MR-based neurological disease classification methodology: Application to lateralization of seizure focus in temporal lobe epilepsy

Detection of Lesions Underlying Intractable Epilepsy on T1-Weighted MRI as an Outlier Detection Problem

Pattern recognition methods, such as computer aided diagnosis (CAD) systems, can help clinicians in their diagnosis by marking abnormal regions in an image. We propose a machine learning system based on a one-class support vector machine (OC-SVM) classifier for the detection of abnormalities in magnetic resonance images (MRI) applied to patients with intractable epilepsy. The system learns the features associated with healthy control subjects, allowing a voxelwise assessment of the deviation of a test subject pattern from the learned patterns. While any number of various features can be chosen and learned, here we focus on two texture parameters capturing image patterns associated with epileptogenic lesions on T1-weighted brain MRI e.g. heterotopia and blurred junction between the grey and white matter. The CAD output consists of patient specific 3D maps locating clusters of suspicious voxels ranked by size and degree of deviation from control patterns. System performance was evaluated using realistic simulations of challenging detection tasks as well as clinical data of 77 healthy control subjects and of eleven patients (13 lesions). It was compared to that of a mass univariate statistical parametric mapping (SPM) single subject analysis based on the same set of features. For all simulations, OC-SVM yielded significantly higher values of the area under the ROC curve (AUC) and higher sensitivity at low false positive rate. For the clinical data, both OC-SVM and SPM successfully detected 100% of the lesions in the MRI positive cases (3/13). For the MRI negative cases (10/13), OC-SVM detected 7/10 lesions and SPM analysis detected 5/10 lesions. In all experiments, OC-SVM produced fewer false positive detections than SPM. OC-SVM may be a versatile system for unbiased lesion detection.

Predicting the laterality of temporal lobe epilepsy from PET, MRI, and DTI: A multimodal study

Pre-surgical evaluation of patients with temporal lobe epilepsy (TLE) relies on information obtained from multiple neuroimaging modalities. The relationship between modalities and their combined power in predicting the seizure focus is currently unknown. We investigated asymmetries from three different modalities, PET (glucose metabolism), MRI (cortical thickness), and diffusion tensor imaging (DTI; white matter anisotropy) in 28 left and 30 right TLE patients (LTLE and RTLE). Stepwise logistic regression models were built from each modality separately and from all three combined, while bootstrapped methods and split-sample validation verified the robustness of predictions. Among all multimodal asymmetries, three PET asymmetries formed the best predictive model (100% success in full sample, >95% success in split-sample validation). The combinations of PET with other modalities did not perform better than PET alone. Probabilistic classifications were obtained for new clinical cases, which showed correct lateralization for 7/7 new TLE patients (100%) and for 4/5 operated patients with discordant or non-informative PET reports (80%). Metabolism showed closer relationship with white matter in LTLE and closer relationship with gray matter in RTLE. Our data suggest that metabolism is a powerful modality that can predict seizure laterality with high accuracy, and offers high value for automated predictive models. The side of epileptogenic focus can affect the relationship of metabolism with brain structure. The data and tools necessary to obtain classifications for new TLE patients are made publicly available.

Magnetic resonance imaging pattern learning in temporal lobe epilepsy: classification and prognostics

OBJECTIVE

In temporal lobe epilepsy (TLE), although hippocampal atrophy lateralizes the focus, the value of magnetic resonance imaging (MRI) to predict postsurgical outcome is rather modest. Prediction solely based on the hippocampus may be hampered by widespread mesiotemporal structural damage shown by advanced imaging. Increasingly complex and high-dimensional representation of MRI metrics motivates a shift to machine learning to establish objective, data-driven criteria for pathogenic processes and prognosis.

METHODS

We applied clustering to 114 consecutive unilateral TLE patients using 1.5T MRI profiles derived from surface morphology of hippocampus, amygdala, and entorhinal cortex. To evaluate the diagnostic validity of the classification, we assessed its yield to predict outcome in 79 surgically treated patients. Reproducibility of outcome prediction was assessed in an independent cohort of 27 patients evaluated on 3.0T MRI.

RESULTS

Four similarly sized classes partitioned our cohort; in all, alterations spanned over the 3 mesiotemporal structures. Compared to 46 controls, TLE-I showed marked bilateral atrophy; in TLE-II atrophy was ipsilateral; TLE-III showed mild bilateral atrophy; whereas TLE-IV showed hypertrophy. Classes differed with regard to histopathology and freedom from seizures. Classwise surface-based classifiers accurately predicted outcome in 92 ± 1% of patients, outperforming conventional volumetry. Predictors of relapse were distributed bilaterally across structures. Prediction accuracy was similarly high in the independent cohort (96%), supporting generalizability.

INTERPRETATION

We provide a novel description of individual variability across the TLE spectrum. Class membership was associated with distinct patterns of damage and outcome predictors that did not spatially overlap, emphasizing the ability of machine learning to disentangle the differential contribution of morphology to patient phenotypes, ultimately refining the prognosis of epilepsy surgery.

Quantitative analysis of structural neuroimaging of mesial temporal lobe epilepsy

Mesial temporal lobe epilepsy (MTLE) is the most common of the surgically remediable drug-resistant epilepsies. MRI is the primary diagnostic tool to detect anatomical abnormalities and, when combined with EEG, can more accurately identify an epileptogenic lesion, which is often hippocampal sclerosis in cases of MTLE. As structural imaging technology has advanced the surgical treatment of MTLE and other lesional epilepsies, so too have the analysis techniques that are used to measure different structural attributes of the brain. These techniques, which are reviewed here and have been used chiefly in basic research of epilepsy and in studies of MTLE, have identified different types and the extent of anatomical abnormalities that can extend beyond the affected hippocampus. These results suggest that structural imaging and sophisticated imaging analysis could provide important information to identify networks capable of generating spontaneous seizures and ultimately help guide surgical therapy that improves postsurgical seizure-freedom outcomes.

Classification and lateralization of temporal lobe epilepsies with and without hippocampal atrophy based on whole-brain automatic MRI segmentation

Brain images contain information suitable for automatically sorting subjects into categories such as healthy controls and patients. We sought to identify morphometric criteria for distinguishing controls (n = 28) from patients with unilateral temporal lobe epilepsy (TLE), 60 with and 20 without hippocampal atrophy (TLE-HA and TLE-N, respectively), and for determining the presumed side of seizure onset. The framework employs multi-atlas segmentation to estimate the volumes of 83 brain structures. A kernel-based separability criterion was then used to identify structures whose volumes discriminate between the groups. Next, we applied support vector machines (SVM) to the selected set for classification on the basis of volumes. We also computed pairwise similarities between all subjects and used spectral analysis to convert these into per-subject features. SVM was again applied to these feature data. After training on a subgroup, all TLE-HA patients were correctly distinguished from controls, achieving an accuracy of 96 ± 2% in both classification schemes. For TLE-N patients, the accuracy was 86 ± 2% based on structural volumes and 91 ± 3% using spectral analysis. Structures discriminating between patients and controls were mainly localized ipsilaterally to the presumed seizure focus. For the TLE-HA group, they were mainly in the temporal lobe; for the TLE-N group they included orbitofrontal regions, as well as the ipsilateral substantia nigra. Correct lateralization of the presumed seizure onset zone was achieved using hippocampi and parahippocampal gyri in all TLE-HA patients using either classification scheme; in the TLE-N patients, lateralization was accurate based on structural volumes in 86 ± 4%, and in 94 ± 4% with the spectral analysis approach. Unilateral TLE has imaging features that can be identified automatically, even when they are invisible to human experts. Such morphometric image features may serve as classification and lateralization criteria. The technique also detects unsuspected distinguishing features like the substantia nigra, warranting further study.

Automated computer differential classification in Parkinsonian Syndromes via pattern analysis on MRI

RATIONALE AND OBJECTIVES

Reported error rates for initial clinical diagnosis of idiopathic Parkinson's disease (IPD) against other Parkinson Plus Syndromes (PPS) can reach up to 35%. Reducing this initial error rate is an important research goal. We evaluated the ability of an automated technique, based on structural, cross-sectional T1-weighted (T1w) magnetic resonance imaging, to perform differential classification of IPD patients versus those with either progressive supranuclear palsy (PSP) or multiple systems atrophy (MSA).

MATERIALS AND METHODS

A total of 181 subjects were included in this retrospective study: 149 healthy controls, 16 IPD patients, and 16 patients diagnosed with either probable PSP (n = 8) or MSA (n = 8). Cross-sectional T1w magnetic resonance imagers were acquired and subsequently corrected, scaled, resampled, and aligned within a common referential space. Tissue composition and deformation features in the hindbrain region were then automatically extracted. Classification of patients was performed using a support vector machine with least-squares optimization within a multidimensional composition/deformation feature space built from the healthy subjects' data. Leave-one-out classification was used to avoid over-determination.

RESULTS

There were no age difference between groups. The automated system obtained 91% accuracy (agreement with long-term clinical follow-up), 88% specificity, and 93% sensitivity.

CONCLUSION

These results demonstrate that a classification approach based on quantitative parameters of three-dimensional hindbrain morphology extracted automatically from T1w magnetic resonance imaging has the potential to assist in the differential diagnosis of IPD versus PSP and MSA with high accuracy, therefore reducing the initial clinical error rate.

Amnestic MCI future clinical status prediction using baseline MRI features

Amnestic mild cognitive impairment (aMCI) individuals are known to be at risk for progression to clinically probable Alzheimer's disease (AD). The objective of this work is to measure the accuracy of an automated classification technique based on clinical-quality, single time-point structural magnetic resonance imaging (MRI) scans for the retrospective prediction of future clinical status in aMCI. Thirty-one aMCI research subjects were followed with annual clinical reassessment after baseline MRI. Twenty subjects progressed to probable AD within an average 2.2 (1.4) years [mean age 76.6 (4.7) years, MMSE 27.1 (2.3)], while 11 remained non-demented on average 5.6 (2.6) years after baseline [mean age 73.3 (7.2) years, MMSE 28.2 (1.8)]. Leave-one-out classification was performed within a multidimensional MRI feature space built from intensity and local volume estimate data of a reference group of 75 probable AD and 75 age-matched control subjects. Prediction using aMCI data reached 81% accuracy, 70% sensitivity and 100% specificity. This automated and objective method has potential in helping predict future clinical status in aMCI.

MRI-based automated computer classification of probable AD versus normal controls

Automated computer classification (ACC) techniques are needed to facilitate physician's diagnosis of complex diseases in individual patients. We provide an example of ACC using computational techniques within the context of cross-sectional analysis of magnetic resonance images (MRI) in neurodegenerative diseases, namely Alzheimer's dementia (AD). In this paper, the accuracy of our ACC methodology is assessed when presented with real life, imperfect data, i.e., cohorts of MRI with varying acquisition parameters and imaging quality. The comparative methodology uses the Jacobian determinants derived from dense deformation fields and scaled grey-level intensity from a selected volume of interest centered on the medial temporal lobe. The ACC performance is assessed in a series of leave-one-out experiments aimed at separating 75 probable AD and 75 age-matched normal controls. The resulting accuracy is 92% using a support vector machine classifier based on least squares optimization. Finally, it is shown in the Appendix that determinants and scaled grey-level intensity are appreciably more robust to varying parameters in validation studies using simulated data, when compared to raw intensities or grey/white matter volumes. The ability of cross-sectional MRI at detecting probable AD with high accuracy could have profound implications in the management of suspected AD candidates.

Structural and functional biomarkers of prodromal Alzheimer's disease: a high-dimensional pattern classification study

This work builds upon previous studies that reported high sensitivity and specificity in classifying individuals with mild cognitive impairment (MCI), which is often a prodromal phase of Alzheimer's disease (AD), via pattern classification of MRI scans. The current study integrates MRI and PET (15)O water scans from 30 participants in the Baltimore Longitudinal Study of Aging, and tests the hypothesis that joint evaluation of structure and function can yield higher classification accuracy than either alone. Classification rates of up to 100% accuracy were achieved via leave-one-out cross-validation, whereas conservative estimates of generalization performance in new scans, evaluated via bagging cross-validation, yielded an area under the receiver operating characteristic (ROC) curve equal to 0.978 (97.8%), indicating excellent diagnostic accuracy. Spatial maps of regions determined to contribute the most to the classification implicated many temporal, prefrontal, orbitofrontal, and parietal regions. Detecting complex patterns of brain abnormality in early stages of cognitive impairment has pivotal importance for the detection and management of AD.

Classification based on cortical folding patterns

We describe here a classification system based on automatically identified cortical sulci. Multivariate recognition methods are required for the detection of complex brain patterns with a spatial distribution. However, such methods may face the well-known issue of the curse of dimensionality-the risk of overfitting the training dataset in high-dimensional space. We overcame this problem, using a classifier pipeline with one- or two-stage of descriptor selection based on machine-learning methods, followed by a support vector machine classifier or linear discriminant analysis. We compared alternative designs of the pipeline on two different datasets built from the same database corresponding to 151 brains. The first dataset dealt with cortex asymmetry and the second dealt with the effect of the subject's sex. Our system successfully (98%) distinguished between the left and right hemispheres on the basis of sulcal shape (size, depth, etc.). The sex of the subject could be determined with a success rate of 85%. These results highlight the attractiveness of multivariate recognition models combined with appropriate descriptor selection. The sulci selected by the pipeline are consistent with previous whole-brain studies on sex effects and hemispheric asymmetries.

Automatic detection and quantification of hippocampal atrophy on MRI in temporal lobe epilepsy: a proof-of-principle study

In temporal lobe epilepsy (TLE), hippocampal atrophy (HA) is a marker of poor prognosis regarding seizure remission, but predicts success of anterior temporal lobe resection. Manual quantification of HA on MRI is time-consuming and limited by investigator availability. Normal ranges of hippocampal volumes, both in absolute terms and relative to intracranial volume, and of hippocampal asymmetry were defined using an automatic label propagation and decision fusion technique based on thirty manually derived atlases of healthy controls. Manual test-retest reliability and overlaps of automatically and manually determined hippocampal volumes were quantified with similarity indices (SIs). Correct clinical identification of ipsilateral HA, and contralaterally normal hippocampal volumes, was determined in nine patients with histologically confirmed hippocampal sclerosis in terms of volumes and asymmetry indices (AIs) for standard statistical thresholds and with receiver operating characteristic (ROC) analysis. Manual test-retest reliability was very high, with SIs between 0.87 and 0.90. Manual and automatic hippocampus labels overlapped with a SI of 0.83 on the unaffected but with 0.76 on the atrophic side. Accuracy was higher for less atrophic hippocampi. The automatic method correctly identified 6/9 HAs in terms of absolute volume, 7/9 in terms of relative volume at a standard 2 SD threshold, and 9/9 for AIs. ROC-determined thresholds allowed clinically desirable correct identification of all HAs (100% sensitivity) with 85-100% specificity for volumes, and 100% specificity for AIs. The method has the potential to automatically detect unilateral HA, but further work is needed to determine its performance in detecting clinically important bilateral disease.