ࡱ> *,)bjbjUU >??HH   Y[[[[[[r`[[pYYjpE0tttd[[tH Q:Abstract The amount of fat on the surroundings of the heart is correlated to health risk factors such as carotid stiffness, coronary artery calcification, atrial fibrillation, atherosclerosis and other health conditions. Furthermore, cardiac fat deposits vary unrelated to the overall fat of the patient which, therefore, reinforces the idea of a direct quantitative analysis as being essential. However, manual quantification has not been widely employed in clinical practice due to the required human workload. Clinical decision support systems are computer programs capable of evaluating data and providing a corresponding diagnosis or information to complement the physicians analyses. The objective of this work is to propose a method capable of fully automatically segmenting two types of cardiac adipose tissues that stand apart from each other by the pericardium. The source for segmentation are CT images which, in turn, were obtained by the standard acquisition protocol used for coronary calcium scoring. Much effort was devoted to promote minimal user intervention and easiness of reproducibility. The proposed segmentation methodology consists of an intersubject registration that roughly standardize images of distinct patients, an extraction of features of the registered images and, finally, an appliance of classification algorithms. The classification algorithm predicts if an incoming pixel corresponds to a certain type of cardiac fat based on the extracted features. Furthermore, we extensively evaluate the performance of several algorithms on this task and discuss which ones provided better predictive models. Experimental results regarding both epicardial and mediastinal fats have shown that the mean accuracy for the proposed method is 98.4% with a mean true positive rate of 96.2%. In average, the Dice similarity index has been equal to 96.8%. Keywords: epicardial, mediastinal, segmentation, automatic, classification, Random Forest, cardiac, fat, adipose tissue, registration, intersubject  w9ARS hMB^Jh ohMB^JhMB hEhMB h ohMB   W RSgd7gd6gd7<P1h:pt. A!"#$% Dpj  666666666666666666666666666666666666666666 6666666666 666666666666 6666666666666666666666666666666666666666666666666666666666666666662 0@P`p2( 0@P`p 0@P`p 0@P`p 0@P`p 0@P`p 0@P`p8XVx OJPJQJ_HmHnHsHtH``` 7Normal$dhx*$`a$CJ^J_HaJmH sH tH b`b 70 Heading 1$$@&!B*CJ OJPJQJ^JaJ ph.tDA D 0Default Paragraph FontRiR 0 Table Normal4 l4a (k ( 0No List b/b 'Heading 1 Char.5CJ KH OJPJQJ\^JaJ mH sH tH d/d 70Heading 1 Char1-B*CJ OJPJQJ^JaJ mH ph.tsH tH r Ar 70 TOC Heading$h@& `a$&5;B*CJOJQJ\^JaJphPK![Content_Types].xmlj0Eжr(΢Iw},-j4 wP-t#bΙ{UTU^hd}㨫)*1P' ^W0)T9<l#$yi};~@(Hu* Dנz/0ǰ $ X3aZ,D0j~3߶b~i>3\`?/[G\!-Rk.sԻ..a濭?PK!֧6 _rels/.relsj0 }Q%v/C/}(h"O = C?hv=Ʌ%[xp{۵_Pѣ<1H0ORBdJE4b$q_6LR7`0̞O,En7Lib/SeеPK!kytheme/theme/themeManager.xml M @}w7c(EbˮCAǠҟ7՛K Y, e.|,H,lxɴIsQ}#Ր ֵ+!,^$j=GW)E+& 8PK!Ptheme/theme/theme1.xmlYOo6w toc'vuر-MniP@I}úama[إ4:lЯGRX^6؊>$ !)O^rC$y@/yH*񄴽)޵߻UDb`}"qۋJחX^)I`nEp)liV[]1M<OP6r=zgbIguSebORD۫qu gZo~ٺlAplxpT0+[}`jzAV2Fi@qv֬5\|ʜ̭NleXdsjcs7f W+Ն7`g ȘJj|h(KD- dXiJ؇(x$( :;˹! I_TS 1?E??ZBΪmU/?~xY'y5g&΋/ɋ>GMGeD3Vq%'#q$8K)fw9:ĵ x}rxwr:\TZaG*y8IjbRc|XŻǿI u3KGnD1NIBs RuK>V.EL+M2#'fi ~V vl{u8zH *:(W☕ ~JTe\O*tHGHY}KNP*ݾ˦TѼ9/#A7qZ$*c?qUnwN%Oi4 =3ڗP 1Pm \\9Mؓ2aD];Yt\[x]}Wr|]g- eW )6-rCSj id DЇAΜIqbJ#x꺃 6k#ASh&ʌt(Q%p%m&]caSl=X\P1Mh9MVdDAaVB[݈fJíP|8 քAV^f Hn- "d>znNJ ة>b&2vKyϼD:,AGm\nziÙ.uχYC6OMf3or$5NHT[XF64T,ќM0E)`#5XY`פ;%1U٥m;R>QD DcpU'&LE/pm%]8firS4d 7y\`JnίI R3U~7+׸#m qBiDi*L69mY&iHE=(K&N!V.KeLDĕ{D vEꦚdeNƟe(MN9ߜR6&3(a/DUz<{ˊYȳV)9Z[4^n5!J?Q3eBoCM m<.vpIYfZY_p[=al-Y}Nc͙ŋ4vfavl'SA8|*u{-ߟ0%M07%<ҍPK! ѐ'theme/theme/_rels/themeManager.xml.relsM 0wooӺ&݈Э5 6?$Q ,.aic21h:qm@RN;d`o7gK(M&$R(.1r'JЊT8V"AȻHu}|$b{P8g/]QAsم(#L[PK-![Content_Types].xmlPK-!֧6 +_rels/.relsPK-!kytheme/theme/themeManager.xmlPK-!Ptheme/theme/theme1.xmlPK-! ѐ' theme/theme/_rels/themeManager.xml.relsPK]  _GoBack: rQ oE-%1"'>MB9#QSLg6M#7PFXt@@@Unknown G*Ax Times New Roman5Symbol3" Arial7.@CalibriO=  jMS Mincho l r   C.,{ @Calibri LightW=   jMS Gothic l r SVbN7@Cambriag"Adobe Fan Heiti Std BMS MinchoACambria Math"(34'(34'<!0$P7! xxABSTRACTrick OliveiraHelioOh+'0  @ L Xdlt| ABSTRACTrick OliveiraNormal_WordconvHelio2Microsoft Office Outlook@@p@p<՜.+,0 hp|    ABSTRACT Title  "#$%&'(+Root Entry F`p-1Table tWordDocumentHSummaryInformation(DocumentSummaryInformation8!CompObjy  F'Microsoft Office Word 97-2003 Document MSWordDocWord.Document.89q  F#Documento do Microsoft Office Word MSWordDocWord.Document.89q