Multiple RF classifier for the hippocampus segmentation: Method and validation on EADC-ADNI Harmonized Hippocampal Protocol.

The hippocampus has a key role in a number of neurodegenerative diseases, such as Alzheimer's Disease. Here we present a novel method for the automated segmentation of the hippocampus from structural magnetic resonance images (MRI), based on a combination of multiple classifiers. The method is validated on a cohort of 50 T1 MRI scans, comprehending healthy control, mild cognitive impairment, and Alzheimer's Disease subjects. The preliminary release of the EADC-ADNI Harmonized Protocol training labels is used as gold standard. The fully automated pipeline consists of a registration using an affine transformation, the extraction of a local bounding box, and the classification of each voxel in two classes (background and hippocampus). The classification is performed slice-by-slice along each of the three orthogonal directions of the 3D-MRI using a Random Forest (RF) classifier, followed by a fusion of the three full segmentations. Dice coefficients obtained by multiple RF (0.87 ± 0.03) are larger than those obtained by a single monolithic RF applied to the entire bounding box, and are comparable to state-of-the-art. A test on an external cohort of 50 T1 MRI scans shows that the presented method is robust and reliable. Additionally, a comparison of local changes in the morphology of the hippocampi between the three subject groups is performed. Our work showed that a multiple classification approach can be implemented for the segmentation for the measurement of volume and shape changes of the hippocampus with diagnostic purposes.

Sustainability evaluation of Sicily's lemon and orange production: an energy, economic and environmental analysis.

The island of Sicily has a long standing tradition in citrus growing. We evaluated the sustainability of orange and lemon orchards, under organic and conventional farming, using an energy, environmental and economic analysis of the whole production cycle by using a life cycle assessment approach. These orchard systems differ only in terms of a few of the inputs used and the duration of the various agricultural operations. The quantity of energy consumption in the production cycle was calculated by multiplying the quantity of inputs used by the energy conversion factors drawn from the literature. The production costs were calculated considering all internal costs, including equipment, materials, wages, and costs of working capital. The performance of the two systems (organic and conventional), was compared over a period of fifty years. The results, based on unit surface area (ha) production, prove the stronger sustainability of the organic over the conventional system, both in terms of energy consumption and environmental impact, especially for lemons. The sustainability of organic systems is mainly due to the use of environmentally friendly crop inputs (fertilizers, not use of synthetic products, etc.). In terms of production costs, the conventional management systems were more expensive, and both systems were heavily influenced by wages. In terms of kg of final product, the organic production system showed better environmental and energy performances.