James R Stone1,2, Elisabeth A Wilde3,4,5,6, Brian A Taylor3,4,6, David F Tate7, Harvey Levin3,4,5, Erin D Bigler8, Randall S Scheibel3,4, Mary R Newsome3,4, Andrew R Mayer9,10, Tracy Abildskov8, Garrett M Black4,8, Michael J Lennon11, Gerald E York12, Rajan Agarwal3, Jorge DeVillasante13, John L Ritter14,15, Peter B Walker16, Stephen T Ahlers16, Nicholas J Tustison1. 1. a Department of Radiology and Medical Imaging. 2. b Department of Neurological Surgery , University of Virginia , Charlottesville , VA , USA. 3. c Michael E. DeBakey Veterans Affairs Medical Center , Houston , TX , USA. 4. d Department of Physical Medicine and Rehabilitation. 5. e Department of Neurology. 6. f Department of Radiology , Baylor College of Medicine , Houston , TX , USA. 7. g Missouri Institute of Mental Health, University of Missouri , St. Louis , MO , USA. 8. h Department of Psychology , Brigham Young University , Provo , UT , USA. 9. i Department of Translational Neuroscience , The Mind Research Network , Albuquerque , NM , USA. 10. j Department of Neurology , University of New Mexico Health Center , Albuquerque , NM , USA. 11. k Hunter Holmes McGuire Veterans Affairs Medical Center , Richmond , VA , USA. 12. l Alaska Radiology Associates , Anchorage , AK , USA. 13. m Department of Radiology , USF Morsani College of Medicine , Tampa , FL , USA. 14. n Department of Radiology , San Antonio Military Medical Center , San Antonio , TX , USA. 15. o Department of Radiology and Radiological Sciences , Uniformed Services University of the Health Sciences , Washington , DC , USA. 16. p Naval Medical Research Center , Silver Spring, MD , USA.
Abstract
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, [Formula: see text] score and relative volume difference. RESULTS: Final average results were: sensitivity = 0.68 ± 0.38, positive predictive value = 0.51 ± 0.40, [Formula: see text] = 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.
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, [Formula: see text] score and relative volume difference. RESULTS: Final average results were: sensitivity = 0.68 ± 0.38, positive predictive value = 0.51 ± 0.40, [Formula: see text] = 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.
Entities:
Keywords:
Neuroimaging; TBI; brain imaging; deep learning; machine learning; magnetic resonance imaging; random forest decision tree
Authors: Leon Lenchik; Laura Heacock; Ashley A Weaver; Robert D Boutin; Tessa S Cook; Jason Itri; Christopher G Filippi; Rao P Gullapalli; James Lee; Marianna Zagurovskaya; Tara Retson; Kendra Godwin; Joey Nicholson; Ponnada A Narayana Journal: Acad Radiol Date: 2019-08-10 Impact factor: 3.173
Authors: Y W Lui; P D Chang; G Zaharchuk; D P Barboriak; A E Flanders; M Wintermark; C P Hess; C G Filippi Journal: AJNR Am J Neuroradiol Date: 2020-07-30 Impact factor: 3.825
Authors: Tushar R Jha; Mark F Quigley; Khashayar Mozaffari; Orgest Lathia; Katherine Hofmann; John S Myseros; Chima Oluigbo; Robert F Keating Journal: Childs Nerv Syst Date: 2022-05-20 Impact factor: 1.532
Authors: Erin S Kenzie; Elle L Parks; Erin D Bigler; David W Wright; Miranda M Lim; James C Chesnutt; Gregory W J Hawryluk; Wayne Gordon; Wayne Wakeland Journal: Front Neurol Date: 2018-04-04 Impact factor: 4.003
Authors: Elisabeth A Wilde; Ina-Beate Wanner; Kimbra Kenney; Jessica Gill; James R Stone; Seth Disner; Caroline Schnakers; Retsina Meyer; Eric M Prager; Magali Haas; Andreas Jeromin Journal: J Neurotrauma Date: 2022-02-14 Impact factor: 5.269