Pregled bibliografske jedinice broj: 519588
Shape Analysis and Classification of Masses in Mammographic Images using Neural Networks
Shape Analysis and Classification of Masses in Mammographic Images using Neural Networks // PROCEEDINGS IWSSIP 2011 / Zovko-Cihlar, Branka ; Behlilović, Narcis ; Hadžialić, Mesud (ur.).
Sarajevo: Faculty of Electrical Engineering, University of Sarajevo, 2011. str. 247-251 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 519588 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Shape Analysis and Classification of Masses in Mammographic Images using Neural Networks
Autori
Tralić, Dijana ; Božek, Jelena ; Grgić, Sonja
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
PROCEEDINGS IWSSIP 2011
/ Zovko-Cihlar, Branka ; Behlilović, Narcis ; Hadžialić, Mesud - Sarajevo : Faculty of Electrical Engineering, University of Sarajevo, 2011, 247-251
ISBN
978-9958-9966-1-0
Skup
18th International Conference on Systems, Signals and Image Processing, IWSSIP 2011
Mjesto i datum
Sarajevo, Bosna i Hercegovina, 16.06.2011. - 18.06.2011
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
mammographic image; shape analysis; shape factors; classification; neural network
Sažetak
Shape analysis of masses in mammographic images includes representation of mass contour and shape factors which are important features for distinguishing between benign and malignant masses. Three shape factors, namely compactness, moments and Fourier descriptors were calculated and used for the classification. Classification was performed using two types of neural networks: single layer and multilayer perceptron. Area under the ROC curve of Az = 0.9528 was achieved using perceptron with 1000 epochs and using all shape factors. Multilayer perceptron with 1000 epochs and all shape factors achieved better classification results and area under the ROC curve of Az = 0.9988.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo
POVEZANOST RADA
Projekti:
036-0361630-1635 - Upravljanje kvalitetom slike u radiodifuziji digitalnog videosignala (Grgić, Sonja, MZO ) ( CroRIS)
036-0982560-1643 - Inteligentno određivanje značajki slike u sustavima za otkrivanje znanja (Grgić, Mislav, MZO ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
