Automatic Detection, Segmentation and Classification of Pulmonary Nodules System in Computed Tomography Images

The goal of project LNDetector is to automatically detect, segment and classify nodules in chest CT scans. The idea is to create a working prototype of a Computer-aided diagnosis (CAD) system for lung nodule diagnosis to be installed in a radiology department. The prototype includes three main modules for nodule detection, segmentation and diagnosis. Furthermore, an anonymised and annotated CT image database will be created with a large diversity of nodules with different sizes, positions, shapes and texture features. The joint collaborative research with a major Radiology Department creates an excellent cooperation opportunity between Engineering and Medicine.