An automated system for lung nodule detection in low-dose computed tomography - Physics Medical PhysicsReport as inadecuate




An automated system for lung nodule detection in low-dose computed tomography - Physics Medical Physics - Download this document for free, or read online. Document in PDF available to download.

Abstract: A computer-aided detection CAD system for the identification of pulmonarynodules in low-dose multi-detector helical Computed Tomography CT images wasdeveloped in the framework of the MAGIC-5 Italian project. One of the maingoals of this project is to build a distributed database of lung CT scans inorder to enable automated image analysis through a data and cpu GRIDinfrastructure. The basic modules of our lung-CAD system, a dot-enhancementfilter for nodule candidate selection and a neural classifier forfalse-positive finding reduction, are described. The system was designed andtested for both internal and sub-pleural nodules. The results obtained on thecollected database of low-dose thin-slice CT scans are shown in terms of freeresponse receiver operating characteristic FROC curves and discussed.



Author: I. Gori, M.E. Fantacci, A. Preite Martinez, A. Retico

Source: https://arxiv.org/







Related documents