| Efficient brain lesion segmentation using multi-modality tissue-based feature selection and support vector machines. | |
| | |
MedLine Citation:
|
PMID: 23303595 Owner: NLM Status: Publisher |
Abstract/OtherAbstract:
|
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. |
| | |
Authors:
|
Jean-Baptiste Fiot; Laurent D Cohen; Parnesh Raniga; Jurgen Fripp |
Related Documents
:
|
12067365 - Multi-field 3d scanning light microscopy of early embryogenesis. 19617885 - Long-term, high-resolution imaging in the mouse neocortex through a chronic cranial win... 12508695 - Flow cytometry and factor analysis evaluation of confocal image sequences of morphologi... 23296085 - Development of a three-dimensional surface imaging system for melanocytic skin lesion e... 21724505 - Non-negative patch alignment framework. 12067365 - Multi-field 3d scanning light microscopy of early embryogenesis. |
Publication Detail:
|
Type: JOURNAL ARTICLE Date: 2013-1-10 |
Journal Detail:
|
Title: International journal for numerical methods in biomedical engineering Volume: - ISSN: 2040-7947 ISO Abbreviation: Int j numer method biomed eng Publication Date: 2013 Jan |
Date Detail:
|
Created Date: 2013-1-10 Completed Date: - Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 101530293 Medline TA: Int j numer method biomed eng Country: - |
Other Details:
|
Languages: ENG Pagination: - Citation Subset: - |
Copyright Information:
|
Copyright © 2013 John Wiley & Sons, Ltd. |
Affiliation:
|
CEREMADE, UMR 7534 CNRS Université Paris Dauphine, France; CSIRO Preventative Health National Research Flagship ICTC, The Australian e-Health Research Centre - BioMedIA, Royal Brisbane and Women's Hospital, Herston, Qld, Australia. |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
|
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Uncovering selection bias in case-control studies using Bayesian post-stratification.
Next Document: Polyoxometalates as a Novel Class of Artificial Proteases: Selective Hydrolysis of Lysozyme under Ph...