Machine learning to investigate superficial white matter integrity in early multiple sclerosis
Corresponding Author
Korhan Buyukturkoglu PhD
Department of Neurology, Columbia University Irving Medical Center, New York, New York, USA
Correspondence
Korhan Buyukturkoglu, Department of Neurology, Columbia University Irving Medical Center, 630 W. 168th Street, PH 18–324 New York, NY 10032, USA.
Email: [email protected]
Search for more papers by this authorChristopher Vergara
Electrical Engineering Department, Universidad de Concepción, Santiago, Chile
Search for more papers by this authorValentina Fuentealba
Electrical Engineering Department, Universidad de Concepción, Santiago, Chile
Search for more papers by this authorCeren Tozlu PhD
Department of Radiology, Weill Cornell Medicine, New York, New York, USA
Search for more papers by this authorJacob B. Dahan
Department of Neurology, Columbia University Irving Medical Center, New York, New York, USA
Search for more papers by this authorBritta E. Carroll
Department of Neurology, Columbia University Irving Medical Center, New York, New York, USA
Search for more papers by this authorAmy Kuceyeski PhD
Department of Radiology, Weill Cornell Medicine, New York, New York, USA
Search for more papers by this authorClaire S. Riley MD
Department of Neurology, Multiple Sclerosis Center, Columbia University Irving Medical Center, New York, New York, USA
Search for more papers by this authorJames F. Sumowski PhD
Corinne Goldsmith Dickinson Center for Multiple Sclerosis, Mount Sinai Hospital, New York, New York, USA
Search for more papers by this authorRanganatha Sitaram ME, PhD
Diagnostic Imaging Department, St. Jude Children's Research Hospital, Memphis, Tennessee, USA
Search for more papers by this authorPamela Guevara PhD
Electrical Engineering Department, Universidad de Concepción, Santiago, Chile
Search for more papers by this authorVictoria M. Leavitt PhD
Department of Neurology, Columbia University Irving Medical Center, New York, New York, USA
Search for more papers by this authorCorresponding Author
Korhan Buyukturkoglu PhD
Department of Neurology, Columbia University Irving Medical Center, New York, New York, USA
Correspondence
Korhan Buyukturkoglu, Department of Neurology, Columbia University Irving Medical Center, 630 W. 168th Street, PH 18–324 New York, NY 10032, USA.
Email: [email protected]
Search for more papers by this authorChristopher Vergara
Electrical Engineering Department, Universidad de Concepción, Santiago, Chile
Search for more papers by this authorValentina Fuentealba
Electrical Engineering Department, Universidad de Concepción, Santiago, Chile
Search for more papers by this authorCeren Tozlu PhD
Department of Radiology, Weill Cornell Medicine, New York, New York, USA
Search for more papers by this authorJacob B. Dahan
Department of Neurology, Columbia University Irving Medical Center, New York, New York, USA
Search for more papers by this authorBritta E. Carroll
Department of Neurology, Columbia University Irving Medical Center, New York, New York, USA
Search for more papers by this authorAmy Kuceyeski PhD
Department of Radiology, Weill Cornell Medicine, New York, New York, USA
Search for more papers by this authorClaire S. Riley MD
Department of Neurology, Multiple Sclerosis Center, Columbia University Irving Medical Center, New York, New York, USA
Search for more papers by this authorJames F. Sumowski PhD
Corinne Goldsmith Dickinson Center for Multiple Sclerosis, Mount Sinai Hospital, New York, New York, USA
Search for more papers by this authorRanganatha Sitaram ME, PhD
Diagnostic Imaging Department, St. Jude Children's Research Hospital, Memphis, Tennessee, USA
Search for more papers by this authorPamela Guevara PhD
Electrical Engineering Department, Universidad de Concepción, Santiago, Chile
Search for more papers by this authorVictoria M. Leavitt PhD
Department of Neurology, Columbia University Irving Medical Center, New York, New York, USA
Search for more papers by this authorFunding information:
Study Funded by National Multiple Sclerosis Society (FG-1808-32225 to KB, RG48101A1/1T to VL), National Institutes of Health (HD-082176 to JFS), and National Agency for Research and Development (ANID FONDECYT 1190701 and ANID-Basal Project FB0008 to PG)
Abstract
Background and Purpose
This study aims todetermine the sensitivity of superficial white matter (SWM) integrity as a metric to distinguish early multiple sclerosis (MS) patients from healthy controls (HC).
Methods
Fractional anisotropy and mean diffusivity (MD) values from SWM bundles across the cortex and major deep white matter (DWM) tracts were extracted from 29 early MS patients and 31 age- and sex-matched HC. Thickness of 68 cortical regions and resting-state functional-connectivity (RSFC) among them were calculated. The distribution of structural and functional metrics between groups were compared using Wilcoxon rank-sum test. Utilizing a machine learning method (adaptive boosting), 6 models were built based on: 1-SWM, 2-DWM, 3-SWM and DWM, 4-cortical thickness, or 5-RSFC measures. In model 6, all features from previous models were incorporated. The models were trained with nested 5-folds cross-validation. Area under the receiver operating characteristic curve (AUCroc) values were calculated to evaluate classification performance of each model. Permutation tests were used to compare the AUCroc values.
Results
Patients had higher MD in SWM bundles including insula, inferior frontal, orbitofrontal, superior and medial temporal, and pre- and post-central cortices (p < .05). No group differences were found for any other MRI metric. The model incorporating SWM and DWM features provided the best classification (AUCroc = 0.75). The SWM model provided higher AUCroc (0.74), compared to DWM (0.63), cortical thickness (0.67), RSFC (0.63), and all-features (0.68) models (p < .001 for all).
Conclusion
Our results reveal a non-random pattern of SWM abnormalities at early stages of MS even before pronounced structural and functional alterations emerge.
REFERENCES
- 1Bae HG, Kim TK, Suk HY, Jung SY, Jo DG. White matter and neurological disorders. Arch Pharm Res 2020; 43: 920–31.
- 2Wycoco V, Shroff M, Sudhakar S, Lee W. White matter anatomy: what the radiologist needs to know. Neuroimaging Clin N Am 2013; 23: 197–216.
- 3Phillips OR, Clark KA, Luders E, Azhir R, Joshi SH, Woods RP, et al. Superficial white matter: effects of age, sex, and hemisphere. Brain Connect 2013; 3: 146–59.
- 4Nazeri A, Chakravarty MM, Felsky D, et al. Alterations of superficial white matter in schizophrenia and relationship to cognitive performance. Neuropsychopharmacology 2013; 38: 1954–62.
- 5Ciccarelli O, Barkhof F, Bodini B, De Stefano N, Golay X, Nicolay K, et al. Pathogenesis of multiple sclerosis: insights from molecular and metabolic imaging. Lancet Neurol 2014; 13: 807–22.
- 6Meynert T. Psychiatry: a clinical treatise on diseases of the forebrain based upon a study of its structure, functions, and nutrition. New York: G.P. Putnam's Sons; 1885.
- 7 A Schüz, R Miller, editors. Cortical areas: unity and diversity. London: Taylor & Francis; 2002.
10.4324/9780203219911 Google Scholar
- 8Kirilina E, Helbling S, Morawski M, Pine K, Reimann K, Jankuhn S, et al. Superficial white matter imaging: contrast mechanisms and whole-brain in vivo mapping. Sci Adv 2020; 6:eaaz9281.
- 9Song AW, Chang HC, Petty C, Guidon A, Chen NK. Improved delineation of short cortical association fibers and gray/white matter boundary using whole-brain three-dimensional diffusion tensor imaging at submillimeter spatial resolution. Brain Connect 2014; 4: 636–40.
- 10Movahedian Attar F, Kirilina E, Haenelt D, Pine KJ, Trampel R, Edwards LJ, et al. Mapping short association fibers in the early cortical visual processing stream using in vivo diffusion tractography. Cereb Cortex 2020; 30: 4496–514.
- 11Guevara M, Guevara P, Roman C, Mangin J-F. Superficial white matter: a review on the dMRI analysis methods and applications. Neuroimage 2020; 212:116673.
- 12Phillips OR, Joshi SH, Squitieri F, Sanchez-Castaneda C, Narr K, Shattuck DW, et al. Major superficial white matter abnormalities in Huntington's disease. Front Neurosci 2016; 10: 197.
- 13Suarez-Sola ML, Gonzalez-Delgado FJ, Pueyo-Morlans M, Medina-Bolívar OC, Hernández-Acosta NC, González-Gómez M, et al. Neurons in the white matter of the adult human neocortex. Front Neuroanat 2009; 3: 7.
- 14Miki Y, Grossman RI, Udupa JK, Wei L, Kolson DL, Mannon LJ, et al. Isolated U-fiber involvement in MS: preliminary observations. Neurology 1998; 50: 1301–6.
- 15Bigham B, Zamanpour SA, Zemorshidi F, Boroumand F, Zare H, Alzheimer's Disease Neuroimaging Initiative. Identification of superficial white matter abnormalities in Alzheimer's disease and mild cognitive impairment using diffusion tensor imaging. J Alzheimers Dis Rep 2020; 4: 49–59.
- 16Soares JM, Marques P, Alves V, Sousa N. A hitchhiker's guide to diffusion tensor imaging. Front Neurosci 2013; 7: 31.
- 17Sbardella E, Tona F, Petsas N, Pantano P. DTI measurements in multiple sclerosis: evaluation of brain damage and clinical implications. Mult Scler Int 2013; 2013:671730.
- 18Van Schependom J, Gielen J, Laton J, Sotiropoulos G, Vanbinst A-M, De Mey J, et al. The effect of morphological and microstructural integrity of the corpus callosum on cognition, fatigue and depression in mildly disabled MS patients. Magn Reson Imaging 2017; 40: 109–14.
- 19Brandstadter R, Ayeni O, Krieger SC, Harel NY, Escalon MX, Sand IK, et al. Detection of subtle gait disturbance and future fall risk in early multiple sclerosis. Neurology 2020; 94: e1395–e406.
- 20Leavitt VM, Brandstadter R, Fabian M, Sand IK, Klineova S, Krieger S, et al. Dissociable cognitive patterns related to depression and anxiety in multiple sclerosis. Mult Scler 2020; 26: 1247–55.
- 21Kurtzke JF. Rating neurologic impairment in multiple sclerosis: an expanded disability status scale (EDSS). Neurology 1983; 33: 1444–52.
- 22Kieseier BC, Pozzilli C. Assessing walking disability in multiple sclerosis. Mult Scler 2012; 18: 914–24.
- 23Cutter GR, Baier ML, Rudick RA, Cookfair DL, Fischer JS, Petkau J, et al. Development of a multiple sclerosis functional composite as a clinical trial outcome measure. Brain 1999; 122: 871–82.
- 24Krupp LB, LaRocca NG, Muir-Nash J, Steinberg AD. The fatigue severity scale. Application to patients with multiple sclerosis and systemic lupus erythematosus. Arch Neurol 1989; 46: 1121–3.
- 25Wechsler, D. Wechsler Test of Adult Reading: WTAR. San Antonio, TX: Psychological Corporation; 2001.
- 26Dale AM, Fischl B, Sereno MI. Cortical surface-based analysis. I. Segmentation and surface reconstruction. Neuroimage 1999; 9: 179–94.
- 27Whitfield-Gabrieli S, Nieto-Castanon A. Conn: a functional connectivity toolbox for correlated and anticorrelated brain networks. Brain Connect 2012; 2: 125–41.
- 28Yeh FC, Verstynen TD, Wang Y, Fernández-Miranda JC, Tseng WYI. Deterministic diffusion fiber tracking improved by quantitative anisotropy. PLoS One 2013; 8:e80713.
- 29Guevara P, Duclap D, Poupon C, Marrakchi-Kacem L, Fillard P, Le Bihan D, et al. Automatic fiber bundle segmentation in massive tractography datasets using a multi-subject bundle atlas. Neuroimage 2012; 61: 1083–99.
- 30Labra N, Guevara P, Duclap D, Houenou J, Poupon C, Mangin J-F, et al. Fast automatic segmentation of white matter streamlines based on a multi-subject bundle atlas. Neuroinformatics 2017; 15: 71–86.
- 31Vázquez A, López-López N, Labra N, Figueroa M, Poupon C, Mangin J-F, et al. Parallel optimization of fiber bundle segmentation for massive tractography datasets. 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) April 8–11, Venice, Italy. Piscataway, NJ: IEEE; 2019. p. 178-81.
- 32Guevara M, Roman C, Houenou J, Duclap D, Poupon C, Mangin J-F, et al. Reproducibility of superficial white matter tracts using diffusion-weighted imaging tractography. Neuroimage 2017; 147: 703–25.
- 33Desikan RS, Segonne F, Fischl B, Quinn BT, Dickerson BC, Blacker D, et al. An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. Neuroimage 2006; 31: 968–80.
- 34Yendiki A, Panneck P, Srinivasan P, Stevens A, Zöllei L, Augustinack J, et al. Automated probabilistic reconstruction of white-matter pathways in health and disease using an atlas of the underlying anatomy. Front Neuroinform 2011; 5: 23.
- 35Benjamini Y, Hochberg Y. Controlling the false discovery rate: a practical and powerful approach to multiple testing. J R Stat Soc Series B Stat Methodol 1995; 57: 289–300.
- 36Alfaro E, Gamez M, García N. adabag: An R package for classification with boosting and bagging. J Stat Softw 2013; 54: 1–35.
- 37David, H.A. The beginnings of randomization tests. Am State 2008; 62: 70–2.
- 38Wu M, Kumar A, Yang S. Development and aging of superficial white matter myelin from young adulthood to old age: mapping by vertex-based surface statistics (VBSS). Hum Brain Mapp 2016; 37: 1759–69.
- 39Phillips OR, Joshi SH, Narr KL, Shattuck DW, Singh M, Di Paola M, et al. Superficial white matter damage in anti-NMDA receptor encephalitis. J Neurol Neurosurg Psychiatry 2018; 89: 518–25.
- 40Narayana PA, Govindarajan KA, Goel P, Datta S, Lincoln JA, Cofield SS, et al. Regional cortical thickness in relapsing remitting multiple sclerosis: a multi-center study. Neuroimage Clin 2012; 2: 120–31.
- 41Tsagkas C, Chakravarty MM, Gaetano L, Naegelin Y, Amann M, Parmar K, et al. Longitudinal patterns of cortical thinning in multiple sclerosis. Hum Brain Mapp 2020; 41: 2198–215.
- 42Futatsuya K, Kakeda S, Yoneda T, Ueda I, Watanabe K, Moriya J, et al. Juxtacortical lesions in multiple sclerosis: assessment of gray matter involvement using phase difference-enhanced imaging (PADRE). Magn Reson Med Sci 2016; 15: 349–54.
- 43Werring DJ, Brassat D, Droogan AG, Clark CA, Symms MR, Barker GJ, et al. The pathogenesis of lesions and normal-appearing white matter changes in multiple sclerosis: a serial diffusion MRI study. Brain 2000; 123: 1667–76.
- 44Nazeri A, Chakravarty MM, Rajji TK, Felsky D, Rotenberg DJ, Mason M, et al. Superficial white matter as a novel substrate of age-related cognitive decline. Neurobiol Aging 2015; 36: 2094–106.
- 45Lazeron RH, Langdon DW, Filippi M, van Waesberghe JH, Stevenson VL, Boringa JB, et al. Neuropsychological impairment in multiple sclerosis patients: the role of (juxta)cortical lesion on FLAIR. Mult Scler 2000; 6: 280–5.
- 46Brandstadter R, Fabian M, Leavitt VM, Krieger S, Yeshokumar A, Sand IK, et al. Word-finding difficulty is a prevalent disease-related deficit in early multiple sclerosis. Mult Scler 2020; 26: 1752–64.
- 47Reveley C, Seth AK, Pierpaoli C, Silva AC, Yu D, Saunders RC, et al. Superficial white matter fiber systems impede detection of long-range cortical connections in diffusion MR tractography. Proc Natl Acad Sci USA 2015; 112: e2820–8.
- 48Calamante F, Tournier JD, Smith RE, Connelly A. A generalised framework for super-resolution track-weighted imaging. Neuroimage 2012; 59: 2494–503.
Citing Literature
