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

2021 ◽  
Author(s):  
João Guilherme Pereira ◽  
Matheus de Freitas Oliveira Baffa ◽  
Fabrício Henrique Simozo ◽  
Luiz Otavio Murta Junior ◽  
Joaquim Cezar Felipe
Keyword(s):  
Deep Neural Network ◽  
Surgical Intervention ◽  
Refractory Epilepsy ◽  
Focal Cortical Dysplasia ◽  
Cortical Dysplasia ◽  
Machine Learning Algorithms ◽  
Textural Features ◽  
Epileptogenic Zone ◽  
Neural Network Classifier ◽  
Multiple Classifiers

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.

Surgical treatment of intractable epilepsy associated with focal cortical dysplasia

2008 ◽  
Vol 25 (3) ◽  
pp. E6 ◽  
Author(s):  
Roberto Jose Diaz ◽  
Elisabeth M. S. Sherman ◽  
Walter J. Hader
Keyword(s):  
Refractory Epilepsy ◽  
Functional Neuroimaging ◽  
Focal Cortical Dysplasia ◽  
Intractable Epilepsy ◽  
Cortical Dysplasia ◽  
Complete Resection ◽  
Epileptogenic Zone ◽  
Malformations Of Cortical Development ◽  
Cortical Dysplasias

Focal cortical dysplasias (FCDs) are congenital malformations of cortical development that are a frequent cause of refractory epilepsy in both children and adults. With advances in structural and functional neuroimaging, these lesions are increasingly being identified as a cause of intractable epilepsy in patients undergoing surgical management for intractable epilepsy. Comprehensive histological classification of FCDs with the establishment of uniform terminology and reproducible pathological features has aided in our understanding of FCDs as an epilepsy substrate. Complete resection of FCDs and the associated epileptogenic zone can result in a good surgical outcome in the majority of patients.

Multinodular and vacuolating neuronal tumor associated with focal cortical dysplasia in a child with refractory epilepsy: a case report and brief review of literature

2020 ◽  
Vol 36 (7) ◽  
pp. 1557-1561 ◽  
Author(s):  
Lídia Nunes Dias ◽  
Santiago Candela-Cantó ◽  
Cristina Jou ◽  
Javier Aparicio Calvo ◽  
Sergio García-García ◽  
...  
Keyword(s):  
Case Report ◽  
Refractory Epilepsy ◽  
Focal Cortical Dysplasia ◽  
Cortical Dysplasia ◽  
Review Of Literature ◽  
Neuronal Tumor

Enhanced MR conspicuity of Type IIb focal cortical dysplasia by T1WI with CHESS: Two case reports

2020 ◽  
pp. 10.1212/CPJ.0000000000000987
Author(s):  
Midori Kusama ◽  
Noriko Sato ◽  
Zen-ichi Tanei ◽  
Yukio Kimura ◽  
Masaki Iwasaki ◽  
...  
Keyword(s):  
Clinical Practice ◽  
Chemical Shift ◽  
Refractory Epilepsy ◽  
Focal Cortical Dysplasia ◽  
Case Reports ◽  
Cortical Dysplasia ◽  
Fat Suppression ◽  
Developmental Anomaly ◽  
Mri Findings ◽  
Mr Sequences

Focal cortical dysplasia (FCD) is a congenital developmental anomaly that is one of the leading causes of refractory epilepsy. MRI is an essential examination and T1WI, T2WI, and FLAIR images are commonly used MR sequences for delineating FCD.1 However, these MRI findings are often insufficiently clear. We experienced two FCD cases that were much better visualized by using T1WI with chemical shift selective (CHESS) than with T2WI and FLAIR images. CHESS is the most frequently used fat suppression pulse in clinical practice. We report two cases in which CHESS clearly demonstrated FCD, and compare the cases' pathology and MRI findings.

scholarly journals Distinguishing Focal Cortical Dysplasia From Glioneuronal Tumors in Patients With Epilepsy by Machine Learning

2020 ◽  
Vol 11 ◽  
Author(s):  
Yi Guo ◽  
Yushan Liu ◽  
Wenjie Ming ◽  
Zhongjin Wang ◽  
Junming Zhu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Focal Cortical Dysplasia ◽  
Cortical Dysplasia ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Supervised Machine Learning ◽  
Seizure Onset ◽  
Glioneuronal Tumors ◽  
Patients With Epilepsy

Purpose: We are aiming to build a supervised machine learning-based classifier, in order to preoperatively distinguish focal cortical dysplasia (FCD) from glioneuronal tumors (GNTs) in patients with epilepsy.Methods: This retrospective study was comprised of 96 patients who underwent epilepsy surgery, with the final neuropathologic diagnosis of either an FCD or GNTs. Seven classical machine learning algorithms (i.e., Random Forest, SVM, Decision Tree, Logistic Regression, XGBoost, LightGBM, and CatBoost) were employed and trained by our dataset to get the classification model. Ten features [i.e., Gender, Past history, Age at seizure onset, Course of disease, Seizure type, Seizure frequency, Scalp EEG biomarkers, MRI features, Lesion location, Number of antiepileptic drug (AEDs)] were analyzed in our study.Results: We enrolled 56 patients with FCD and 40 patients with GNTs, which included 29 with gangliogliomas (GGs) and 11 with dysembryoplasic neuroepithelial tumors (DNTs). Our study demonstrated that the Random Forest-based machine learning model offered the best predictive performance on distinguishing the diagnosis of FCD from GNTs, with an F1-score of 0.9180 and AUC value of 0.9340. Furthermore, the most discriminative factor between FCD and GNTs was the feature “age at seizure onset” with the Chi-square value of 1,213.0, suggesting that patients who had a younger age at seizure onset were more likely to be diagnosed as FCD.Conclusion: The Random Forest-based machine learning classifier can accurately differentiate FCD from GNTs in patients with epilepsy before surgery. This might lead to improved clinician confidence in appropriate surgical planning and treatment outcomes.

scholarly journals Induced pluripotent stem cells from patients with focal cortical dysplasia and refractory epilepsy

2017 ◽  
Vol 15 (4) ◽  
pp. 2049-2056 ◽  
Author(s):  
Daniel Rodrigo Marinowic ◽  
Fernanda Majolo ◽  
Alessandra Deise Sebben ◽  
Vinicius Duval Da Silva ◽  
Tiago Giuliani Lopes ◽  
...  
Keyword(s):  
Stem Cells ◽  
Induced Pluripotent Stem Cells ◽  
Pluripotent Stem Cells ◽  
Refractory Epilepsy ◽  
Focal Cortical Dysplasia ◽  
Cortical Dysplasia ◽  
Induced Pluripotent

scholarly journals Validating EEG, MEG and combined MEG and EEG beamforming for an estimation of the epileptogenic zone in focal cortical dysplasia

2021 ◽  
Author(s):  
Frank Neugebauer ◽  
Marios Antonakakis ◽  
Kanjana Unnwongse ◽  
Yaroslav Parpaley ◽  
Jörg Wellmer ◽  
...  
Keyword(s):  
Regularization Parameter ◽  
Focal Cortical Dysplasia ◽  
Estimation Method ◽  
Cortical Dysplasia ◽  
Source Analysis ◽  
Seizure Freedom ◽  
Epileptogenic Zone ◽  
Scanning Method ◽  
Eeg Source Analysis ◽  
Skull Conductivity

AbstractMEG and EEG source analysis is frequently used for the presurgical evaluation of pharma-coresistant epilepsy patients. The source localization of the epileptogenic zone depends, among other aspects, on the selected inverse and forward approaches and their respective parameter choices. In this validation study, we compare for the inverse problem the standard dipole scanning method with two beamformer approaches and we investigate the influence of the covariance estimation method and the strength of regularization on the localization performance for EEG, MEG and combined EEG and MEG. For forward modeling, we investigate the difference between calibrated six-compartment and standard three-compartment head modeling. In a retrospective study of two patients with focal epilepsy due to focal cortical dysplasia type IIb and seizure-freedom following lesionectomy or radiofrequency-guided thermocoagulation, we used the distance of the localization of interictal epileptic spikes to the resection cavity resp. rediofrequency lesion as reference for good localization. We found that beamformer localization can be sensitive to the choice of the regularization parameter, which has to be individually optimized. Estimation of the covariance matrix with averaged spike data yielded more robust results across the modalities. MEG was the dominant modality and provided a good localization in one case, while it was EEG for the other. When combining the modalities, the good results of the dominant modality were mostly not spoiled by the weaker modality. For appropriate regularization parameter choices, the beamformer localized better than the standard dipole scan. Compared to the importance of an appropriate regularization, the sensitivity of the localization to the head modeling was smaller, due to similar skull conductivity modeling and the fixed source space without orientation constraint.

Sign in / Sign up

Export Citation Format

Share Document