TY - JOUR
T1 - Multiple RF classifier for the hippocampus segmentation
T2 - Method and validation on EADC-ADNI Harmonized Hippocampal Protocol
AU - Inglese, P.
AU - Amoroso, N.
AU - Boccardi, M.
AU - Bocchetta, M.
AU - Bruno, S.
AU - Chincarini, A.
AU - Errico, R.
AU - Frisoni, G. B.
AU - Maglietta, R.
AU - Redolfi, A.
AU - Sensi, F.
AU - Tangaro, S.
AU - Tateo, A.
AU - Bellotti, R.
PY - 2015/12/1
Y1 - 2015/12/1
N2 - 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.
AB - 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.
KW - Alzheimer's disease
KW - Hippocampus segmentation
KW - Random forest classifier
UR - http://www.scopus.com/inward/record.url?scp=84959521558&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84959521558&partnerID=8YFLogxK
U2 - 10.1016/j.ejmp.2015.08.003
DO - 10.1016/j.ejmp.2015.08.003
M3 - Article
C2 - 26481815
AN - SCOPUS:84959521558
VL - 31
SP - 1085
EP - 1091
JO - Physica Medica
JF - Physica Medica
SN - 1120-1797
IS - 8
ER -