Show simple item record

Efficient brain lesion segmentation using multi-modality tissue-based feature selection and support vector machines

hal.structure.identifier
dc.contributor.authorFiot, Jean-Baptiste*
hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
dc.contributor.authorCohen, Laurent D.
HAL ID: 738939		*
hal.structure.identifier
dc.contributor.authorRaniga, Parnesh*
hal.structure.identifier
dc.contributor.authorFripp, Jürgen*
dc.date.accessioned2013-06-21T10:55:56Z
dc.date.available2013-06-21T10:55:56Z
dc.date.issued2013
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/11454
dc.language.isoenen
dc.subjectimage processingen
dc.subjectbrain lesionen
dc.subjectsegmentationen
dc.subjectclassificationen
dc.subjectsupport vector machinesen
dc.subject.ddc621.3en
dc.titleEfficient brain lesion segmentation using multi-modality tissue-based feature selection and support vector machinesen
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenSupport 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.en
dc.relation.isversionofjnlnameInternational Journal for Numerical Methods in Biomedical Engineering
dc.relation.isversionofjnlvol29
dc.relation.isversionofjnlissue9
dc.relation.isversionofjnldate2013
dc.relation.isversionofjnlpages905-915
dc.relation.isversionofdoihttp://dx.doi.org/10.1002/cnm.2537en
dc.relation.isversionofjnlpublisherWileyen
dc.subject.ddclabelTraitement du signalen
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut


Files in this item

Thumbnail
Name:
_FIOT_IJNM2013_Efficicient_bra ...
Size:
570.0Kb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record