hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.2498/cit.2000.02.06

Computer Aided Diagnosis of Clustered Microcalcifications Using Artificial Neural Nets

Peter Winkler
Ewald Graif
Csaba Szepesvári
Michael Becker
Heinz Mayer
Ferdinand Schmidt
Erich Sorantin

Puni tekst: engleski, pdf (818 KB) str. 151-160 preuzimanja: 357* citiraj
APA 6th Edition
Winkler, P., Graif, E., Szepesvári, C., Becker, M., Mayer, H., Schmidt, F. i Sorantin, E. (2000). Computer Aided Diagnosis of Clustered Microcalcifications Using Artificial Neural Nets. Journal of computing and information technology, 8 (2), 151-160. https://doi.org/10.2498/cit.2000.02.06
MLA 8th Edition
Winkler, Peter, et al. "Computer Aided Diagnosis of Clustered Microcalcifications Using Artificial Neural Nets." Journal of computing and information technology, vol. 8, br. 2, 2000, str. 151-160. https://doi.org/10.2498/cit.2000.02.06. Citirano 21.02.2020.
Chicago 17th Edition
Winkler, Peter, Ewald Graif, Csaba Szepesvári, Michael Becker, Heinz Mayer, Ferdinand Schmidt i Erich Sorantin. "Computer Aided Diagnosis of Clustered Microcalcifications Using Artificial Neural Nets." Journal of computing and information technology 8, br. 2 (2000): 151-160. https://doi.org/10.2498/cit.2000.02.06
Harvard
Winkler, P., et al. (2000). 'Computer Aided Diagnosis of Clustered Microcalcifications Using Artificial Neural Nets', Journal of computing and information technology, 8(2), str. 151-160. https://doi.org/10.2498/cit.2000.02.06
Vancouver
Winkler P, Graif E, Szepesvári C, Becker M, Mayer H, Schmidt F i sur. Computer Aided Diagnosis of Clustered Microcalcifications Using Artificial Neural Nets. Journal of computing and information technology [Internet]. 2000 [pristupljeno 21.02.2020.];8(2):151-160. https://doi.org/10.2498/cit.2000.02.06
IEEE
P. Winkler, et al., "Computer Aided Diagnosis of Clustered Microcalcifications Using Artificial Neural Nets", Journal of computing and information technology, vol.8, br. 2, str. 151-160, 2000. [Online]. https://doi.org/10.2498/cit.2000.02.06

Sažetak
Objective: Development of a fully automated computer application for detection and classification of clustered microcalcifications using neural nets. Material and Methods: Mammographic films with clustered microcalcifications of known histology were digitized. All clusters were rated by two radiologists on a 3 point scale: benign, indeterminate and malignant. Automated detected clustered microcalcifications were clustered. Features derived from those clusters were used as input to 2 artificial neural nets: one was trained to identify the indeterminate clusters, whereas the second ANN classified the remaining clusters in benign or malignant ones. Performance evaluation followed the patient-based receiver operator characteristic analysis. Results: For identification of patients with indeterminate clusters a an Az-value of 0.8741 could be achieved. For the remaining patients their clusters could be classified as benign or malignant at an Az-value of 0.8749, a sensitivity of 0.977 and specificity of 0.471. Conclusions: A fully automated computer system for detection and classification of clustered microcalcifications was developed. The system is able to identify patients with indeterminate clusters, where additional investigations are recommended, and produces a reliable estimation of the biologic dignity for the remaining ones.

Hrčak ID: 44841

URI
https://hrcak.srce.hr/44841

Posjeta: 487 *