Premium
Efficient brain lesion segmentation using multi‐modality tissue‐based feature selection and support vector machines
Author(s) -
Fiot JeanBaptiste,
Cohen Laurent D.,
Raniga Parnesh,
Fripp Jurgen
Publication year - 2013
Publication title -
international journal for numerical methods in biomedical engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.741
H-Index - 63
eISSN - 2040-7947
pISSN - 2040-7939
DOI - 10.1002/cnm.2537
Subject(s) - pattern recognition (psychology) , artificial intelligence , segmentation , support vector machine , fluid attenuated inversion recovery , computer science , feature selection , dice , false positive paradox , feature vector , mathematics , magnetic resonance imaging , medicine , radiology , statistics
SUMMARY 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. Copyright © 2013 John Wiley & Sons, Ltd.