On The Use of Machine Learning Algorithms to Classify Focal Cortical Dysplasia on MRI

• João Guilherme Pereira USP
• Matheus de Freitas Oliveira Baffa USP
• Fabrício Henrique Simozo USP
• Luiz Otavio Murta Junior USP
• Joaquim Cezar Felipe USP

DOI: https://doi.org/10.5753/sbcas.2021.16063

Abstract

Refractory epilepsy is a condition characterized by epileptic seizure occurrence which cannot be controlled with antiepileptic drugs. This condition is associated with an excessive neuronal discharge produced by a group of neurons in a certain epileptogenic zone. Focal Cortical Dysplasia (FCD), usually found in these zones, was detected as one of the main causes of refractory epilepsy. In these cases, surgical intervention is necessary to minimize or eliminate the seizure occurrences. However, surgical treatment is only indicated in cases where there is complete certainty of the FCD. In order to assist neurosurgeons to detect precisely these regions, this paper aims to develop a classification method to detect FCD on MRI based on morphological and textural features from a voxel-level perspective. Multiple classifiers were tested throughout the extracted features, the best results achieved an accuracy of 91.76% using a Deep Neural Network classifier and 96.15% with J48 Decision Tree. The set of evaluating metrics showed that the results are promising.

References

Adler, S., Wagstyl, K., Gunny, R., Ronan, L., Carmichael, D., Cross, J. H., Fletcher, P. C., and Baldeweg, T. (2017). Novel surface features for automated detection of focal cortical dysplasias in paediatric epilepsy. NeuroImage: Clinical, 14:18–27.

Antel, S. B., Collins, D. L., Bernasconi, N., Andermann, F., Shinghal, R., Kearney, R. E., Arnold, D. L., and Bernasconi, A. (2003). Automated detection of focal cortical dysplasia lesions using computational models of their mri characteristics and texture analysis. Neuroimage, 19(4):1748–1759.

Besson, P., Colliot, O., Evans, A., and Bernasconi, A. (2008). Automatic detection of subtle focal cortical dysplasia using surface-based features on mri. In 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pages 1633– 1636. IEEE.

Colombo, N., Tassi, L., Galli, C., Citterio, A., Russo, G. L., Scialfa, G., and Spreaco, R. (2003). Focal cortical dysplasias: Mr imaging, histopathologic, and clinical correlations in surgically treated patients with epilepsy. American Journal of Neuroradiology, 24(4):724–733.

Conci, A., Azevedo, E., and Leta, F. R. (2008). Computação gráca–teoria e prática,[v.2]. Rio de Janeiro.

Dev, K. B., Jogi, P. S., Niyas, S., Vinayagamani, S., Kesavadas, C., and Rajan, J. (2019). Automatic detection and localization of focal cortical dysplasia lesions in mri using fully convolutional neural network. Biomedical Signal Processing and Control, 52:218–225.

Fisher, R. S., Acevedo, C., Arzimanoglou, A., Bogacz, A., Cross, J. H., Elger, C. E., Engel Jr, J., Forsgren, L., French, J. A., Glynn, M., et al. (2014). Ilae ofcial report: a practical clinical denition of epilepsy. Epilepsia, 55(4):475–482.

French, J. A. (2007). Refractory epilepsy: clinical overview. Epilepsia, 48:3–7.

Gallucci Neto, J. and Marchetti, R. L. (2005). Aspectos epidemiológicos e relevância dos transtornos mentais associados à epilepsia. Brazilian Journal of Psychiatry, 27(4):323–328.

Hong, S.-J., Kim, H., Schrader, D., Bernasconi, N., Bernhardt, B. C., and Bernasconi, A. (2014). Automated detection of cortical dysplasia type ii in mri-negative epilepsy. Neurology, 83(1):48–55.

Jin, B., Krishnan, B., Adler, S., Wagstyl, K., Hu, W., Jones, S., Najm, I., Alexopoulos, A., Zhang, K., Zhang, J., et al. (2018). Automated detection of focal cortical dysplasia type ii with surface-based magnetic resonance imaging postprocessing and machine learning. Epilepsia, 59(5):982–992.

Kwan, P. and Brodie, M. J. (2000). Early identication of refractory epilepsy. New England Journal of Medicine, 342(5):314–319.

Li, L. and Hurford, R. (2020). Journal club: The risk of new-onset epilepsy and refractory epilepsy in older adult stroke survivors. Neurology.

Loyek, C., Woermann, F. G., and Nattkemper, T. W. (2008). Detection of focal cortical dysplasia lesions in mri using textural features. In Bildverarbeitung für die Medizin 2008, pages 432–436. Springer.

Rosenow, F. and Lüders, H. (2001). Presurgical evaluation of epilepsy. Brain, 124(9):1683–1700.

Roy, H., Lippé, S., Lussier, F., Sauerwein, H. C., Lortie, A., Lacroix, J., and Lassonde, M. (2011). Developmental outcome after a single episode of status epilepticus. Epilepsy & Behavior, 21(4):430–436.

Sheppard, E. and Lippé, S. (2012). Cognitive outcome of status epilepticus in children. Epilepsy research and treatment, 2012.

Simozo, F. H. (2018). Caracterização e identicação de displasias corticais focais em pacientes com epilepsia refratária através de análise de imagens estruturais de ressonância magnética nuclear. PhD thesis, Universidade de São Paulo.

Taylor, D., Falconer, M., Bruton, C., and Corsellis, J. (1971). Focal dysplasia of the cerebral cortex in epilepsy. Journal of Neurology, Neurosurgery & Psychiatry, 34(4):369– 387.

Wang, H., Ahmed, S. N., and Mandal, M. (2020). Automated detection of focal cortical dysplasia using a deep convolutional neural network. Computerized Medical Imaging and Graphics, 79:101662.

WHO, W. H. O. (2019). Oms destaca escassez de tratamento para epilepsia em países de baixa renda. Available at: <https://www.paho.org/bra/index.php?option=comcontentview=articleid=5972>. Accessed in: 15 jul. 2020.