Breast Density Classification Using Multiple Feature Selection

AbstractMammography as an x-ray method usually gives good results for lower density breasts while higher breast tissue densities significantly reduce the overall detection sensitivity and can lead to false negative results. In automatic detection algorithms knowledge about breast density can be useful for setting an appropriate decision threshold in order to produce more accurate detection. Because the overall intensity of mammograms is not directly correlated with the breast density we have decided to observe breast density as a texture classification problem. In this paper we propose breast density classification using feature selection process for different classifiers based on grayscale features of first and second order. In feature selection process different selection methods were used and obtained results show the improvement on overall classification by choosing the appropriate method and classifier. The classification accuracy has been tested on the mini-MIAS database and KBD-FER digital mammography database with different number of categories for each database. Obtained accuracy stretches between 97.2 % and 76.4 % for different number of categories.Mamografija je rendgenska metoda koja daje dobre rezultate pri slikanju dojki koje imaju manju gustoću, dok joj osjetljivost značajno opada pri snimanju dojki veće gustoće i time može doći do lažno pozitivnih rezultata. Poznavanje gustoće dojke može biti korisno kod algoritama za automatsku detekciju zbog mogućnosti određivanja praga odluke na osnovi tog znanja. S obzirom na to da ukupni intenzitet pojedinog mamograma nije izravno povezan s gustoćom, odlučili smo se promatrati gustoću kao problem klasifikacije teksture. U ovom radu predlažemo klasifikaciju dojki prema gustoći izborom izdvojenih znaćajki intenziteta prvog i drugog reda za različite klasifikatore. Za odredivanje prikladnih značajki koristili smo razlicite metode i tako dobivene značajke pokazale su bolju točnost klasifikacije za odabrane klasifikatore. Točnost klasifikacije testirali smo na bazi mamografskih slika mini-MIAS i bazi digitalnih mamografskih slika KBD-FER s različitim brojem kategorija u koje su slike bile podijeljene. Postignuta točnost klasifikacije proteže se između 97,2 % i 76,4 % za različit broj kategorija u koje su mamogrami podijeljeni.Key words: Breast DensityFeature SelectionHaralick FeaturesSoh FeaturesClassificationKljučne riječi: Gustoća dojkeizbor značajkiHaralickove značajkeSohove značajkeklasifikacija Additional informationNotes on contributorsMario MuštraMario Muštra received the B.Sc. degree in electrical engineering from the University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Croatia in 2007. Since 2007 he is with the University of Zagreb, FER, Department of Wireless Communications and Video Communication Laboratory where he is a Research Assistant. His current research interests are image processing techniques in medical imaging and development of automatic algorithms for detection of tissue types in mammograms.Mislav GrgićMislav Grgić received his BSc, MSc, and PhD in electrical engineering from University of Zagreb, Faculty of Electrical Engineering and Computing (FER), Zagreb, Croatia, in 1997,1998, and 2000, respectively. He is currently a full professor in the Department of Wireless Communications at FER. His research interests include multimedia communications and image processing. He has had more than 120 scientific papers published in international journals and conference proceedings.Krešimir DelačKrešimir Delać received the PhD. degree in electrical engineering from the University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Croatia in 2007. He is with the Video Communication Laboratory where he is a Collaborator Researcher. His current research interests are image processing techniques in face recognition and medical imaging, pattern classification and recognition and data mining.