Automated hippocampal segmentation in 3D MRI using random undersampling with boosting algorithm
Authors:
- The Alzheimers Disease Neuroimaging InitiativeTIThe Alzheimers Disease Neuroimaging Initiative
- Rosalia MagliettaRMRosalia Maglietta
- Nicola AmorosoNicola Amoroso
- Marina BoccardiMBMarina Boccardi
- Andrea ChincariniACAndrea Chincarini
- Giovanni B. FrisoniGFGiovanni B. Frisoni
- Paolo InglesePIPaolo Inglese
- Alberto RedolfiARAlberto Redolfi
- Sabina TangaroSabina Tangaro
- Andrea TateoATAndrea Tateo
- Roberto BellottiRBRoberto Bellotti
Open Access
- 9 July 2015
- journal article
- industrial and-commercial-application
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 19 (2) , 579-591
Abstract
The automated identification of brain structure in Magnetic Resonance Imaging is very important both in neuroscience research and as a possible clinical diagnostic tool. In this study, a novel strategy for fully automated hippocampal segmentation in MRI is presented. It is based on a supervised algorithm, called RUSBoost, which combines data random undersampling with a boosting algorithm. RUSBoost is an algorithm specifically designed for imbalanced classification, suitable for large data sets because it uses random undersampling of the majority class. The RUSBoost performances were compared with those of ADABoost, Random Forest and the publicly available brain segmentation package, FreeSurfer. This study was conducted on a data set of 50 T1-weighted structural brain images. The RUSBoost-based segmentation tool achieved the best results with a Dice’s index of \(0.88 \pm 0.01\) (\(0.87 \pm 0.01\)) for the left (right) brain hemisphere. An independent data set of 50 T1-weighted structural brain scans was used for an independent validation of the fully trained strategies. Again the RUSBoost segmentations compared favorably with manual segmentations with the highest performances among the four tools. Moreover, the Pearson correlation coefficient between hippocampal volumes computed by manual and RUSBoost segmentations was 0.83 (0.82) for left (right) side, statistically significant, and higher than those computed by Adaboost, Random Forest and FreeSurfer. The proposed method may be suitable for accurate, robust and statistically significant segmentations of hippocampi.
Keywords
This publication has 55 references indexed in Scilit:
- Editorial: Advanced physical methods in brain researchThe European Physical Journal Plus, 2012
- Neurodegenerative dementias: From MR Physics lab to assessment roomThe European Physical Journal Plus, 2012
- Alzheimer’s disease markers from structural MRI and FDG-PET brain imagesThe European Physical Journal Plus, 2012
- Multi-Atlas Segmentation with Joint Label FusionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- The Alzheimer's Disease Neuroimaging Initiative: A review of papers published since its inceptionAlzheimer's & Dementia, 2011
- Hippocampal and amygdalar volume changes in elderly patients with Alzheimer's disease and schizophreniaPsychiatry Research: Neuroimaging, 2011
- Harmonization of magnetic resonance‐based manual hippocampal segmentation: A mandatory step for wide clinical useAlzheimer's & Dementia, 2011
- Comparison of AdaBoost and Support Vector Machines for Detecting Alzheimer's Disease Through Automated Hippocampal SegmentationIEEE Transactions on Medical Imaging, 2009
- Research criteria for the diagnosis of Alzheimer's disease: revising the NINCDS–ADRDA criteriaThe Lancet Neurology, 2007
- Active Shape Models-Their Training and ApplicationComputer Vision and Image Understanding, 1995