Carlos Platero1, M Carmen Tobar2. 1. Health Science Technology Group, Technical University of Madrid, Ronda de Valencia 3, 28012 Madrid, Spain. Electronic address: carlos.platero@upm.es. 2. Health Science Technology Group, Technical University of Madrid, Ronda de Valencia 3, 28012 Madrid, Spain. Electronic address: m.carmen.tobar@upm.es.
Abstract
BACKGROUND: We provide and evaluate an open-source software solution for automatically measuring hippocampal volume and hippocampal surface roughness based on T1-weighted MRI, which allows for discriminating between patients with Alzheimer's disease (AD) or mild cognitive impairment (MCI) and elderly controls (NC) using only one scan. NEW METHOD: This solution is based on a fast multiple-atlas segmentation technique, which combines a patch-based labeling method with an atlas-warping using non-rigid registrations. RESULTS: The classifications are comparable to the best classifications in a large clinical dataset. For AD vs control, we obtain a high degree of accuracy, approximately 90%. For MCI vs control, we obtain accuracies ranging from 70% to 78%. The average time for the hippocampal segmentation from a T1-MRI is less than 17min. COMPARISON WITH EXISTING METHOD: In this study, we investigate a combination of our method with annotations using the Harmonized Hippocampal Protocol (HarP). We compare its capabilities with the FreeSurfer method and verify its impact on segmentation and diagnostic group separation capabilities. Our approach is developed and validated using 134 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database with annotations from HarP. Then, this method, tuned with the best parameters, is applied to 162 subjects from a private image database. CONCLUSIONS: Our approach with HarP annotations has a high level of accuracy for segmentation of the hippocampus and is robust to multi-site data. The bio-markers extracted from our proposed method have discriminative power based on a scalar feature, showing robustness in generalization and avoid overfitting. The computational time in our hippocampal segmentation algorithm has decreased considerably compared to other available analysis.
BACKGROUND: We provide and evaluate an open-source software solution for automatically measuring hippocampal volume and hippocampal surface roughness based on T1-weighted MRI, which allows for discriminating between patients with Alzheimer's disease (AD) or mild cognitive impairment (MCI) and elderly controls (NC) using only one scan. NEW METHOD: This solution is based on a fast multiple-atlas segmentation technique, which combines a patch-based labeling method with an atlas-warping using non-rigid registrations. RESULTS: The classifications are comparable to the best classifications in a large clinical dataset. For AD vs control, we obtain a high degree of accuracy, approximately 90%. For MCI vs control, we obtain accuracies ranging from 70% to 78%. The average time for the hippocampal segmentation from a T1-MRI is less than 17min. COMPARISON WITH EXISTING METHOD: In this study, we investigate a combination of our method with annotations using the Harmonized Hippocampal Protocol (HarP). We compare its capabilities with the FreeSurfer method and verify its impact on segmentation and diagnostic group separation capabilities. Our approach is developed and validated using 134 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database with annotations from HarP. Then, this method, tuned with the best parameters, is applied to 162 subjects from a private image database. CONCLUSIONS: Our approach with HarP annotations has a high level of accuracy for segmentation of the hippocampus and is robust to multi-site data. The bio-markers extracted from our proposed method have discriminative power based on a scalar feature, showing robustness in generalization and avoid overfitting. The computational time in our hippocampal segmentation algorithm has decreased considerably compared to other available analysis.
Authors: Leon Lenchik; Laura Heacock; Ashley A Weaver; Robert D Boutin; Tessa S Cook; Jason Itri; Christopher G Filippi; Rao P Gullapalli; James Lee; Marianna Zagurovskaya; Tara Retson; Kendra Godwin; Joey Nicholson; Ponnada A Narayana Journal: Acad Radiol Date: 2019-08-10 Impact factor: 3.173
Authors: Mike F Schmidt; Judd M Storrs; Kevin B Freeman; Clifford R Jack; Stephen T Turner; Michael E Griswold; Thomas H Mosley Journal: Hum Brain Mapp Date: 2018-02-21 Impact factor: 5.038
Authors: Long Xie; Laura E M Wisse; John Pluta; Robin de Flores; Virgine Piskin; Jose V Manjón; Hongzhi Wang; Sandhitsu R Das; Song-Lin Ding; David A Wolk; Paul A Yushkevich Journal: Hum Brain Mapp Date: 2019-04-29 Impact factor: 5.038
Authors: Long Xie; Russell T Shinohara; Ranjit Ittyerah; Hugo J Kuijf; John B Pluta; Kim Blom; Minke Kooistra; Yael D Reijmer; Huiberdina L Koek; Jaco J M Zwanenburg; Hongzhi Wang; Peter R Luijten; Mirjam I Geerlings; Sandhitsu R Das; Geert Jan Biessels; David A Wolk; Paul A Yushkevich; Laura E M Wisse Journal: J Alzheimers Dis Date: 2018 Impact factor: 4.472