A fully automated and three-dimensional (3D) segmentation method for the identification of the pulmonary parenchyma in thorax X-ray computed tomography (CT) datasets is proposed. It is meant to be used as preprocessing step in the computer-assisted detection (CAD) system for malignant lung nodule detection that is being developed by the Medical Applications in a Grid Infrastructure Connection (MAGIC-5) Project. In this new approach the segmentation of the external airways (trachea and bronchi), is obtained by 3D region growing with wavefront simulation and suitable stop conditions, thus allowing an accurate handling of the hilar region, notoriously difficult to be segmented. Particular attention was also devoted to checking and solving the problem of the apparent ‘fusion’ between the lungs, caused by partialvolume effects, while 3D morphology operations ensure the accurate inclusion of all the nodules (internal, pleural, and vascular) in the segmented volume. The newalgorithm was initially developed and tested on a dataset of 130 CT scans fromthe Italung-CT trial, andwas then applied to the ANODE09-competition images (55 scans) and to the LIDC database (84 scans), giving very satisfactory results. In particular, the lung contour was adequately located in 96% of the CT scans, with incorrect segmentation of the external airways in the remaining cases. Segmentation metrics were calculated that quantitatively express the consistency between automatic and manual segmentations: themean overlap degree of the segmentationmasks is 0.96±0.02, and the mean and the maximum distance between the mask borders (averaged on the whole dataset) are 0.74±0.05 and 4.5±1.5, respectively, which confirms that the automatic segmentations quite correctly reproduce the borders traced by the radiologist. Moreover, no tissue containing internal and pleural nodules was removed in the segmentation process, so that this method proved to be fit for the use in the framework of a CAD system. Finally, in the comparison with a two-dimensional segmentation procedure, inter-slice smoothness was calculated, showing that the masks created by the 3D algorithm are significantly smoother than those calculated by the 2D-only procedure.

Objectives We detail a procedure for generating a set of templates for the hippocampal region in Magnetic Resonance images, representative of the clinical conditions of the population under investigation. Methods The first step is robust standardization of the intensity scale of brain MR images, belonging to patients with different degrees of neuropathology (Alzheimer’s Disease). So similar tissues have similar intensities, even across images coming from different sources. After the automatic extraction of the hippocampal region from a large dataset of images, we address template generation, choosing by clusterization methods a small number of the extracted regions. Results We assess that template generation is largely independent on the clusterization method and on the number and the clinical condition of the patients. The templates are chosen as the most representative images in a population. The estimation of the ‘minimum’ number of templates for the hippocampal region can be proposed, using a metric based on the geometrical position of the extracted regions. Conclusions This study describes a simple and easily reproducible procedure to generate templates for the hippocampal region. It can be generalized and applied to other brain regions, which may be relevant for neuroimaging studies.

We detail a procedure for generating a set of templates for the hippocampal region in magnetic resonance (MR) images, representative of the clinical conditions of the population under investigation. METHODS: The first step is robust standardization of the intensity scale of brain MR images, belonging to patients with different degrees of neuropathology (Alzheimer's disease). So similar tissues have similar intensities, even across images coming from different sources. After the automatic extraction of the hippocampal region from a large dataset of images, we address template generation, choosing by clusterization methods a small number of the extracted regions. RESULTS: We assess that template generation is largely independent on the clusterization method and on the number and the clinical condition of the patients. The templates are chosen as the most representative images in a population. The estimation of the "minimum" number of templates for the hippocampal region can be proposed, using a metric based on the geometrical position of the extracted regions. CONCLUSIONS: This study describes a simple and easily reproducible procedure to generate templates for the hippocampal region. It can be generalized and applied to other brain regions, which may be relevant for neuroimaging studies.