Improved Automatic Segmentation of White Matter Hyperintensities in MRI Based on Multilevel Lesion Features
- PDF / 2,996,679 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 65 Downloads / 206 Views
ORIGINAL ARTICLE
Improved Automatic Segmentation of White Matter Hyperintensities in MRI Based on Multilevel Lesion Features M. Rincón 1 & E. Díaz-López 1 & P. Selnes 2 & K. Vegge 3 & M. Altmann 2 & T. Fladby 2 & A. Bjørnerud 4,5
# Springer Science+Business Media New York 2017
Abstract Brain white matter hyperintensities (WMHs) are linked to increased risk of cerebrovascular and neurodegenerative diseases among the elderly. Consequently, detection and characterization of WMHs are of significant clinical importance. We propose a novel approach for WMH segmentation from multi-contrast MRI where both voxel-based and lesionbased information are used to improve overall performance in both volume-oriented and object-oriented metrics. Our segmentation method (AMOS-2D) consists of four stages following a Bgenerate-and-test^ approach: pre-processing, Gaussian white matter (WM) modelling, hierarchical multi-threshold WMH segmentation and object-based WMH filtering using support vector machines. Data from 28 subjects was used in this study covering a wide range of lesion loads. Volumetric T1weighted images and 2D fluid attenuated inversion recovery (FLAIR) images were used as basis for the WM model and lesion masks defined manually in each subject by experts were used for training and evaluating the proposed method. The method obtained an average agreement (in terms of the Dice similarity coefficient, DSC) with experts equivalent to inter-
* M. Rincón [email protected]
1
Department of Artificial Intelligence, UNED, Madrid, Spain
2
Department of Neurology, Akershus University Hospital, Oslo, Norway
3
Department of Radiology, Akershus University Hospital, Oslo, Norway
4
The Intervention Centre, Oslo University Hospital, Oslo, Norway
5
Department of Physics, University of Oslo, Oslo, Norway
expert agreement both in terms of WMH number (DSC = 0.637 vs. 0.651) and volume (DSC = 0.743 vs. 0.781). It allowed higher accuracy in detecting WMH compared to alternative methods tested and was further found to be insensitive to WMH lesion burden. Good agreement with expert annotations combined with stable performance largely independent of lesion burden suggests that AMOS-2D will be a valuable tool for fully automated WMH segmentation in patients with cerebrovascular and neurodegenerative pathologies. Keywords White matter lesions . White matter hyperintensities . Amorphous object segmentation . Object-oriented analysis . Similarity index . WM modelling . Automated WMH detection
Introduction White matter hyperintensities (WMH), as detected by magnetic resonance imaging (MRI), are of significant clinical importance since they are associated with increased risk of stroke, cognitive impairment, dementia and ultimately, death (Ramirez et al. 2011; Wardlaw et al. 2013). Manual WMH segmentation is very time-consuming and prone to user-bias, which has resulted in an ongoing effort to generate automated analysis tools for WMH segmentation. Such automated tools typically require multiple MR sequences with different relaxation weig
Data Loading...
