A methodology for training and validating a CAD system and potential pitfalls

作者: M Dundar , G Fung , L Bogoni , M Macari , A Megibow

DOI: 10.1016/J.ICS.2003.10.002

关键词: Test setCad systemData miningClassifier (UML)Training setComputer science

摘要: Abstract In this study we first discuss potential pitfalls involved in training a classifier for CAD system and then propose methodology successful validation of system. Our approach tries to achieve balance between performing well on the data while generalizing new cases. We performed several experiments justify each step proposed methodology. As our experimental results suggest, one can safely consider leave-one-patient-out tuning selecting relevant features as performance measure. However, final should always be evaluated an independent test set.

参考文章(6)
George H John, Ron Kohavi, Karl Pfleger, None, Irrelevant Features and the Subset Selection Problem Machine Learning Proceedings 1994. pp. 121- 129 ,(1994) , 10.1016/B978-1-55860-335-6.50023-4
Anna K. Jerebko, James D. Malley, Marek Franaszek, Ronald M. Summers, Multinetwork classification scheme for detection of colonic polyps in CT colonography data sets Medical Imaging 2002: Physiology and Function from Multidimensional Images. ,vol. 4683, pp. 207- 212 ,(2002) , 10.1117/12.463584
S.B. Gokturk, C. Tomasi, B. Acar, C.F. Beaulieu, D.S. Paik, R.B.Jr. Jeffrey, J. Yee, S. Napel, A statistical 3-D pattern processing method for computer-aided detection of polyps in CT colonography IEEE Transactions on Medical Imaging. ,vol. 20, pp. 1251- 1260 ,(2001) , 10.1109/42.974920
Sebastian Mika, Gunnar Rätsch, Jason Weston, Bernhard Schölkopf, KR Müller, Fisher discriminant analysis with kernels ieee workshop on neural networks for signal processing. pp. 41- 48 ,(1999) , 10.1109/NNSP.1999.788121
Anna K. Jerebko, James D. Malley, Marek Franaszek, Ronald M. Summers, Multiple Neural Network Classification Scheme for Detection of Colonic Polyps in CT Colonography Data Sets Academic Radiology. ,vol. 10, pp. 154- 160 ,(2003) , 10.1016/S1076-6332(03)80039-9