Lung nodules detection and classification
Paola Campadelli, Elena Casiraghi and Giorgio Valentini
In: ICIP 05, The IEEE International Conference on Image Processing, Genova, Italy(2005).
Image processing techniques and Computer Aided Diagnosis (CAD)
systems have proved to be effective for the improvement of
radiologists' diagnosis. In this paper a system which
automatically detect lung nodules from Postero Anterior Chest
Radiographs is presented. The system extract a set of candidate
regions by applying to the radiograph three different and
consecutive multi-scale schemes. The comparison of the result
obtained and the ones presented in the literature show the
efficacy of the multi-scale framework employed. Learning systems
using as input different sets of features have been experimented for
candidates classification, showing that Support Vector Machines
(SVMs) can be successfully applied for this task.