Algorithms for automatic detection of lung nodules in CT scans

The purpose of the work here presented consists in the evaluation of the performance of CAD (Computer Aided Detection) systems for automated lung nodule identification on multislice CT examinations based on different analysis approaches and on their combination. Three different CADe systems, the ^CAMCAD (Channeler Ant Model), the ^RGVPCAD (Region Growing Volume Plateau) and the ^VBNACAD (Voxel Based Neural Approach) were tested on public research datasets and evaluated in terms of FROC (Free-response Receiver Operating Characteristics) curves both individually and combined.