Data mining MR image features of select structures for lateralization of mesial temporal lobe epilepsy (original) (raw)
Related papers
TURKISH JOURNAL OF MEDICAL SCIENCES, 2020
Background/aim: In temporal lobe epilepsy (TLE), brain positron emission tomography (PET) performed with F-18 fluorodeoxyglucose (FDG) is commonly used for lateralization of the epileptogenic temporal lobe. In this study, we aimed to evaluate the success of quantitative analysis of brain FDG PET images using data mining methods in the lateralization of the epileptogenic temporal lobe. Materials and methods: Presurgical interictal brain FDG PET images of 49 adult mesial TLE patients with a minimum of 2 years of postsurgical follow-up and Engel I outcomes were retrospectively analyzed. Asymmetry indices were calculated from PET images from the mesial temporal lobe and its contiguous structures. The J48 and the logistic model tree (LMT) data mining algorithms were used to find classification rules for the lateralization of the epileptogenic temporal lobe. The classification results obtained by these rules were compared with the physicians' visual readings and the findings of single-patient statistical parametric mapping (SPM) analyses in a test set of 18 patients. An additional 5-fold cross-validation was applied to the data to overcome the limitation of a relatively small sample size. Results: In the lateralization of 18 patients in the test set, J48 and LMT methods were successful in 16 (89%) and 17 (94%) patients, respectively. The visual consensus readings were correct in all patients and SPM results were correct in 16 patients. The 5-fold crossvalidation method resulted in a mean correct lateralization ratio of 96% (47/49) for the LMT algorithm. This ratio was 88% (43 / 49) for the J48 algorithm. Conclusion: Lateralization of the epileptogenic temporal lobe with data mining methods using regional metabolic asymmetry values obtained from interictal brain FDG PET images in mesial TLE patients is highly accurate. The application of data mining can contribute to the reader in the process of visual evaluation of FDG PET images of the brain.
NeuroImage, 2006
Classification approaches for neurological diseases tend to concentrate on specific structures such as the hippocampus (HC). The hypothesis for the novel methodology presented in this work is that pathologies will impact large tissue areas with detectable variations of T1-weighted MR signal intensity and registration metrics. The technique is applied to lateralization of seizure focus in 127 patients with intractable temporal lobe epilepsy (TLE), in which the site of seizure onset was determined by comprehensive evaluation (69 with left MTL seizure focus (SF) (group "L") and 58 with right SF (group "R")). The method analyses large, non-specific Volumes of Interest (VOI) centered on the left and right medial temporal lobes (MTL) (55 x 82 x 80 voxels) in pre-processed scans aligned in stereotaxic space. Extracted VOIs are linearly and nonlinearly registered to a reference target image. Principal Components Analyses of (i) the normalized intensity and (ii) the trace...
NeuroImage: Clinical, 2021
Artificial intelligence has recently gained popularity across different medical fields to aid in the detection of diseases based on pathology samples or medical imaging findings. Brain magnetic resonance imaging (MRI) is a key assessment tool for patients with temporal lobe epilepsy (TLE). The role of machine learning and artificial intelligence to increase detection of brain abnormalities in TLE remains inconclusive. We used support vector machine (SV) and deep learning (DL) models based on region of interest (ROI-based) structural (n = 336) and diffusion (n = 863) brain MRI data from patients with TLE with ("lesional") and without ("non-lesional") radiographic features suggestive of underlying hippocampal sclerosis from the multinational (multi-center) ENIGMA-Epilepsy consortium. Our data showed that models to identify TLE performed better or similar (68-75%) compared to models to lateralize the side of TLE (56-73%, except structural-based) based on diffusion data with the opposite pattern seen for structural data (67-75% to diagnose vs. 83% to lateralize). In other aspects, structural and diffusion-based models showed similar classification accuracies. Our classification models for patients with hippocampal sclerosis were more accurate (68-76%) than models that stratified non-lesional patients (53-62%). Overall, SV and DL models performed similarly with several instances in which SV mildly outperformed DL. We discuss the relative performance of these models with ROI-level data and the implications for future applications of machine learning and artificial intelligence in epilepsy care.
AUTOMATICALLY DETECTING TEMPORAL LOBE EPILEPSY USING CORTICAL THICKNESS MEASURES
Several studies have shown that the anatomic abnormality in patients with chronic mesial temporal lobe epilepsy (MTLE) exist outside of the bounds of the mesial temporal lobe, including the entire cerebral cortex. The purpose of this work is twofold: first to separate patients with temporal lobe epilepsy from controls using just the measures of cortical thickness and second to automatically select the main regions that suffer significant thinning. For this, we developed a robust framework, based on established algorithms. This framework includes: an automated method for accurately measuring the thickness of the cerebral cortex across the entire brain; employing the feature selection algorithm Relief, which selects relevant features using a statistical method; and the 1-nearest neighbor and decision tree as classifiers. We used high resolution MRI scans from 174 healthy controls and 123 MTLE patients. The results show accuracy values up to 100%, indicating that the cortical thickness with traditional classifiers are well-suited to detect MTLE.
Machine Learning Approach for the Outcome Prediction of Temporal Lobe Epilepsy Surgery
PLoS ONE, 2013
Epilepsy surgery is effective in reducing both the number and frequency of seizures, particularly in temporal lobe epilepsy (TLE). Nevertheless, a significant proportion of these patients continue suffering seizures after surgery. Here we used a machine learning approach to predict the outcome of epilepsy surgery based on supervised classification data mining taking into account not only the common clinical variables, but also pathological and neuropsychological evaluations. We have generated models capable of predicting whether a patient with TLE secondary to hippocampal sclerosis will fully recover from epilepsy or not. The machine learning analysis revealed that outcome could be predicted with an estimated accuracy of almost 90% using some clinical and neuropsychological features. Importantly, not all the features were needed to perform the prediction; some of them proved to be irrelevant to the prognosis. Personality style was found to be one of the key features to predict the outcome. Although we examined relatively few cases, findings were verified across all data, showing that the machine learning approach described in the present study may be a powerful method. Since neuropsychological assessment of epileptic patients is a standard protocol in the pre-surgical evaluation, we propose to include these specific psychological tests and machine learning tools to improve the selection of candidates for epilepsy surgery.
Hippocampus Volume and Texture Analysis for Temporal Lobe Epilepsy
2006
It has been previously shown that intensity and volume features of the hippocampus from MR images of the brain are useful in detecting the abnormality and consequently candidacy of the hippocampus for temporal lobe epilepsy (TLE) surgery. In this paper, we have studied and compared volume and texture features of hippocampus for TLE lateralization. Volume and some features describing the intensity non-uniformities are used. We use manual segmentation of the hippocampi from T1 weighted images and map them to the FLAIR images. Wavelet features as well as mean and variance of the hippocampus intensities of the FLAIR slices are used as texture features. A dataset of 55 patients with 28 right and 27 left abnormal sides was used in the experiments. Experimental results show that the volume and intensity features are useful in determining the abnormal side
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2014
Surgical treatment is suggested for seizure control in medically intractable epilepsy patients. Detailed pre-surgical evaluation and lateralization using Magnetic Resonance Images (MRI) is expected to result in a successful surgical outcome. In this study, an optimized pattern recognition approach is proposed for lateralization of mesial Temporal Lobe Epilepsy (mTLE) patients using asymmetry of imaging indices of hippocampus. T1-weighted and Fluid-Attenuated Inversion Recovery (FLAIR) images of 76 symptomatic mTLE patients are considered. First, hippocampus is segmented using automatic and manual segmentation methods; then, volumetric and intensity features are extracted from the MR images. A nonlinear Support Vector Machine (SVM) with optimized Gaussian Radial Basis Function (GRBF) kernel is used to classify the imaging features. Using leave-one-out cross validation, this method results in a correct lateralization rate of 82%, a probability of detection for the left side of 0.90 (w...
Epilepsy & behavior : E&B, 2018
In this study, we employed a kernel support vector machine to predict epilepsy localization and lateralization for patients with a diagnosis of epilepsy (n = 228). We assessed the accuracy to which indices of verbal memory, visual memory, verbal fluency, and naming would localize and lateralize seizure focus in comparison to standard electroencephalogram (EEG). Classification accuracy was defined as models that produced the least cross-validated error (CVϵ). In addition, we assessed whether the inclusion of norm-based standard scores, demographics, and emotional functioning data would reduce CVϵ. Finally, we obtained class probabilities (i.e., the probability of a particular classification for each case) and produced receiver operating characteristic (ROC) curves for the primary analyses. We obtained the least error assessing localization data with the Gaussian radial basis kernel function (RBF; support vectors = 157, CVϵ = 0.22). There was no overlap between the localization and la...
2010
Brain structural volumes can be used for automatically classifying subjects into categories like controls and patients. We aimed to automatically separate patients with temporal lobe epilepsy (TLE) with and without hippocampal atrophy on MRI, pTLE and nTLE, from controls, and determine the epileptogenic side. In the proposed framework 83 brain structure volumes are identified using multi-atlas segmentation. We then use structure selection using a divergence measure and classification based on structural volumes, as well as morphological similarities using SVM. A spectral analysis step is used to convert the pairwise measures of similarity between subjects into per-subject features. Up to 96% of pTLE patients were correctly separated from controls using 14 structural brain volumes. The classification method based on spectral analysis was 91% accurate at separating nTLE patients from controls. Right and left hippocampus were sufficient for the lateralization of the seizure focus in the pTLE group and achieved 100% accuracy.