Lesion segmentation from multimodal MRI using random forest following ischemic stroke

Mitra, Jhimli, Bourgeat, Pierrick, Fripp, Jurgen, Ghose, Soumya, Rose, Stephen, Salvado, Olivier, Connelly, Alan, Campbell, Bruce, Palmer, Susan, Sharma, Gagan, Christensen, Soren and Carey, Leeanne (2014) Lesion segmentation from multimodal MRI using random forest following ischemic stroke. NeuroImage, 98 324-335. doi:10.1016/j.neuroimage.2014.04.056

Author Mitra, Jhimli
Bourgeat, Pierrick
Fripp, Jurgen
Ghose, Soumya
Rose, Stephen
Salvado, Olivier
Connelly, Alan
Campbell, Bruce
Palmer, Susan
Sharma, Gagan
Christensen, Soren
Carey, Leeanne
Title Lesion segmentation from multimodal MRI using random forest following ischemic stroke
Journal name NeuroImage   Check publisher's open access policy
ISSN 1095-9572
Publication date 2014-09
Year available 2014
Sub-type Article (original research)
DOI 10.1016/j.neuroimage.2014.04.056
Open Access Status
Volume 98
Start page 324
End page 335
Total pages 12
Place of publication Amsterdam, Netherlands
Publisher Elsevier BV
Collection year 2015
Language eng
Subject 2805 Cognitive Neuroscience
2808 Neurology
Formatted 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. ±. 14.23. yrs) at 3. months 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 3.06. mm. ±. 3.17. mm. The results signify that our method was successful in identifying most of the lesion areas in FLAIR with a low false positive rate.
Keyword Chronic stroke
Ischemic infarct
Lesion likelihood
Markov random field
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Non-UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: UQ Centre for Clinical Research Publications
Faculty of Medicine
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 5 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 15 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Fri, 23 Jan 2015, 18:30:45 EST by System User on behalf of Faculty of Medicine