Long Xie1,2, Russell T Shinohara3, Ranjit Ittyerah1, Hugo J Kuijf4, John B Pluta1,2, Kim Blom5, Minke Kooistra5,6, Yael D Reijmer6, Huiberdina L Koek7, Jaco J M Zwanenburg8, Hongzhi Wang9, Peter R Luijten8, Mirjam I Geerlings5, Sandhitsu R Das1,2, Geert Jan Biessels6, David A Wolk2, Paul A Yushkevich1, Laura E M Wisse1,2. 1. Department of Radiology, Penn Image Computing and Science Laboratory (PICSL), University of Pennsylvania, Philadelphia, PA, USA. 2. Department of Neurology, Penn Memory Center, University of Pennsylvania, Philadelphia, PA, USA. 3. Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, PA, USA. 4. Image Sciences Institute, UMC Utrecht, Utrecht, The Netherlands. 5. Julius Center for Health Sciences and Primary Care, UMC Utrecht, Utrecht, The Netherlands. 6. Department of Neurology, Brain Center Rudolf Magnus, UMC Utrecht, Utrecht, The Netherlands. 7. Department of Geriatrics, UMC Utrecht, Utrecht, The Netherlands. 8. Department of Radiology, UMC Utrecht, Utrecht, The Netherlands. 9. Almaden Research Center, IBM Research, Almaden, CA, USA.
Abstract
BACKGROUND: Multi-atlas segmentation, a popular technique implemented in the Automated Segmentation of Hippocampal Subfields (ASHS) software, utilizes multiple expert-labelled images ("atlases") to delineate medial temporal lobe substructures. This multi-atlas method is increasingly being employed in early Alzheimer's disease (AD) research, it is therefore becoming important to know how the construction of the atlas set in terms of proportions of controls and patients with mild cognitive impairment (MCI) and/or AD affects segmentation accuracy. OBJECTIVE: To evaluate whether the proportion of controls in the training sets affects the segmentation accuracy of both controls and patients with MCI and/or early AD at 3T and 7T. METHODS: We performed cross-validation experiments varying the proportion of control subjects in the training set, ranging from a patient-only to a control-only set. Segmentation accuracy of the test set was evaluated by the Dice similarity coeffiecient (DSC). A two-stage statistical analysis was applied to determine whether atlas composition is linked to segmentation accuracy in control subjects and patients, for 3T and 7T. RESULTS: The different atlas compositions did not significantly affect segmentation accuracy at 3T and for patients at 7T. For controls at 7T, including more control subjects in the training set significantly improves the segmentation accuracy, but only marginally, with the maximum of 0.0003 DSC improvement per percent increment of control subject in the training set. CONCLUSION: ASHS is robust in this study, and the results indicate that future studies investigating hippocampal subfields in early AD populations can be flexible in the selection of their atlas compositions.
BACKGROUND:Multi-atlas segmentation, a popular technique implemented in the Automated Segmentation of Hippocampal Subfields (ASHS) software, utilizes multiple expert-labelled images ("atlases") to delineate medial temporal lobe substructures. This multi-atlas method is increasingly being employed in early Alzheimer's disease (AD) research, it is therefore becoming important to know how the construction of the atlas set in terms of proportions of controls and patients with mild cognitive impairment (MCI) and/or AD affects segmentation accuracy. OBJECTIVE: To evaluate whether the proportion of controls in the training sets affects the segmentation accuracy of both controls and patients with MCI and/or early AD at 3T and 7T. METHODS: We performed cross-validation experiments varying the proportion of control subjects in the training set, ranging from a patient-only to a control-only set. Segmentation accuracy of the test set was evaluated by the Dice similarity coeffiecient (DSC). A two-stage statistical analysis was applied to determine whether atlas composition is linked to segmentation accuracy in control subjects and patients, for 3T and 7T. RESULTS: The different atlas compositions did not significantly affect segmentation accuracy at 3T and for patients at 7T. For controls at 7T, including more control subjects in the training set significantly improves the segmentation accuracy, but only marginally, with the maximum of 0.0003 DSC improvement per percent increment of control subject in the training set. CONCLUSION: ASHS is robust in this study, and the results indicate that future studies investigating hippocampal subfields in early AD populations can be flexible in the selection of their atlas compositions.
Authors: R J Killiany; B T Hyman; T Gomez-Isla; M B Moss; R Kikinis; F Jolesz; R Tanzi; K Jones; M S Albert Journal: Neurology Date: 2002-04-23 Impact factor: 9.910
Authors: Pierrick Coupé; José V Manjón; Vladimir Fonov; Jens Pruessner; Montserrat Robles; D Louis Collins Journal: Neuroimage Date: 2010-09-17 Impact factor: 6.556
Authors: Josephine Barnes; Jonathan W Bartlett; Laura A van de Pol; Clement T Loy; Rachael I Scahill; Chris Frost; Paul Thompson; Nick C Fox Journal: Neurobiol Aging Date: 2008-03-17 Impact factor: 4.673
Authors: Hongzhi Wang; Sandhitsu R Das; Jung Wook Suh; Murat Altinay; John Pluta; Caryne Craige; Brian Avants; Paul A Yushkevich Journal: Neuroimage Date: 2011-01-13 Impact factor: 6.556
Authors: Kelvin K Leung; Josephine Barnes; Gerard R Ridgway; Jonathan W Bartlett; Matthew J Clarkson; Kate Macdonald; Norbert Schuff; Nick C Fox; Sebastien Ourselin Journal: Neuroimage Date: 2010-03-15 Impact factor: 6.556
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: Margareta A Clarke; Dhairya A Lakhani; Sijin Wen; Si Gao; Seth A Smith; Richard Dortch; Junzhong Xu; Francesca Bagnato Journal: Mult Scler Relat Disord Date: 2021-01-05 Impact factor: 4.339