The affinity propagation algorithm is applied to a problem of breast cancer subtyping using traditional biologic markers. The algorithm provides a procedure to determine the number of profiles to be considered. A well know breast cancer case series was used to compare the results of the affinity propagation with the results obtained with standard algorithms and indexes for the optimal choice of the number of clusters. Results from affinity propagation are consistent with the results already obtained having the advantage of providing an indication about the number of clusters
Cancer profiles by affinity propagation / F. Ambrogi, E. Raimondi, D. Soria, P. Boracchi, E. Biganzoli - In: 7. International conference on machine learning and applications (ICMLA 2008) : Proceedings / [a cura di] F. Arif Wani, C. Xue-wen, D. Casasent, L. Kurgan, T. Hu, K. Hafeez. - Los Alamitos, CA : IEEE computer society CPS, 2008. - ISBN 978-0-7695-3495-4. - pp. 650-655 (( Intervento presentato al 7. convegno International conference on machine learning and applications (ICMLA) tenutosi a San Diego, CA nel 2008.
Cancer profiles by affinity propagation
F. AmbrogiPrimo
;P. BoracchiPenultimo
;E. BiganzoliUltimo
2008
Abstract
The affinity propagation algorithm is applied to a problem of breast cancer subtyping using traditional biologic markers. The algorithm provides a procedure to determine the number of profiles to be considered. A well know breast cancer case series was used to compare the results of the affinity propagation with the results obtained with standard algorithms and indexes for the optimal choice of the number of clusters. Results from affinity propagation are consistent with the results already obtained having the advantage of providing an indication about the number of clusters
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
