?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.relation=http%3A%2F%2Fwww.eledia.org%2Fstudents-reports%2F382%2F&rft.title=An+Integration+Between+SVM+Classifiers+and+Multi-Resolution+Techniques+for+Early+Breast+Cancer+Detection&rft.creator=Rocca%2C+Paolo&rft.creator=Viani%2C+Federico&rft.creator=Donelli%2C+Massimo&rft.creator=Benedetti%2C+Manuel&rft.creator=Massa%2C+Andrea&rft.subject=TU+Technical+Reports+and+Publications&rft.description=Because+of+the+high+contrast+between+the+dielectric+properties+of+normal+and+malignant+breast+tissues+at+microwave+frequencies%2C+microwave+imaging+techniques+seem+to+be+very+attractive+diagnosis+methods+for+cancer+detection+%5B1%5D%5B2%5D.+In+such+a+framework%2C+inverse+scattering+methods+are+very+promising+tools%2C+but+their+practical+application+is+strongly+limited+by+the+need+of+3D+reconstructions%2C+high+spatial+resolutions%2C+and+fast+processing.+Recently%2C+to+reduce+the+high+computational+costs+and+to+fit+the+real-time+requirements%2C+inversion+methods+based+on+learning+by+example+techniques+have+been+proposed+%5B3%5D.+LBE+approaches+based+on+support+vector+machines+(SVMs)+%5B3%5D+and+neural+networks+(NNs)+%5B4%5D+have+been+satisfactorily+applied+in+various+and+complex+electromagnetic+problems.+When+dealing+with+breast+cancer+detection%2C+the+inversion+process+is+recast+as+a+classification+or+regression+problem+where+the+unknowns+are+retrieved+from+the+data+(i.e.%2C+the+electric+field+samples+collected+in+an+external+observation+domain)+by+approximating+the+unknown+relation+data-unknowns+through+an+off-line+data+fitting+procedure+(training+phase).+Once+the+training+procedure+(performed+once+and+off-line)+is+completed%2C+the+characteristics+of+the+malignant+breast+tissue+are+real-time+estimated+in+the+testing+phase.+In+such+a+work%2C+the+detection+problem+is+addressed+by+integrating+a+SVM-based+classifier+with+an+iterative+multi-zooming+procedure.+More+in+detail%2C+a+succession+of+approximations+of+a+probability+map+of+the+presence+of+pathology+is+determined.+At+each+step%2C+the+spatial+resolution+of+the+risk-map+is+improved+in+a+limited+set+of+regions+of+interest+(ROIs)+defined+at+the+previous+zooming+step+and+characterized+by+a+greater+value+of+the+occurrence+probability+of+a+malignant+tissue.+The+multi-step+procedure+is+stopped+when+a+stationary+condition+on+the+probability+and+on+the+number+of+ROIs+is+reached.+The+achievable+trade-off+between+computational+complexity+and+spatial+resolution+is+preliminary+assessed+by+discussing+a+selected+set+of+numerical+simulations+concerned+with+both+noiseless+as+well+as+corrupted+data.&rft.date=2011-01&rft.type=Technical+Report&rft.type=NonPeerReviewed&rft.format=application%2Fpdf&rft.language=en&rft.identifier=http%3A%2F%2Fwww.eledia.org%2Fstudents-reports%2F382%2F1%2FDISI-11-202.C163.pdf&rft.identifier=++Rocca%2C+Paolo+and+Viani%2C+Federico+and+Donelli%2C+Massimo+and+Benedetti%2C+Manuel+and+Massa%2C+Andrea++(2011)+An+Integration+Between+SVM+Classifiers+and+Multi-Resolution+Techniques+for+Early+Breast+Cancer+Detection.++%5BTechnical+Report%5D+++++