Optimal image feature set for detecting lung nodules on chest X-ray images
The performance of a computer-aided diagnosis system depends on the feature set used in it. This paper shows the results of image feature selection experiments. We evaluated 210 features to look for the optimum feature set. For the purpose, a forward stepwise selection approach was employed. The area under the receiver operating characteristic (ROC) curve was adopted to evaluate the performance of each feature set. Analysis of the optimally selected feature set is given and the experiments using 247 chest x-ray images are also shown.
KeywordsComputer aided diagnosis lung cancer feature selection
Unable to display preview. Download preview PDF.
- 5.Y.Wu, M.L.Giger, K.Doi, C.J.Vyboorny, R.A.Schmidt, C.E.Metz,“Artificial Neural Networks in Mammography: Application to Decision Making in the Diagnosis of Breast Cancer,” Radiology, Vol..l87,pp.81–87, 1993.Google Scholar
- 8.M.A.Kupinski, M.L.Giger, “Feature selection and Classifiers for the Computerized Detection of Mass Lesions in Digital Mammography,” IEEE International Congress on Neural Networks, Houston, Texas, June, pp. 2460–2463, 1997.Google Scholar
- 10.Jun Wei, Yoshihiro Hagihara and Hidefumi Kobatake: Detection of Cancerous Tumors on Chest X-ray Images - Candidate Detection Filter and Its Application -, Proc. of ICIP, Paper No. 27AP4.2, 1999.Google Scholar
- 13.J. Wei, Y. Hagihara, H. Kobatake, “Detection of lung nodules on digital chest radiographs,” Med. Imag. Tech., Vol. 19, No. 6, pp. 468–476, 2001. (in Japanese)Google Scholar