Format

Send to

Choose Destination
See comment in PubMed Commons below
Neuroimage. 2014 Sep;98:324-35. doi: 10.1016/j.neuroimage.2014.04.056. Epub 2014 May 2.

Lesion segmentation from multimodal MRI using random forest following ischemic stroke.

Author information

1
CSIRO Preventative Health Flagship, CSIRO Computational Informatics, The Australian e-Health Research Centre, Herston, QLD, Australia. Electronic address: jhimli.mitra@csiro.au.
2
CSIRO Preventative Health Flagship, CSIRO Computational Informatics, The Australian e-Health Research Centre, Herston, QLD, Australia. Electronic address: pierrick.bourgeat@csiro.au.
3
CSIRO Preventative Health Flagship, CSIRO Computational Informatics, The Australian e-Health Research Centre, Herston, QLD, Australia. Electronic address: jurgen.fripp@csiro.au.
4
CSIRO Preventative Health Flagship, CSIRO Computational Informatics, The Australian e-Health Research Centre, Herston, QLD, Australia. Electronic address: soumya.ghose@csiro.au.
5
CSIRO Preventative Health Flagship, CSIRO Computational Informatics, The Australian e-Health Research Centre, Herston, QLD, Australia. Electronic address: stephen.rose@csiro.au.
6
CSIRO Preventative Health Flagship, CSIRO Computational Informatics, The Australian e-Health Research Centre, Herston, QLD, Australia. Electronic address: olivier.salvado@csiro.au.
7
The Florey Institute of Neuroscience and Mental Health, Parkville, VIC, Australia.
8
Department of Medicine and Neurology, Melbourne Brain Centre at the Royal Melbourne Hospital, University of Melbourne, Parkville, VIC, Australia.
9
The Florey Institute of Neuroscience and Mental Health, Parkville, VIC, Australia. Electronic address: spalmer1@gmail.com.
10
Department of Radiology, Melbourne Brain Centre at the Royal Melbourne Hospital, University of Melbourne, Parkville, VIC, Australia.
11
The Florey Institute of Neuroscience and Mental Health, Parkville, VIC, Australia; Department of Occupational Therapy, La Trobe University, Bundoora, VIC, Australia. Electronic address: Leeanne.Carey@florey.edu.au.

Abstract

Understanding structure-function relationships in the brain after stroke is reliant not only on the accurate anatomical delineation of the focal ischemic lesion, but also on previous infarcts, remote changes and the presence of white matter hyperintensities. The robust definition of primary stroke boundaries and secondary brain lesions will have significant impact on investigation of brain-behavior relationships and lesion volume correlations with clinical measures after stroke. Here we present an automated approach to identify chronic ischemic infarcts in addition to other white matter pathologies, that may be used to aid the development of post-stroke management strategies. Our approach uses Bayesian-Markov Random Field (MRF) classification to segment probable lesion volumes present on fluid attenuated inversion recovery (FLAIR) MRI. Thereafter, a random forest classification of the information from multimodal (T1-weighted, T2-weighted, FLAIR, and apparent diffusion coefficient (ADC)) MRI images and other context-aware features (within the probable lesion areas) was used to extract areas with high likelihood of being classified as lesions. The final segmentation of the lesion was obtained by thresholding the random forest probabilistic maps. The accuracy of the automated lesion delineation method was assessed in a total of 36 patients (24 male, 12 female, mean age: 64.57±14.23yrs) at 3months after stroke onset and compared with manually segmented lesion volumes by an expert. Accuracy assessment of the automated lesion identification method was performed using the commonly used evaluation metrics. The mean sensitivity of segmentation was measured to be 0.53±0.13 with a mean positive predictive value of 0.75±0.18. The mean lesion volume difference was observed to be 32.32%±21.643% with a high Pearson's correlation of r=0.76 (p<0.0001). The lesion overlap accuracy was measured in terms of Dice similarity coefficient with a mean of 0.60±0.12, while the contour accuracy was observed with a mean surface distance of 3.06mm±3.17mm. The results signify that our method was successful in identifying most of the lesion areas in FLAIR with a low false positive rate.

KEYWORDS:

Chronic stroke; FLAIR MRI; Ischemic infarct; Lesion likelihood; Markov random field; Random forest; Secondary lesions; White matter lesions

[Indexed for MEDLINE]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Elsevier Science
    Loading ...
    Support Center