Supervised learning technique for the automated identification of white matter hyperintensities in traumatic brain injury

James R. Stone*, Elisabeth A. Wilde, Brian A. Taylor, David F. Tate, Harvey Levin, Erin D. Bigler, Randall S. Scheibel, Mary R. Newsome, Andrew R. Mayer, Tracy Abildskov, Garrett M. Black, Michael J. Lennon, Gerald E. York, Rajan Agarwal, Jorge DeVillasante, John L. Ritter, Peter B. Walker, Stephen T. Ahlers, Nicholas J. Tustison

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

21 Scopus citations


Background: White matter hyperintensities (WMHs) are foci of abnormal signal intensity in white matter regions seen with magnetic resonance imaging (MRI). WMHs are associated with normal ageing and have shown prognostic value in neurological conditions such as traumatic brain injury (TBI). The impracticality of manually quantifying these lesions limits their clinical utility and motivates the utilization of machine learning techniques for automated segmentation workflows. Methods: This study develops a concatenated random forest framework with image features for segmenting WMHs in a TBI cohort. The framework is built upon the Advanced Normalization Tools (ANTs) and ANTsR toolkits. MR (3D FLAIR, T2- and T1-weighted) images from 24 service members and veterans scanned in the Chronic Effects of Neurotrauma Consortium’s (CENC) observational study were acquired. Manual annotations were employed for both training and evaluation using a leave-one-out strategy. Performance measures include sensitivity, positive predictive value, F1 score and relative volume difference. Results: Final average results were: sensitivity = 0.68 ± 0.38, positive predictive value = 0.51 ± 0.40, F1 = 0.52 ± 0.36, relative volume difference = 43 ± 26%. In addition, three lesion size ranges are selected to illustrate the variation in performance with lesion size. Conclusion: Paired with correlative outcome data, supervised learning methods may allow for identification of imaging features predictive of diagnosis and prognosis in individual TBI patients.

Original languageEnglish
Pages (from-to)1458-1468
Number of pages11
JournalBrain Injury
Issue number12
StatePublished - 14 Oct 2016
Externally publishedYes


  • Neuroimaging
  • TBI
  • brain imaging
  • deep learning
  • machine learning
  • magnetic resonance imaging
  • random forest decision tree


Dive into the research topics of 'Supervised learning technique for the automated identification of white matter hyperintensities in traumatic brain injury'. Together they form a unique fingerprint.

Cite this