Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Development and Validation of MRI-Based Radiomics Models for Diagnosing Juvenile Myoclonic Epilepsy

  • Kyung Min Kim (Department of Neurology, Epilepsy Research Institute, Yonsei University College of Medicine) ;
  • Heewon Hwang (Department of Neurology, Wonju Severance Christian Hospital, Yonsei University Wonju College of Medicine) ;
  • Beomseok Sohn (Department of Radiology, Severance Hospital, Research Institute of Radiological Science and Centre for Clinical Imaging Data Science, Yonsei University College of Medicine) ;
  • Kisung Park (Department of Radiology, Severance Hospital, Research Institute of Radiological Science and Centre for Clinical Imaging Data Science, Yonsei University College of Medicine) ;
  • Kyunghwa Han (Department of Radiology, Severance Hospital, Research Institute of Radiological Science and Centre for Clinical Imaging Data Science, Yonsei University College of Medicine) ;
  • Sung Soo Ahn (Department of Radiology, Severance Hospital, Research Institute of Radiological Science and Centre for Clinical Imaging Data Science, Yonsei University College of Medicine) ;
  • Wonwoo Lee (Department of Neurology, Yongin Severance Hospital, Yonsei University Health System) ;
  • Min Kyung Chu (Department of Neurology, Epilepsy Research Institute, Yonsei University College of Medicine) ;
  • Kyoung Heo (Department of Neurology, Epilepsy Research Institute, Yonsei University College of Medicine) ;
  • Seung-Koo Lee (Department of Radiology, Severance Hospital, Research Institute of Radiological Science and Centre for Clinical Imaging Data Science, Yonsei University College of Medicine)
  • Received : 2022.06.23
  • Accepted : 2022.09.26
  • Published : 2022.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: Radiomic modeling using multiple regions of interest in MRI of the brain to diagnose juvenile myoclonic epilepsy (JME) has not yet been investigated. This study aimed to develop and validate radiomics prediction models to distinguish patients with JME from healthy controls (HCs), and to evaluate the feasibility of a radiomics approach using MRI for diagnosing JME. Materials and Methods: A total of 97 JME patients (25.6 ± 8.5 years; female, 45.5%) and 32 HCs (28.9 ± 11.4 years; female, 50.0%) were randomly split (7:3 ratio) into a training (n = 90) and a test set (n = 39) group. Radiomic features were extracted from 22 regions of interest in the brain using the T1-weighted MRI based on clinical evidence. Predictive models were trained using seven modeling methods, including a light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, with radiomics features in the training set. The performance of the models was validated and compared to the test set. The model with the highest area under the receiver operating curve (AUROC) was chosen, and important features in the model were identified. Results: The seven tested radiomics models, including light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, showed AUROC values of 0.817, 0.807, 0.783, 0.779, 0.767, 0.762, and 0.672, respectively. The light gradient boosting machine with the highest AUROC, albeit without statistically significant differences from the other models in pairwise comparisons, had accuracy, precision, recall, and F1 scores of 0.795, 0.818, 0.931, and 0.871, respectively. Radiomic features, including the putamen and ventral diencephalon, were ranked as the most important for suggesting JME. Conclusion: Radiomic models using MRI were able to differentiate JME from HCs.

Keywords

References

  1. Camfield CS, Striano P, Camfield PR. Epidemiology of juvenile myoclonic epilepsy. Epilepsy Behav 2013;28 Suppl 1:S15-S17 
  2. No authors listed. Proposal for revised classification of epilepsies and epileptic syndromes. Commission on classification and terminology of the international league against epilepsy. Epilepsia 1989;30:389-399 
  3. Cao B, Tang Y, Li J, Zhang X, Shang HF, Zhou D. A meta-analysis of voxel-based morphometry studies on gray matter volume alteration in juvenile myoclonic epilepsy. Epilepsy Res 2013;106:370-377 
  4. O'Muircheartaigh J, Vollmar C, Barker GJ, Kumari V, Symms MR, Thompson P, et al. Abnormal thalamocortical structural and functional connectivity in juvenile myoclonic epilepsy. Brain 2012;135(Pt 12):3635-3644 
  5. Roebling R, Scheerer N, Uttner I, Gruber O, Kraft E, Lerche H. Evaluation of cognition, structural, and functional MRI in juvenile myoclonic epilepsy. Epilepsia 2009;50:2456-2465 
  6. de Oliveira MS, Betting LE, Mory SB, Cendes F, Castellano G. Texture analysis of magnetic resonance images of patients with juvenile myoclonic epilepsy. Epilepsy Behav 2013;27:22-28 
  7. Keller SS, Ahrens T, Mohammadi S, Moddel G, Kugel H, Ringelstein EB, et al. Microstructural and volumetric abnormalities of the putamen in juvenile myoclonic epilepsy. Epilepsia 2011;52:1715-1724 
  8. Filho GM, Jackowski AP, Lin K, Silva I, Guaranha MSB, Guilhoto LM, et al. The integrity of corpus callosum and cluster B personality disorders: a quantitative MRI study in juvenile myoclonic epilepsy. Prog Neuropsychopharmacol Biol Psychiatry 2010;34:516-521 
  9. Lee DA, Ko J, Lee HJ, Kim HC, Park BS, Park S, et al. Alterations of the intrinsic amygdala-hippocampal network in juvenile myoclonic epilepsy. Brain Behav 2021;11:e2274 
  10. Wang Y, Berglund IS, Uppman M, Li TQ. Juvenile myoclonic epilepsy has hyper dynamic functional connectivity in the dorsolateral frontal cortex. Neuroimage Clin 2019;21:101604 
  11. Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Carvalho S, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 2014;5:4006 
  12. Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology 2016;278:563-577 
  13. Mo J, Liu Z, Sun K, Ma Y, Hu W, Zhang C, et al. Automated detection of hippocampal sclerosis using clinically empirical and radiomics features. Epilepsia 2019;60:2519-2529 
  14. Liu Z, Wang Y, Liu X, Du Y, Tang Z, Wang K, et al. Radiomics analysis allows for precise prediction of epilepsy in patients with low-grade gliomas. Neuroimage Clin 2018;19:271-278 
  15. Segonne F, Dale AM, Busa E, Glessner M, Salat D, Hahn HK, et al. A hybrid approach to the skull stripping problem in MRI. Neuroimage 2004;22:1060-1075 
  16. Fischl B, Salat DH, Busa E, Albert M, Dieterich M, Haselgrove C, et al. Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain. Neuron 2002;33:341-355 
  17. Segonne F, Pacheco J, Fischl B. Geometrically accurate topology-correction of cortical surfaces using nonseparating loops. IEEE Trans Med Imaging 2007;26:518-529 
  18. Dale AM, Fischl B, Sereno MI. Cortical surface-based analysis. I. Segmentation and surface reconstruction. Neuroimage 1999;9:179-194 
  19. Focke NK, Diederich C, Helms G, Nitsche MA, Lerche H, Paulus W. Idiopathic-generalized epilepsy shows profound white matter diffusion-tensor imaging alterations. Hum Brain Mapp 2014;35:3332-3342 
  20. Ekmekci B, Bulut HT, Gumus,tas, F, Yildirim A, Kus,tepe A. The relationship between white matter abnormalities and cognitive functions in new-onset juvenile myoclonic epilepsy. Epilepsy Behav 2016;62:166-170 
  21. Saini J, Sinha S, Bagepally BS, Ramchandraiah CT, Thennarasu K, Prasad C, et al. Subcortical structural abnormalities in juvenile myoclonic epilepsy (JME): MR volumetry and vertex based analysis. Seizure 2013;22:230-235 
  22. Zhong C, Liu R, Luo C, Jiang S, Dong L, Peng R, et al. Altered structural and functional connectivity of juvenile myoclonic epilepsy: an fMRI study. Neural Plast 2018;2018:7392187 
  23. Bartolini E, Pesaresi I, Fabbri S, Cecchi P, Giorgi FS, Sartucci F, et al. Abnormal response to photic stimulation in juvenile myoclonic epilepsy: an EEG-fMRI study. Epilepsia 2014;55:1038-1047 
  24. Ciumas C, Wahlin TB, Jucaite A, Lindstrom P, Halldin C, Savic I. Reduced dopamine transporter binding in patients with juvenile myoclonic epilepsy. Neurology 2008;71:788-794 
  25. Rossi J, Cavallieri F, Giovannini G, Benuzzi F, Ballotta D, Vaudano AE, et al. Can disruption of basal ganglia-thalamocortical circuit in Wilson disease be associated with juvenile myoclonic epilepsy phenotype? Brain Sci 2022;12:553 
  26. Tae WS, Hong SB, Joo EY, Han SJ, Cho JW, Seo DW, et al. Structural brain abnormalities in juvenile myoclonic epilepsy patients: volumetry and voxel-based morphometry. Korean J Radiol 2006;7:162-172 
  27. Lin K, de Araujo Filho GM, Pascalicchio TF, Silva I, Tudesco IS, Guaranha MS, et al. Hippocampal atrophy and memory dysfunction in patients with juvenile myoclonic epilepsy. Epilepsy Behav 2013;29:247-251 
  28. Zhang J, Wu D, Yang H, Lu H, Ji Y, Liu H, et al. Correlations between structural brain abnormalities, cognition and electroclinical characteristics in patients with juvenile myoclonic epilepsy. Front Neurol 2022;13:883078 
  29. Mory SB, Betting LE, Fernandes PT, Lopes-Cendes I, Guerreiro MM, Guerreiro CA, et al. Structural abnormalities of the thalamus in juvenile myoclonic epilepsy. Epilepsy Behav 2011;21:407-411 
  30. Kim JH, Kim JB, Seo WK, Suh SI, Koh SB. Volumetric and shape analysis of thalamus in idiopathic generalized epilepsy. J Neurol 2013;260:1846-1854 
  31. Ur Ozcelik E, Kurt E, S,irin NG, Eryurek K, Ulas,oglu Yildiz C, Hari E, et al. Functional connectivity disturbances of ascending reticular activating system and posterior thalamus in juvenile myoclonic epilepsy in relation with photosensitivity: a resting-state fMRI study. Epilepsy Res 2021;171:106569 
  32. O'Muircheartaigh J, Vollmar C, Barker GJ, Kumari V, Symms MR, Thompson P, et al. Focal structural changes and cognitive dysfunction in juvenile myoclonic epilepsy. Neurology 2011;76:34-40 
  33. Kim SH, Lim SC, Kim W, Kwon OH, Jeon S, Lee JM, et al. Extrafrontal structural changes in juvenile myoclonic epilepsy: a topographic analysis of combined structural and microstructural brain imaging. Seizure 2015;30:124-131 
  34. Gilsoul M, Grisar T, Delgado-Escueta AV, de Nijs L, Lakaye B. Subtle brain developmental abnormalities in the pathogenesis of juvenile myoclonic epilepsy. Front Cell Neurosci 2019;13:433 
  35. Gong J, Chang X, Jiang S, Klugah-Brown B, Tan S, Yao D, et al. Microstructural alterations of white matter in juvenile myoclonic epilepsy. Epilepsy Res 2017;135:1-8 
  36. van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res 2017;77:e104-e107 
  37. Lambin P, Leijenaar RTH, Deist TM, Peerlings J, de Jong EEC, van Timmeren J, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 2017;14:749-762 
  38. Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ 2015;350:g7594 
  39. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 2002;16:321-357 
  40. Lundberg SM, Lee SI. A unified approach to interpreting model predictions. proceedings.neurips.cc Web site. https://proceedings.neurips.cc/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html. Accessed March 22, 2022 
  41. Geithner J, Schneider F, Wang Z, Berneiser J, Herzer R, Kessler C, et al. Predictors for long-term seizure outcome in juvenile myoclonic epilepsy: 25-63 years of follow-up. Epilepsia 2012;53:1379-1386 
  42. Betting LE, Mory SB, Li LM, Lopes-Cendes I, Guerreiro MM, Guerreiro CA, et al. Voxel-based morphometry in patients with idiopathic generalized epilepsies. Neuroimage 2006;32:498-502 
  43. Liu M, Concha L, Beaulieu C, Gross DW. Distinct white matter abnormalities in different idiopathic generalized epilepsy syndromes. Epilepsia 2011;52:2267-2275 
  44. Woermann FG, Free SL, Koepp MJ, Sisodiya SM, Duncan JS. Abnormal cerebral structure in juvenile myoclonic epilepsy demonstrated with voxel-based analysis of MRI. Brain 1999;122(Pt 11):2101-2108 
  45. Alhusaini S, Ronan L, Scanlon C, Whelan CD, Doherty CP, Delanty N, et al. Regional increase of cerebral cortex thickness in juvenile myoclonic epilepsy. Epilepsia 2013;54:e138-e141 
  46. Wandschneider B, Hong SJ, Bernhardt BC, Fadaie F, Vollmar C, Koepp MJ, et al. Developmental MRI markers cosegregate juvenile patients with myoclonic epilepsy and their healthy siblings. Neurology 2019;93:e1272-e1280 
  47. Kim JH, Suh SI, Park SY, Seo WK, Koh I, Koh SB, et al. Microstructural white matter abnormality and frontal cognitive dysfunctions in juvenile myoclonic epilepsy. Epilepsia 2012;53:1371-1378 
  48. Si X, Zhang X, Zhou Y, Sun Y, Jin W, Yin S, et al. Automated detection of juvenile myoclonic epilepsy using CNN based transfer learning in diffusion MRI. Annu Int Conf IEEE Eng Med Biol Soc 2020;2020:1679-1682 
  49. Johns MW. A new method for measuring daytime sleepiness: the Epworth sleepiness scale. Sleep 1991;14:540-545 
  50. Landvogt C, Buchholz HG, Bernedo V, Schreckenberger M, Werhahn KJ. Alteration of dopamine D2/D3 receptor binding in patients with juvenile myoclonic epilepsy. Epilepsia 2010;51:1699-1706 
  51. Lee HJ, Seo SA, Lee BI, Kim SE, Park KM. Thalamic nuclei volumes and network in juvenile myoclonic epilepsy. Acta Neurol Scand 2020;141:271-278 
  52. Renganathan R, Delanty N. Juvenile myoclonic epilepsy: under-appreciated and under-diagnosed. Postgrad Med J 2003;79:78-80