Lung nodule detection in low-dose and high-resolution CT scans

Abstract

We are developing a computer-aided detection (CAD) system for the identification of small pulmonary nodules in screening CT scans. The main modules of our system, i.e. a dot-enhancement filter for nodule candidate selection and a neural classifier for false positive finding reduction, are described. The preliminary results obtained on the so-far collected database of lung CT are discussed.

4 pages, 1 figure; Proceedings of the Frontier Science 2005, 4th International Conference on Frontier Science, 12-17 September, 2005, Milano, Italy