Efficient brain lesion segmentation using multi-modality tissue-based feature selection and support vector machines
Fiot, Jean-Baptiste; Cohen, Laurent D.; Raniga, Parnesh; Fripp, Jürgen (2013), Efficient brain lesion segmentation using multi-modality tissue-based feature selection and support vector machines, International Journal for Numerical Methods in Biomedical Engineering, 29, 9, p. 905-915. http://dx.doi.org/10.1002/cnm.2537
TypeArticle accepté pour publication ou publié
Nom de la revueInternational Journal for Numerical Methods in Biomedical Engineering
MétadonnéesAfficher la notice complète
Cohen, Laurent D.
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Résumé (EN)Support vector machines (SVM) are machine learning techniques that have been used for segmentation and classification of medical images, including segmentation of white matter hyper-intensities (WMH). Current approaches using SVM for WMH segmentation extract features from the brain and classify these followed by complex post-processing steps to remove false positives. The method presented in this paper combines advanced pre-processing, tissue-based feature selection and SVM classification to obtain efficient and accurate WMH segmentation. Features from 125 patients, generated from up to four MR modalities [T1-w, T2-w, proton-density and fluid attenuated inversion recovery(FLAIR)], differing neighbourhood sizes and the use of multi-scale features were compared. We found that although using all four modalities gave the best overall classification (average Dice scores of 0.54 ± 0.12, 0.72 ± 0.06 and 0.82 ± 0.06 respectively for small, moderate and severe lesion loads); this was not significantly different (p = 0.50) from using just T1-w and FLAIR sequences (Dice scores of 0.52 ± 0.13, 0.71 ± 0.08 and 0.81 ± 0.07). Furthermore, there was a negligible difference between using 5 × 5 × 5 and 3 × 3 × 3 features (p = 0.93). Finally, we show that careful consideration of features and pre-processing techniques not only saves storage space and computation time but also leads to more efficient classification, which outperforms the one based on all features with post-processing.
Mots-clésimage processing; brain lesion; segmentation; classification; support vector machines
Affichage des éléments liés par titre et auteur.
Combining Imaging and Clinical Data in Manifold Learning: Distance-Based and Graph-Based Extensions of Laplacian Eigenmaps Fiot, Jean-Baptiste; Fripp, Jürgen; Cohen, Laurent D. (2012) Communication / Conférence
Fiot, Jean-Baptiste; Cohen, Laurent D.; Bourgeat, Pierrick; Raniga, Parnesh; Acosta, Oscar; Villemagne, Victor; Salvado, Olivier; Fripp, Jürgen (2012) Communication / Conférence
Longitudinal deformation models, spatial regularizations and learning strategies to quantify Alzheimer's disease progression Cohen, Laurent D.; Fiot, Jean-Baptiste; Fripp, Jürgen; Raguet, Hugo; Risser, Laurent; Vialard, François-Xavier (2014) Article accepté pour publication ou publié
Local vs global descriptors of hippocampus shape evolution for Alzheimer's longitudinal population analysis Fiot, Jean-Baptiste; Risser, Laurent; Cohen, Laurent D.; Fripp, Jürgen; Vialard, François-Xavier (2012) Communication / Conférence