Generating ROC curves for artificial neural networks

Receiver operating characteristic (ROC) analysis is an established method of measuring diagnostic performance in medical imaging studies. Traditionally, artificial neural networks (ANN's) have been applied as a classifier to find one "best" detection rate. Recently researchers have begun to report ROC curve results for ANN classifiers. The current standard method of generating ROC curves for an ANN is to vary the output node threshold for classification. Here, the authors propose a different technique for generating ROC curves for a two class ANN classifier. They show that this new technique generates better ROC curves in the sense of having greater area under the ROC curve (AUC), and in the sense of being composed of a better distribution of operating points.

[1]  C E Metz,et al.  Some practical issues of experimental design and data analysis in radiological ROC studies. , 1989, Investigative radiology.

[2]  Kunio Doi,et al.  Neural network approach for differential diagnosis of interstitial lung diseases , 1990, Medical Imaging: Image Processing.

[3]  G. W. Gross,et al.  Neural networks in radiologic diagnosis. II. Interpretation of neonatal chest radiographs. , 1990, Investigative radiology.

[4]  C. Metz.  ROC Methodology in Radiologic Imaging , 1986, Investigative radiology.

[5]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[6]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[7]  Kevin Knight,et al.  Connectionist ideas and algorithms , 1990, CACM.

[8]  J. Swets.  ROC analysis applied to the evaluation of medical imaging techniques. , 1979, Investigative radiology.

[9]  J. Hanley,et al.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases. , 1983, Radiology.

[10]  Carey E. Priebe,et al.  Comparative evaluation of pattern recognition techniques for detection of microcalcifications , 1993, Electronic Imaging.

[11]  J M Boone,et al.  Neural networks in radiology: an introduction and evaluation in a signal detection task. , 1990, Medical physics.

[12]  K Doi,et al.  Computerized detection of clustered microcalcifications in digital mammograms: applications of artificial neural networks. , 1992, Medical physics.

[13]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[14]  I. Bankman,et al.  Feature-based detection of the K-complex wave in the human electroencephalogram using neural networks , 1992, IEEE Transactions on Biomedical Engineering.

[15]  W. Kegelmeyer,et al.  Dense feature maps for detection of calcifications , 1994 .