TY - GEN
T1 - A two-step approach for feature selection and classifier ensemble construction in computer-aided diagnosis
AU - Lee, Michael C.
AU - Boroczky, Lilla
AU - Sungur-Stasik, Kivilcim
AU - Cann, Aaron D.
AU - Borczuk, Alain C.
AU - Kawut, Steven M.
AU - Powell, Charles A.
PY - 2008
Y1 - 2008
N2 - Accurate classification methods are critical in computer-aided diagnosis and other clinical decision support systems. Previous research has studied methods for combining genetic algorithms for feature selection with ensemble classifier systems in an effort to increase classification accuracy. We propose a two-step approach that first uses genetic algorithms to reduce the number of features used to characterize the data, then applies the random subspace method on the remaining features to create a set of diverse but high performing classifiers. These classifiers are combined using ensemble learning techniques to yield afinal classification. We demonstrate this approach for computer-aided diagnosis of solitary pulmonary nodules from CT scans, in which the proposed method outperforms several previously described methods.
AB - Accurate classification methods are critical in computer-aided diagnosis and other clinical decision support systems. Previous research has studied methods for combining genetic algorithms for feature selection with ensemble classifier systems in an effort to increase classification accuracy. We propose a two-step approach that first uses genetic algorithms to reduce the number of features used to characterize the data, then applies the random subspace method on the remaining features to create a set of diverse but high performing classifiers. These classifiers are combined using ensemble learning techniques to yield afinal classification. We demonstrate this approach for computer-aided diagnosis of solitary pulmonary nodules from CT scans, in which the proposed method outperforms several previously described methods.
UR - http://www.scopus.com/inward/record.url?scp=51849162939&partnerID=8YFLogxK
U2 - 10.1109/CBMS.2008.68
DO - 10.1109/CBMS.2008.68
M3 - Conference contribution
AN - SCOPUS:51849162939
SN - 9780769531656
T3 - Proceedings - IEEE Symposium on Computer-Based Medical Systems
SP - 548
EP - 553
BT - Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008
T2 - 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008
Y2 - 17 June 2008 through 19 June 2008
ER -