nach oben

Erschienen in:

23.03.2021 | Neuro

Machine learning may predict individual hand motor activation from resting-state fMRI in patients with brain tumors in perirolandic cortex

verfasst von: Chen Niu, Yang Wang, Alexander D. Cohen, Xin Liu, Hongwei Li, Pan Lin, Ziyi Chen, Zhigang Min, Wenfei Li, Xiao Ling, Xin Wen, Maode Wang, Hannah P. Thompson, Ming Zhang

Erschienen in: European Radiology | Ausgabe 7/2021

Einloggen, um Zugang zu erhalten

Abstract

Objective

The study aimed to evaluate the predictive validity of the neural network (NN) method for presurgical mapping of motor areas using resting-state functional MRI (rs-fMRI) data of patients with brain tumor located in the perirolandic cortex (PRC).

Methods

A total of 109 patients with brain tumors occupying PRC underwent rs-fMRI and hand movement task-based fMRI (tb-fMRI) scans. Using a NN model trained on fMRI data of 47 healthy controls, individual task activation maps were predicted from their rs-fMRI data. NN-predicted maps were compared with task activation and independent component analysis (ICA)–derived maps. Spatial Pearson’s correlation coefficients (CC) matrices and Dice coefficients (DC) between task activation and predicted activation using NN (DC_{NN_Act}) and ICA (DC_{ICA_Act}) were calculated and compared using non-parametric tests. The effects of tumor types and head motion on predicted maps were demonstrated.

Results

The CC matrix of NN-predicted maps showed higher diagonal values compared with ICA-derived maps (p < 0.001). DC_{NN_Act} were higher than DC_{ICA_Act} (p < 0.001) for patients with or without motor deficits. Lower DCs were found in subjects with head motion greater than one voxel. DCs were higher on the nontumor side than on the tumor side (p < 0.001), especially in the glioma group compared with meningioma and metastatic groups.

Conclusions

This study indicated that the NN approach could predict individual motor activation using rs-fMRI data and could have promising clinical applications in brain tumor patients with anatomical and functional reorganizations.

Key Points

• The neural network machine learning approach successfully predicted hand motor activation in patients with a tumor in the perirolandic cortex, despite space-occupying effects and possible functional reorganization.

• Compared to the conventional independent component analysis, the neural network approach utilizing resting-state fMRI data yielded a higher correlation to the active task hand activation data.

• The Dice coefficient of machine learning–predicted activation vs. task fMRI activation was different between tumor and nontumor side, also between tumor types, which might indicate different effects of possible neurovascular uncoupling on resting-state and task fMRI.

Nur mit Berechtigung zugänglich

McGirt MJ, Chaichana KL, Gathinji M et al (2009) Independent association of extent of resection with survival in patients with malignant brain astrocytoma. J Neurosurg 110:156–162CrossRef

Chang EF, Clark A, Smith JS et al (2011) Functional mapping–guided resection of low-grade gliomas in eloquent areas of the brain: improvement of long-term survival. J Neurosurg 114:566–573CrossRef

Sanai N, Berger MS (2018) Surgical oncology for gliomas: the state of the art. Nat Rev Clin Oncol 15:112CrossRef

Hervey-Jumper SL, Berger MS (2016) Maximizing safe resection of low-and high-grade glioma. J Neurooncol 130:269–282CrossRef

Niu C, Zhang M, Min Z et al (2014) Motor network plasticity and low-frequency oscillations abnormalities in patients with brain gliomas: a functional MRI study. PLoS One 9:e105134CrossRef

Fraga de Abreu VH, Peck KK, Petrovich-Brennan NM, Woo KM, Holodny AI (2016) Brain tumors: the influence of tumor type and routine MR imaging characteristics at BOLD functional MR imaging in the primary motor gyrus. Radiology 281:876–883CrossRef

Jones OP, Voets N, Adcock J, Stacey R, Jbabdi S (2017) Resting connectivity predicts task activation in pre-surgical populations. NeuroImage Clin 13:378–385CrossRef

Tavor I, Jones OP, Mars R, Smith S, Behrens T, Jbabdi S (2016) Task-free MRI predicts individual differences in brain activity during task performance. Science 352:216–220CrossRef

Rosazza C, Zacà D, Bruzzone MG (2018) Pre-surgical brain mapping: to rest or not to rest? Front Neurol 9:520CrossRef

10.

Kocak M, Ulmer JL, Sahin Ugurel M, Gaggl W, Prost RW (2009) Motor homunculus: passive mapping in healthy volunteers by using functional MR imaging—initial results. Radiology 251:485–492CrossRef

11.

Blatow M, Reinhardt J, Riffel K, Nennig E, Wengenroth M, Stippich C (2011) Clinical functional MRI of sensorimotor cortex using passive motor and sensory stimulation at 3 Tesla. J Magn Reson Imaging 34:429–437CrossRef

12.

Dierker D, Roland JL, Kamran M et al (2017) Resting-state functional magnetic resonance imaging in presurgical functional mapping: sensorimotor localization. Neuroimaging Clin 27:621–633CrossRef

13.

Fox ME, King TZ (2018) Functional connectivity in adult brain tumor patients: a systematic review. Brain Connect 8:381–397CrossRef

14.

Lee MH, Miller-Thomas MM, Benzinger TL et al (2016) Clinical resting-state fMRI in the preoperative setting: are we ready for prime time? Top Magn Reson Imaging 25:11–18CrossRef

15.

Liu H, Buckner RL, Talukdar T, Tanaka N, Madsen JR, Stufflebeam SM (2009) Task-free presurgical mapping using functional magnetic resonance imaging intrinsic activity. J Neurosurg 111:746–754CrossRef

16.

Zhang D, Johnston JM, Fox MD et al (2009) Preoperative sensorimotor mapping in brain tumor patients using spontaneous fluctuations in neuronal activity imaged with functional magnetic resonance imaging: initial experience. Oper Neurosurg 65:ons226–ons236CrossRef

17.

Schölvinck ML, Maier A, Frank QY, Duyn JH, Leopold DA (2010) Neural basis of global resting-state fMRI activity. Proc Natl Acad Sci 107:10238–10243CrossRef

18.

Ghinda DC, Wu J-S, Duncan NW, Northoff G (2018) How much is enough—can resting state fMRI provide a demarcation for neurosurgical resection in glioma? Neurosci Biobehav Rev 84:245–261CrossRef

19.

Kokkonen S-M, Nikkinen J, Remes J et al (2009) Preoperative localization of the sensorimotor area using independent component analysis of resting-state fMRI. Magn Reson Imaging 27:733–740CrossRef

20.

Mannfolk P, Nilsson M, Hansson H et al (2011) Can resting-state functional MRI serve as a complement to task-based mapping of sensorimotor function? A test–retest reliability study in healthy volunteers. J Magn Reson Imaging 34:511–517CrossRef

21.

Hacker CD, Laumann TO, Szrama NP et al (2013) Resting state network estimation in individual subjects. Neuroimage 82:616–633CrossRef

22.

Cohen AD, Chen Z, Parker Jones O, Niu C, Wang Y (2020) Regression-based machine-learning approaches to predict task activation using resting-state fMRI. Hum Brain Mapp 41:815–826CrossRef

23.

Rasero J, Aerts H, Ortega MO, Cortes JM, Stramaglia S, Marinazzo D (2018) Predicting functional networks from region connectivity profiles in task-based versus resting-state fMRI data. PLoS One 13:e0207385CrossRef

24.

Cox RW (1996) AFNI: software for analysis and visualization of functional magnetic resonance neuroimages. Comput Biomed Res 29:162–173CrossRef

25.

Jenkinson M, Beckmann CF, Behrens TE, Woolrich MW, Smith SM (2012) FSL. Neuroimage 62:782–790CrossRef

26.

Smith SM, Beckmann CF, Andersson J et al (2013) Resting-state fMRI in the Human Connectome Project. Neuroimage 80:144–168CrossRef

27.

Filippini N, MacIntosh BJ, Hough MG et al (2009) Distinct patterns of brain activity in young carriers of the APOE-ε4 allele. Proc Natl Acad Sci 106:7209–7214CrossRef

28.

Cole MW, Bassett DS, Power JD, Braver TS, Petersen SE (2014) Intrinsic and task-evoked network architectures of the human brain. Neuron 83:238–251CrossRef

29.

Niu C, Cohen AD, Wen X et al (2020) Modeling motor task activation from resting-state fMRI using machine learning in individual subjects. Brain Imaging Behav 1–11 https://doi.org/10.1007/s11682-019-00239-9

30.

Seto E, Sela G, McIlroy W et al (2001) Quantifying head motion associated with motor tasks used in fMRI. Neuroimage 14:284–297CrossRef

31.

Fisicaro RA, Jost E, Shaw K, Brennan NP, Peck KK, Holodny AI (2016) Cortical plasticity in the setting of brain tumors. Top Magn Reson Imaging 25:25CrossRef

32.

Agarwal S, Sair HI, Yahyavi-Firouz-Abadi N, Airan R, Pillai JJ (2016) Neurovascular uncoupling in resting state fMRI demonstrated in patients with primary brain gliomas. J Magn Reson Imaging 43:620–626CrossRef

Titel: Machine learning may predict individual hand motor activation from resting-state fMRI in patients with brain tumors in perirolandic cortex
verfasst von: Chen Niu
Yang Wang
Alexander D. Cohen
Xin Liu
Hongwei Li
Pan Lin
Ziyi Chen
Zhigang Min
Wenfei Li
Xiao Ling
Xin Wen
Maode Wang
Hannah P. Thompson
Ming Zhang
Publikationsdatum: 23.03.2021
Verlag: Springer Berlin Heidelberg
Erschienen in: European Radiology / Ausgabe 7/2021
Print ISSN: 0938-7994
Elektronische ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-021-07825-w

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Springer Medizin

Machine learning may predict individual hand motor activation from resting-state fMRI in patients with brain tumors in perirolandic cortex