WSEAS Transactions on Information Science and Applications
Auto-detection of non-isolated pulmonary nodules in X-ray CT images
AIKED'09 Proceedings of the 8th WSEAS international conference on Artificial intelligence, knowledge engineering and data bases
WSEAS Transactions on Information Science and Applications
| Hi-index | 0.00 |
The purpose of this study is to apply a genetic-algorithm (GA) template-matching method to detect lung nodules in chest helical x-ray CT (computed tomography) images. We combined GA and template matching to search the positions of nodules and to calculate adaptation scales of individuals on GA, respectively. We used four simulated nodules created by Gaussian distribution, whose sizes were different each other, as reference patterns in the GA template matching. The GA selected an adequate reference image from four ones and searched adequate positions to template matching. We used cross-correlation as similarity of tmplate matching and as adaptation scales of individuals on GA. It was possible to detect 23 nodules from 45 ones that did not touch lung walls without consideration of their sizes. It was also possible to detect all nodules that touched lung walls by using conventional template matching along lung walls. The total detection rate was approximately 67%. The number of false positives per one slice was over 10. To improve the detection performance and to decrease the number of false positives, we are now working on considering operators and their parameters of GA.