Top

European Radiology

Published in:

13-01-2022 | Magnetic Resonance Imaging | Nuclear Medicine

Individual [¹⁸F]FDG PET and functional MRI based on simultaneous PET/MRI may predict seizure recurrence after temporal lobe epilepsy surgery

Authors: Jingjuan Wang, Kun Guo, Bixiao Cui, Yaqin Hou, Guoguang Zhao, Jie Lu

Published in: European Radiology | Issue 6/2022

Abstract

Objectives

To investigate the individual measures of brain glucose metabolism, neural activity obtained from simultaneous ¹⁸[F]FDG PET/MRI, and their association with surgical outcomes in medial temporal lobe epilepsy due to hippocampal sclerosis (mTLE-HS).

Methods

Thirty-nine unilateral mTLE-HS patients who underwent anterior temporal lobectomy were classified as having completely seizure-free (Engel class IA; n = 22) or non-seizure-free (Engel class IB–IV; n = 17) outcomes at 1 year after surgery. Preoperative [¹⁸F]FDG PET and functional MRI (fMRI) were obtained from a simultaneous PET/MRI scanner, and individual glucose metabolism and fractional amplitude of low-frequency fluctuation (fALFF) were evaluated by standardizing these with respect to healthy controls. These abnormality measures and clinical data from each patient were incorporated into a machine learning framework (gradient boosting decision tree and logistic regression analysis) to estimate seizure recurrence. The predictive values of features were evaluated by the receiver operating characteristic (ROC) curve in the training and test cohorts.

Results

The machine learning classification model showed [¹⁸F]FDG PET and fMRI variations in contralateral hippocampal network and age of onset identify unfavorable surgical outcomes effectively. In the validation dataset, the logistic regression model with [¹⁸F]FDG PET and fALFF obtained from simultaneous [¹⁸F]FDG PET/MRI gained the maximum area under the ROC curve of 0.905 for seizure recurrence, higher than 0.762 with ¹⁸[F]-FDG PET, and 0.810 with fALFF alone.

Conclusion

Machine learning model suggests individual [¹⁸F]FDG PET and fMRI variations in contralateral hippocampal network based on ¹⁸[F]-FDG PET/MRI could serve as a potential biomarker of unfavorable surgical outcomes.

Key Points

• Individual [ ¹⁸ F]FDG PET and fMRI obtained from preoperative [ ¹⁸ F]FDG PET/MR were investigated.

• Individual differences were further assessed based on a seizure propagation network.

• Machine learning can classify surgical outcomes with 90.5% accuracy.

Available only for authorised users

Rodriguez-Cruces R, Bernhardt BC, Concha L (2020) Multidimensional associations between cognition and connectome organization in temporal lobe epilepsy. Neuroimage 213:116706. https://doi.org/10.1016/j.neuroimage.2020.116706CrossRefPubMed

Li W, Jiang Y, Qin Y et al (2021) Structural and functional reorganization of contralateral hippocampus after temporal lobe epilepsy surgery. Neuroimage Clin 31:102714. https://doi.org/10.1016/j.nicl.2021.102714CrossRefPubMedPubMedCentral

Thijs RD, Surges R, O’Brien TJ, Sander JW (2019) Epilepsy in adults. Lancet 393:689–701. https://doi.org/10.1016/S0140-6736(18)32596-0CrossRefPubMed

Pitkanen A, Loscher W, Vezzani A et al (2016) Advances in the development of biomarkers for epilepsy. Lancet Neurol 15:843–856. https://doi.org/10.1016/S1474-4422(16)00112-5CrossRefPubMed

Grobelny BT, London D, Hill TC, North E, Dugan P, Doyle WK (2018) Betweenness centrality of intracranial electroencephalography networks and surgical epilepsy outcome. Clin Neurophysiol 129:1804–1812. https://doi.org/10.1016/j.clinph.2018.02.135CrossRefPubMed

Andrews JP, Gummadavelli A, Farooque P et al (2019) Association of seizure spread with surgical failure in epilepsy. JAMA Neurol 76:462–469. https://doi.org/10.1001/jamaneurol.2018.4316CrossRefPubMed

O’Muircheartaigh J, Vollmar C, Barker GJ et al (2012) Abnormal thalamocortical structural and functional connectivity in juvenile myoclonic epilepsy. Brain 135:3635–3644. https://doi.org/10.1093/brain/aws296CrossRefPubMedPubMedCentral

Zhang Z, Lu G, Zhong Y et al (2010) fMRI study of mesial temporal lobe epilepsy using amplitude of low-frequency fluctuation analysis. Hum Brain Mapp 31:1851–1861. https://doi.org/10.1002/hbm.20982CrossRefPubMedPubMedCentral

Zou QH, Zhu CZ, Yang Y et al (2008) An improved approach to detection of amplitude of low-frequency fluctuation (ALFF) for resting-state fMRI: fractional ALFF. J Neurosci Methods 172:137–141. https://doi.org/10.1016/j.jneumeth.2008.04.012CrossRefPubMedPubMedCentral

10.

Hwang G, Nair VA, Mathis J et al (2019) Using low-frequency oscillations to detect temporal lobe epilepsy with machine learning. Brain Connect 9:184–193. https://doi.org/10.1089/brain.2018.0601CrossRefPubMedPubMedCentral

11.

Tomas J, Pittau F, Hammers A et al (2019) The predictive value of hypometabolism in focal epilepsy: a prospective study in surgical candidates. Eur J Nucl Med Mol Imaging 46:1806–1816. https://doi.org/10.1007/s00259-019-04356-xCrossRefPubMed

12.

Cahill V, Sinclair B, Malpas CB et al (2019) Metabolic patterns and seizure outcomes following anterior temporal lobectomy. Ann Neurol 85:241–250. https://doi.org/10.1002/ana.25405CrossRefPubMed

13.

Higo T, Sugano H, Nakajima M et al (2016) The predictive value of FDG-PET with 3D-SSP for surgical outcomes in patients with temporal lobe epilepsy. Seizure 41:127–133. https://doi.org/10.1016/j.seizure.2016.07.019CrossRefPubMed

14.

Abbasi B, Goldenholz DM (2019) Machine learning applications in epilepsy. Epilepsia 60:2037–2047. https://doi.org/10.1111/epi.16333CrossRefPubMed

15.

An Q, Yu L(2021) A heterogeneous network embedding framework for predicting similarity-based drug-target interactions. Brief Bioinform. bbab275. https://doi.org/10.1093/bib/bbab275

16.

Wang YH et al (2018) Comparison between simultaneously acquired arterial spin labeling and [¹⁸F]FDG PET in mesial temporal lobe epilepsy assisted by a PET/MR system and SEEG. Neuroimage Clin 19:824–830. https://doi.org/10.1016/j.nicl.2018.06.008CrossRefPubMedPubMedCentral

17.

Scheffer IE, Berkovic S, Capovilla G et al (2017) ILAE classification of the epilepsies: position paper of the ILAE Commission for Classification and Terminology. Epilepsia 58:512–521. https://doi.org/10.1111/epi.13709CrossRefPubMedPubMedCentral

18.

DeSalvo MN, Tanaka N, Douw L, Cole AJ, Stufflebeam SM (2020) Contralateral preoperative resting-state functional MRI network integration is associated with surgical outcome in temporal lobe epilepsy. Radiology 294:622–627. https://doi.org/10.1148/radiol.2020191008CrossRefPubMed

19.

Job AS, David O, Minotti L, Bartolomei F, Chabardes S, Kahane P (2019) Epileptogenicity maps of intracerebral fast activities (60–100 Hz) at seizure onset in epilepsy surgery candidates. Front Neurol 10:1263. https://doi.org/10.3389/fneur.2019.01263CrossRefPubMedPubMedCentral

20.

Lagarde S, Boucekine M, McGonigal A et al (2020) Relationship between PET metabolism and SEEG epileptogenicity in focal lesional epilepsy. Eur J Nucl Med Mol Imaging 47:3130–3142. https://doi.org/10.1007/s00259-020-04791-1CrossRefPubMed

21.

Lin Y, Fang YD, Wu G et al (2018) Quantitative positron emission tomography-guided magnetic resonance imaging postprocessing in magnetic resonance imaging-negative epilepsies. Epilepsia 59:1583–1594. https://doi.org/10.1111/epi.14474CrossRefPubMed

22.

Morgan VL, Englot DJ, Rogers BP et al (2017) Magnetic resonance imaging connectivity for the prediction of seizure outcome in temporal lobe epilepsy. Epilepsia 58:1251–1260. https://doi.org/10.1111/epi.13762CrossRefPubMedPubMedCentral

23.

He X, Doucet GE, Pustina D, Sperling MR, Sharan AD, Tracy JI (2017) Presurgical thalamic “hubness” predicts surgical outcome in temporal lobe epilepsy. Neurology 88:2285–2293. https://doi.org/10.1212/WNL.0000000000004035CrossRefPubMed

24.

Sinha N, Wang Y, Moreira da Silva N et al (2021) Structural brain network abnormalities and the probability of seizure recurrence after epilepsy surgery. Neurology 96:e758–e771. https://doi.org/10.1212/WNL.0000000000011315CrossRefPubMedPubMedCentral

25.

Bettus G, Guedj E, Joyeux F et al (2009) Decreased basal fMRI functional connectivity in epileptogenic networks and contralateral compensatory mechanisms. Hum Brain Mapp 30:1580–1591. https://doi.org/10.1002/hbm.20625CrossRefPubMed

26.

Morgan VL, Abou-Khalil B, Rogers BP (2015) Evolution of functional connectivity of brain networks and their dynamic interaction in temporal lobe epilepsy. Brain Connect 5:35–44. https://doi.org/10.1089/brain.2014.0251CrossRefPubMedPubMedCentral

27.

Chassoux F, Artiges E, Semah F et al (2016) Determinants of brain metabolism changes in mesial temporal lobe epilepsy. Epilepsia 57:907–919. https://doi.org/10.1111/epi.13377CrossRefPubMed

28.

Jo HJ, Reynolds RC, Gotts SJ et al (2020) Fast detection and reduction of local transient artifacts in resting-state fMRI. Comput Biol Med 120:103742. https://doi.org/10.1016/j.compbiomed.2020.103742CrossRefPubMedPubMedCentral

29.

Gupta L, Janssens R, Vlooswijk MC et al (2017) Towards prognostic biomarkers from BOLD fluctuations to differentiate a first epileptic seizure from new-onset epilepsy. Epilepsia 58:476–483. https://doi.org/10.1111/epi.13658CrossRefPubMed

30.

Liao W, Zhang Z, Pan Z et al (2011) Default mode network abnormalities in mesial temporal lobe epilepsy: a study combining fMRI and DTI. Hum Brain Mapp 32:883–895. https://doi.org/10.1002/hbm.21076CrossRefPubMed

31.

Xu Q, Hu Z, Yang F et al (2020) Resting state signal latency assesses the propagation of intrinsic activations and estimates anti-epileptic effect of levetiracetam in Rolandic epilepsy. Brain Res Bull 162:125–131. https://doi.org/10.1016/j.brainresbull.2020.05.016CrossRefPubMed

32.

Shang K, Wang J, Fan X et al (2018) Clinical value of hybrid TOF-PET/MR imaging-based multiparametric imaging in localizing seizure focus in patients with MRI-negative temporal lobe epilepsy. AJNR Am J Neuroradiol 39:1791–1798. https://doi.org/10.3174/ajnr.A5814CrossRefPubMedPubMedCentral

33.

Wang J, Shan Y, Dai J et al (2020) Altered coupling between resting-state glucose metabolism and functional activity in epilepsy. Ann Clin Transl Neurol 7:1831–1842. https://doi.org/10.1002/acn3.51168CrossRefPubMedPubMedCentral

34.

Zhou Y, Ma X-L, Zhang T et al (2021) Use of radiomics based on 18F-FDG PET/CT and machine learning methods to aid clinical decision-making in the classification of solitary pulmonary lesions: an innovative approach. Eur J Nucl Med Mol Imaging 48:2904–2913. https://doi.org/10.1007/s00259-021-05220-7CrossRefPubMed

35.

Halgren M, Ulbert I, Bastuji H et al (2019) The generation and propagation of the human alpha rhythm. Proc Natl Acad Sci U S A 116:23772–23782. https://doi.org/10.1073/pnas.1913092116CrossRefPubMedPubMedCentral

Title: Individual [18F]FDG PET and functional MRI based on simultaneous PET/MRI may predict seizure recurrence after temporal lobe epilepsy surgery
Authors: Jingjuan Wang
Kun Guo
Bixiao Cui
Yaqin Hou
Guoguang Zhao
Jie Lu
Publication date: 13-01-2022
Publisher: Springer Berlin Heidelberg
Keywords: Magnetic Resonance Imaging
Magnetic Resonance Imaging
Epilepsy
Positron Emission Tomography
Published in: European Radiology / Issue 6/2022
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-021-08490-9

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Individual [¹⁸F]FDG PET and functional MRI based on simultaneous PET/MRI may predict seizure recurrence after temporal lobe epilepsy surgery

Abstract

Objectives

Methods

Results

Conclusion

Key Points

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Abstract

Objectives

Methods

Results

Conclusion

Key Points

Please log in to get access to this content

Other articles of this Issue 6/2022

Prediction of hemorrhagic complications after ultrasound-guided biopsy of the thyroid and neck

Tumor resectability and response on CT following neoadjuvant therapy for pancreatic cancer: inter-observer agreement study

Statin use and MRI subchondral bone marrow lesion worsening in generalized osteoarthritis: longitudinal analysis from Osteoarthritis Initiative data

Fully automatic segmentation of craniomaxillofacial CT scans for computer-assisted orthognathic surgery planning using the nnU-Net framework

Measurement of myocardial extracellular volume fraction in patients with heart failure with preserved ejection fraction using dual-energy computed tomography

Performance of current ultrasound-based malignancy risk stratification systems for thyroid nodules in patients with follicular neoplasms