovetheperformanceofhumanboneThisdocumentisa1.soapp1.icab1.etomedica1.3Dprintingsystemsthatinc1.udemedica1.3Dmode1.1.ing2capabi1.ities.NormativereferencesR不眦Htg6entsdtffi1efe11AMA0机底W四布a郎ifH由由诅Q1.a初制6tutesthe1.atesteditionofthereferenceddocument(inc1.udinganyamendments)app1.
20、ies.ISO15708-1,NondestructivetestingRadiationmethodsforcomputedtomographyPart1:Termino1.ogyISO/IEC2382rInformationtechno1.ogyVocabu1.ary31W6FFHfttiOnsmanufacturingGenera1.princip1.esOvemewofdataprocessingfiWI/hS举ftJf1.Qh1够HCWingdWUKent,thetermsanddefinitionsgiveninISO/ASTM52950,ISO15708-1.rISOandIEC
21、maintainIermino1.ogjrdatabasesforuseinstandardizationatthefo1.1.owingaddresses：ISOOn1.inebrowsingp1.atform：avai1.ab1.eathttps卜WWWiSoQgobpj-1ECE1.ectropedia:avai1.ab1.eathttps:WWW.e1.ectropedia.org/imageacquisitionscanningofthestructureOfinterestusingcomputedtomography(CT),magneticresonance(MR)imagin
22、gorgtgerthree-dimensiona1.imagingtechno1.ogyimageannotation股CeSSofattaching1.abe1.stoanimage1.abe1.c1.assifyingphraseornameapp1.iedtoatarget3.41.earningprocessbywhichabio1.ogica1.oranautomaticsystemgainsknow1.edgeorski1.1.sthatitmayusetoimproveitsperformanceNotestoentryhavebeenremoved.SOURCE:1SOIEC2
23、382:2015,2122966,modifiedsegmentationprocessOfseparatingtheobjectsOfinterestfromtheirSunoundingsNote1toentry:Segmentationcanbeapp1.icab1.eto2D.3D,rasterorvectordata.3.6ground-tnith1.abe1.丐ree1.answerofthetrainingsetforsegmentationbasedonsupervised1.earningregionOfinterestRO1.兆Cifiodboundaryasdefined
24、intheimagemachine1.earningM1.processofoptimizingmode1.parametersthroughcomputationa1.techniques,suchthatthernodcsbehaviourref1.ectsthedataorexperiencepgURCE:ISO!EC22989:2022,3.3.5oneormore1.abe1.s1.abe1.1.eddata8POfdatathathavebeentaggedwithIiyperparanietercharacteristicofamachine1.earninga1.gorithm
25、thataffectsitsIeaniingprocessNote1toparameters.entr)r：Hyperparametersarese1.ectedpriortotrainingandcanbeusedinprocessestohe1.pestimatemode1.Note2toentry:Examp1.esofhyperparametersinc1.udenumberofnetwork1.ayers,widthofeachIaycrztypeofactivation的眠砒BIIW廊qfty总艇性a三ksd1.svtM肃取圃NftiHi愉厢时811Aseisexpectation
26、maximizationa1.gorithm：thenumberotGaussiansinaGaussianmixture.依QWRCE:ISO/IEC22989:2022,3.3.4Jmedica1.imagetypeofimagesgeneratedbymedica1.imagingdevices4AbbreviatedtermsA1.artificia1.inte1.1.igenceAIMannotationandimagemarkupCDcomputer-aideddiagnosisCC1.CNNworkCRFCTconditiona1.randomfie1.dcomputedtomo
27、graphyDICOMD1.digita1.imagingandcommunicationsinmedicinedeep1.earningDSCFCNworkFOVFNfie1.dofviewfa1.senegativeFPHUfa1.sepositiveHounsfie1.dunitIoUMIoUintersectionoverunionmeanintersectionoverunionM1.MRmachine1.earningmagneticresonanceMRINIfTImagneticresonanceimagingneuroimaginginformaticstechno1.ogr
28、initiativePETSPECTpositionemissiontomographysing1.e-photonemissioncomputerizedtomographyTNTPtruenegativetruepositive5sObjective2e三址帆qo*5.1BackgroundThepurposeofsegmentationistoextractaspecificregionororganfromapatientsCT/MRmedica1.imageanduseittocreatea3Dmode1.Segmentationistheprocessofpartitioninga
29、nimageintodifferentmeaningfu1.segments.Formedica1.imageqyre11tntmodatahojuwibbdyIdpartieoptji3wiiden1.(5U)YrrtmUrttion.ac(fDhdinHutanichartoienbtcdofandextractedbysegmentationtechniques,anda3Dske1.eta1.mode1.isbui1.tfromthissegmentation.Theminimizationoferrorsduringsegmentationofre1.evantanatomyiscr
30、itica1.旭曲I11ffiFdW自辂PhUn1.qntingtissue昶轴厢降三mgmentati8htfhR1M1T邦面明ngi献esoftwarecannotsegmenthumanboneeffective1.y.Forr出睢f1.ovedmedica1.imagebased3Dmode1.1.ing,forma1.izationandstandardizationoftheseproceduresis5.2TypesofsegmentationmethodsSevera1.methodshavebeeninvestigatedthatsegmenthumanbonefromCTi
31、nagcs.(iai9(221123)“闻WM。修e*臃期炭Etat1.Q想我刎的想必，帔险。*3tiw3re版M故M加他CinSCg1.nCntatiem.widobjectpixe1.ifthepixe1.intensityisgreaterthanaspecifichumanbonethresho1.dva1.ue,orrep1.acesitwithabackgroundpixe1.ifthepixe1.intensityis1.essthanaspecifichumanbonethresho1.dva1.ue.则阳出柚三tf三wMf三四治”咖加瞭碗6淋耐boundaries.Thein
32、terna1.forcesaredefinedsuchthattheypreservetheshapesmoothnessofthemode1.Whi1.Ctheexterna1.forcesaredefinedbytheimagefeaturestodrivethemode1.towardthedesiredregion帆晒BySh嘟S懈肥慨r三8端ariesrobusmesssmoo/独dIJ三蝌厘JoIta喇ft三布聊However,thereisa1.imitduetothedifficu1.tyofsegmentationattheweakobjectboundaryofathinb
33、onewitha1.owintensityva1.uesimi1.artosofttissue.IXIQiNmK常&SSegmdh吆HOnPa廊由中CN1.M1.Wkg淋期神幽QayerS玳部VUI帆心品似*hkd!给临三1.yusedformedica1.imagesegmentation,workandconsistsofacontractingpathandanexpansivepath,whichgivesittheU-shapedarchitecture.6Overa1.1.segmentationprocess6.1 Genera1.Theovera1.1.segmentation
34、processconsistsofsevenstepsintota1.,asdescribedin6.2to6.8.Figure1showstheovera1.1.processf1.owofsegmentation,wherethenumbersinparenthesisrefertoc1.ausesofthisdocument.SOIEC2024-A1.1.rightsreserved4Trainingphasef1.ow(CUum12)(CauseB)RunningPhaSe11owFigure1Overa1.1.processf1.owOfsegmentationThesoftware
35、deve1.opershou1.dimp1.ementtheoptimizedsegmentationprocessformedica1.image-basedmode1.1.ing.Theconsiderationsoftheoptimizedsegmentationprocessformedica1.image-basedmode1.1.ingshou1.dbereferencedfromthisdocument.6.2 Step1:datapreparationTheobjectiveofthedatapreparationstageistotransirgforfgmiutationC
36、1.ause7.丽制懵耀的由fition源郴c嘤tagesg皿由O班淋媚和es在於胸布曲f1.，施厢WPWqUa1.iB*4的痴nduceto1.earn.Detai1.edinformationisprovidedinC1.ause8.6.4 Step3:annotationTheobjectiveoftheannotationstageistomakethe1.abe1.1.edtrainingdatafiUrXhe1.earningofM1.D1.-6a5cS1.ep；4rfie1.eotiQn:efjikmk)ttakidnetwat?kini0de1.isprovidedinC1.a
37、use9.XBftvorko帮困9b施etai1.eHiWS&HiWetWO新用费修。OnStageistose1.ecttheoptima)segmentation6.6Step5:performanceeva1.uationTheobjectiveoftheperformanceeva1.uationstageistoca1.cu1.atetheagreementbetweentheresu1.tofBnR1.JnB1.thesegmentationtechniqueandtheground-truth1.abe1.Detai1.edinformationisprovidedin6.7 S
38、tep6:mode1.dep1.oymentandrunningmode1.environmentprintingDetai1.edinformationisachievingC1.ausemaximizedsegmentationperformanceinarea1.6.8 Step7:post-processingforsegmentationthesegmentationpreparationDetai1.edinformationisprovidedinC1.ause13.7.1 Genera1.7.2 beMedica1.image7.2.1 Genera1.Generatedsca
39、nners.NormaIIy1FromVariousreconstructedfromStoredorStandardizedproduced(eg.detectors.7.2.2 CTscanpixc1.body.-1024,3072,s1.icebecausemosttypica1.1.ystored12StorageDICOMperformat.Eachintensityrangeofva1.uegeneratescannerseriesofmu1.tip1.eradiographicprojectionsandportionusesthehumanreconstructionreso1
40、utionoftheWhenobtaininghumanqua1.itymedica1.examp1.e,InstandardizedtheSCanningbone,parameterCondidonsrecommendationused7.2.3 MRimageforthemagneticphysio1.ogica1.examinationofpatientMRIscannersuseimagingtechniquefie1.ds,magneticStandardizedMRIscanningconditionsorMRIscanningprofi1.esshou1.dbeconsider
41、ed.Theobjectiveofthedep1.oymentandrunningstageistoapp1.ytheoptima1.1.ytraineddeep1.earningnetworkwor1.dthe3Dmode1.1.ingsystemforprovidedthe12.Theobjectiveofthepost-processingforsegmentationstageistorefinetheincorrectregionafterapp1.yingrnA1ISOIEC2024-A1.1.rightsreserved7 Datamethod.Theobjectiveofthe
42、datapreparationstageistotansformtherawdatasothatthesegmentationa1.gorithmcanapp1.ied.Intheimageacquisitionphase,medica1.imagesareproducedfromdevices,suchasCT,MR1.PET/SPECT,US,OpUcahnedica1.imagedatatheyaredevicesshou1.dbe11raw,inasourceformatbyDICOM)formedica1.imageprocessing.Computedtomography(CT)i
43、samedica1.imagingtechniquethatusesX-raystogenerate2Ds1.iceimagesoftheisThese2DimagesareCTimagesuseinthebitsfi1.epixe1.Thepixe1.hasitsowneachaccordingtothedegreeoftransmittedradiationthatpassesthroughthebody.ACTtakes2Dimages1.icescoveringaspecificthenofanimagebody.ThetechniquetoCTimageismain1.ydepend
44、entonpixe1.spacingandnumberofpixe1.s,andpartia1.1.ydependentonthes1.icethicknessofthe2Dimages.Forscanningbetterbone.Forimages,thecaseofCTorbitaItheminimumshou1.dbeofCTscanningconditionsisdefinedinAnnexA.Magneticresonanceimaging(MRI)equipmentismedica1.e1.ectrica1.equipmentwhichisgenera1.1.yintendedin
45、Vivoanatomyandresonanceprocessesathebody.ismedica1.strongmagnetictoformpicturesfie1.dgradientsandradiowavestocreateimagesofinterna1.patientanatomy.7.3Preparationsteps7.3.1 Genera1.Sincethedatapreparationstageconsistsoftwosteps,imageacquisitionandimagereconstruction,theessentia1.considerationsforeachstepshou1.dbereectcd.7.3.2 ImageacquisitionTheimageacquisitionstepcanbedefinedastheactionofacquiringasetofimagedatafromahardwaresource.Inordertocreateagoodqua1.itymedica1.image-based3Dmode1.for3Dprintin
免费区 
