A Computer-Aided Detection system for lung nodules in CT images

摘要

Lung cancer is the leading cause of cancer-related mortality in developed countries. To support radiologists in the identification of early-stage lung cancers, we propose a Computer-Aided Detection (CAD) system, composed by two different procedures: ~(VBNA)CAD_1 devoted to the identification of small nodules embedded in the lung parenchyma (internal nodules) and ~(VBNA)CAD_(JP) devoted the identification of nodules originating on the pleura surface (juxta-pleural nodules). The CAD system has been developed and tested on a dataset of low-dose and thin-slice CT scans collected in the framework of the first Italian randomized and controlled screening trial (ITALUNG-CT). This work has been carried out in the framework of MAGIC-5 (Medical Application on a Grid Infrastructure Connection), an Italian collaboration funded by Istituto Nazionale di Fisica Nucleare (INFN) and Ministero dell'Lniversita e della Ricerca (MIUR), which aims at developing models and algorithms for a distributed analysis of biomedical images, by making use of the GRID services.