An open presurgery MRI dataset of people with epilepsy and focal cortical dysplasia type II

Focal cortical dysplasia detection by artificial intelligence using MRI: A systematic review and meta-analysis

PURPOSE

Focal cortical dysplasia (FCD) is a common cause of pharmacoresistant epilepsy. However, it can be challenging to detect FCD using MRI alone. This study aimed to review and analyze studies that used machine learning and artificial neural networks (ANN) methods as an additional tool to enhance MRI findings in FCD patients.

METHODS

A systematic search was conducted in four databases (Embase, PubMed, Scopus, and Web of Science). The quality of the studies was assessed using QUADAS-AI, and a bivariate random-effects model was used for analysis. The main outcome analyzed was the sensitivity and specificity of patient-wise outcomes. Heterogeneity among studies was assessed using I2.

RESULTS

A total of 41 studies met the inclusion criteria, including 24 ANN-based studies and 17 machine learning studies. Meta-analysis of internal validation datasets showed a pooled sensitivity of 0.81 and specificity of 0.92 for AI-based models in detecting FCD lesions. Meta-analysis of external validation datasets yielded a pooled sensitivity of 0.73 and specificity of 0.66. There was moderate heterogeneity among studies in the external validation dataset, but no significant publication bias was found.

CONCLUSION

Although there is an increasing number of machine learning and ANN-based models for FCD detection, their clinical applicability remains limited. Further refinement and optimization, along with longitudinal studies, are needed to ensure their integration into clinical practice. Addressing the identified limitations and intensifying research efforts will improve their relevance and reliability in real medical scenarios.

Detection of focal cortical dysplasia: Development and multicentric evaluation of artificial intelligence models

OBJECTIVE

Focal cortical dysplasia (FCD) is a common cause of drug-resistant focal epilepsy but can be challenging to detect visually on magnetic resonance imaging. Three artificial intelligence models for automated FCD detection are publicly available (MAP18, deepFCD, MELD) but have only been compared on single-center data. Our first objective is to compare them on independent multicenter test data. Additionally, we train and compare three new models and make them publicly available.

METHODS

We retrospectively collected FCD cases from four epilepsy centers. We chose three novel models that take two-dimensional (2D) slices (2D-nnUNet), 2.5D slices (FastSurferCNN), and large 3D patches (3D-nnUNet) as inputs and trained them on a subset of Bonn data. As core evaluation metrics, we used voxel-level Dice similarity coefficient (DSC), cluster-level F1 score, subject-level detection rate, and specificity.

RESULTS

We collected 329 subjects, 244 diagnosed with FCD (27.7 ± 14.4 years old, 54% male) and 85 healthy controls (7.1 ± 2.4 years old, 51% female). We used 118 subjects for model training and kept the remaining subjects as an independent test set. 3D-nnUNet achieved the highest F1 score of .58, the highest DSC of .36 (95% confidence interval [CI] = .30-.41), a detection rate of 55%, and a specificity of 86%. deepFCD showed the highest detection rate (82%) but had the lowest specificity (0%) and cluster-level precision (.03, 95% CI = .03-.04, F1 score = .07). MELD showed the least performance variation across centers, with detection rates between 46% and 54%.

SIGNIFICANCE

This study shows the variance in performance for FCD detection models in a multicenter dataset. The two models with 3D input data showed the highest sensitivity. The 2D models performed worse than all other models, suggesting that FCD detection requires 3D data. The greatly improved precision of 3D-nnUNet may make it a sensible choice to aid FCD detection.

A Quantitative Comparison Between Human and Artificial Intelligence in the Detection of Focal Cortical Dysplasia

OBJECTIVES

Artificial intelligence (AI) is thought to improve lesion detection. However, a lack of knowledge about human performance prevents a comparative evaluation of AI and an accurate assessment of its impact on clinical decision-making. The objective of this work is to quantitatively evaluate the ability of humans to detect focal cortical dysplasia (FCD), compare it to state-of-the-art AI, and determine how it may aid diagnostics.

MATERIALS AND METHODS

We prospectively recorded the performance of readers in detecting FCDs using single points and 3-dimensional bounding boxes. We acquired predictions of 3 AI models for the same dataset and compared these to readers. Finally, we analyzed pairwise combinations of readers and models.

RESULTS

Twenty-eight readers, including 20 nonexpert and 5 expert physicians, reviewed 180 cases: 146 subjects with FCD (median age: 25, interquartile range: 18) and 34 healthy control subjects (median age: 43, interquartile range: 19). Nonexpert readers detected 47% (95% confidence interval [CI]: 46, 49) of FCDs, whereas experts detected 68% (95% CI: 65, 71). The 3 AI models detected 32%, 51%, and 72% of FCDs, respectively. The latter, however, also predicted more than 13 false-positive clusters per subject on average. Human performance was improved in the presence of a transmantle sign ( P < 0.001) and cortical thickening ( P < 0.001). In contrast, AI models were sensitive to abnormal gyration ( P < 0.01) or gray-white matter blurring ( P < 0.01). Compared with single experts, expert-expert pairs detected 13% (95% CI: 9, 18) more FCDs ( P < 0.001). All AI models increased expert detection rates by up to 19% (95% CI: 15, 24) ( P < 0.001). Nonexpert+AI pairs could still outperform single experts by up to 13% (95% CI: 10, 17).

CONCLUSIONS

This study pioneers the comparative evaluation of humans and AI for FCD lesion detection. It shows that AI and human predictions differ, especially for certain MRI features of FCD, and, thus, how AI may complement the diagnostic workup.

Cortical and subcortical morphometric changes in patients with frontal focal cortical dysplasia type II

PURPOSE

This study investigates the morphometric changes in the brains of patients with frontal focal cortical dysplasia (FCD) Type II, distinguishing between right and left FCD, using voxel-based morphometry (VBM), surface-based morphometry (SBM), and subcortical shape analysis.

METHODS

The study included 53 patients with frontal lobe FCD Type II (28 left-sided, 25 right-sided) and 66 age- and gender-matched healthy controls. VBM and SBM analyses were conducted using Computational Anatomy Toolbox 12.8 (CAT12.8) and Statistical Parametric Mapping 12 (SPM12). Subcortical structures were segmented using FSL-FIRST. Statistical analyses were performed using non-parametric tests, with a significance threshold of p < 0.05.

RESULTS

VBM revealed increased gray matter volume in the bilateral ventral diencephalon, left putamen, and left thalamus in the left FCD group. SBM indicated reduced sulcal depth in the right precentral, postcentral, and caudal middle frontal gyrus in the right FCD group. Subcortical shape analysis showed internal deformation in the left hippocampus and external deformation in bilateral putamen in the left FCD group, and external deformation in the left caudate nucleus, left putamen, and right amygdala in the right FCD group.

CONCLUSION

Morphometric changes in frontal FCD Type II patients vary depending on the hemisphere. Right FCD Type II is associated with sulcal shallowing and external deformation in contralateral subcortical structures, while left FCD Type II shows internal and external deformations in the hippocampus and putamen, respectively, along with increased gray matter volume in the basal ganglia. These findings highlight the need for hemisphere-specific analyses in epilepsy research.

A new perspective on drug-resistant epilepsy in children with focal cortical dysplasia type 1: From challenge to favorable outcome

OBJECTIVE

We comprehensively characterized a large pediatric cohort with focal cortical dysplasia (FCD) type 1 to expand the phenotypic spectrum and to identify predictors of postsurgical outcomes.

METHODS

We included pediatric patients with histopathological diagnosis of isolated FCD type 1 and at least 1 year of postsurgical follow-up. We systematically reanalyzed clinical, electrophysiological, and radiological features. The results of this reanalysis served as independent variables for subsequent statistical analyses of outcome predictors.

RESULTS

All children (N = 31) had drug-resistant epilepsy with varying impacts on neurodevelopment and cognition (presurgical intelligence quotient [IQ]/developmental quotient scores = 32-106). Low presurgical IQ was associated with abnormal slow background electroencephalographic (EEG) activity and disrupted sleep architecture. Scalp EEG showed predominantly multiregional and often bilateral epileptiform activity. Advanced epilepsy magnetic resonance imaging (MRI) protocols identified FCD-specific features in 74.2% of patients (23/31), 17 of whom were initially evaluated as MRI-negative. In six of eight MRI-negative cases, fluorodeoxyglucose-positron emission tomography (PET) and subtraction ictal single photon emission computed tomography coregistered to MRI helped localize the dysplastic cortex. Sixteen patients (51.6%) underwent invasive EEG. By the last follow-up (median = 5 years, interquartile range = 3.3-9 years), seizure freedom was achieved in 71% of patients (22/31), including seven of eight MRI-negative patients. Antiseizure medications were reduced in 21 patients, with complete withdrawal in six. Seizure outcome was predicted by a combination of the following descriptors: age at epilepsy onset, epilepsy duration, long-term invasive EEG, and specific MRI and PET findings.

SIGNIFICANCE

This study highlights the broad phenotypic spectrum of FCD type 1, which spans far beyond the narrow descriptions of previous studies. The applied multilayered presurgical approach helped localize the epileptogenic zone in many previously nonlesional cases, resulting in improved postsurgical seizure outcomes, which are more favorable than previously reported for FCD type 1 patients.

Three-branch feature enhancement and fusion network for focal cortical dysplasia lesions segmentation using multimodal imaging

OBJECTIVE

Conventional multimodal imaging, including MRI and fluorodeoxyglucose positron emission tomography (FDG-PET), has difficulty in accurately detecting subtle or blurred focal cortical dysplasia (FCD) lesions. Morphometric maps assist localization by highlighting abnormal regions, whereas wavelet-filtered images emphasize texture and edge details. Therefore, we propose a three-branch feature enhancement and fusion network (TBFEF-Net) that integrates conventional multimodal imaging, morphometric maps, and wavelet-filtered images to enhance the accuracy of FCD localization.

METHODS

The proposed TBFEF-Net comprises a semantic segmentation backbone, a cross-branch feature enhancement (CFE) module, and a multi-feature fusion (MFF) module. In the semantic segmentation backbone, three UNet-based branches separately extract semantic features from conventional multimodal imaging, morphometric maps, and wavelet-filtered images. In the encoding stage, the CFE incorporates a residual-based convolutional block attention module (CBAM) to aggregate features from all branches, enhancing the feature representation of FCD lesions. While in the decoding stage, the MFF integrates edge detail features from the wavelet-filtered imaging branch into the conventional multimodal imaging branch, enhancing the ability to capture lesion edges. As a result, this approach enables more precise segmentation.

RESULTS

Experimental results show that TBFEF-Net surpasses several state-of-the-art methods in FCD segmentation. In the primary cohort, the Dice and sensitivity reached 59.73 % and 67.13 %, respectively, while in the open cohort, the Dice and sensitivity were 54.67 % and 54.81 %, respectively.

SIGNIFICANCE

We introduced wavelet-filtered images for the first time in FCD segmentation, offering a novel approach and perspective for FCD lesions localization.

The Imaging Database for Epilepsy And Surgery (IDEAS)

OBJECTIVE

Magnetic resonance imaging (MRI) is a crucial tool for identifying brain abnormalities in a wide range of neurological disorders. In focal epilepsy, MRI is used to identify structural cerebral abnormalities. For covert lesions, machine learning and artificial intelligence (AI) algorithms may improve lesion detection if abnormalities are not evident on visual inspection. The success of this approach depends on the volume and quality of training data.

METHODS

Herein, we release an open-source data set of pre-processed MRI scans from 442 individuals with drug-refractory focal epilepsy who had neurosurgical resections and detailed demographic information. We also share scans from 100 healthy controls acquired on the same scanners. The MRI scan data include the preoperative three-dimensional (3D) T1 and, where available, 3D fluid-attenuated inversion recovery (FLAIR), as well as a manually inspected complete surface reconstruction and volumetric parcellations. Demographic information includes age, sex, age a onset of epilepsy, location of surgery, histopathology of resected specimen, occurrence and frequency of focal seizures with and without impairment of awareness, focal to bilateral tonic-clonic seizures, number of anti-seizure medications (ASMs) at time of surgery, and a total of 1764 patient years of post-surgical followup. Crucially, we also include resection masks delineated from post-surgical imaging.

RESULTS

To demonstrate the veracity of our data, we successfully replicated previous studies showing long-term outcomes of seizure freedom in the range of ~50%. Our imaging data replicate findings of group-level atrophy in patients compared to controls. Resection locations in the cohort were predominantly in the temporal and frontal lobes.

SIGNIFICANCE

We envisage that our data set, shared openly with the community, will catalyze the development and application of computational methods in clinical neurology.

Status epilepticus and thinning of the entorhinal cortex

Status epilepticus (SE) carries risks of morbidity and mortality. Experimental studies have implicated the entorhinal cortex in prolonged seizures; however, studies in large human cohorts are limited. We hypothesised that individuals with temporal lobe epilepsy (TLE) and a history of SE would have more severe entorhinal atrophy compared to others with TLE and no history of SE. 357 individuals with drug resistant temporal lobe epilepsy (TLE) and 100 healthy controls were scanned on a 3T MRI. For all subjects, the cortex was segmented, parcellated, and the thickness calculated from the T1-weighted anatomical scan. Subcortical volumes were derived similarly. Cohen's d and Wilcoxon rank-sum tests respectively were used to capture effect sizes and significance. Individuals with TLE and SE had reduced entorhinal thickness compared to those with TLE and no history of SE. The entorhinal cortex was more atrophic ipsilaterally (d = 0.51, p < 0.001) than contralaterally (d = 0.37, p = 0.01). Reductions in ipsilateral entorhinal thickness were present in both left TLE (n = 22:176, d = 0.78, p < 0.001), and right TLE (n = 19:140, d = 0.31, p = 0.04), albeit with a smaller effect size in right TLE. Several other regions exhibited atrophy in individuals with TLE, but these did not relate to a history of SE. These findings suggest potential involvement or susceptibility of the entorhinal cortex in prolonged seizures.

Application of preoperative MRI lesion identification algorithm in pediatric and young adult focal cortical dysplasia-related epilepsy

OBJECTIVE

The purpose of this study was to evaluate the performance and generalizability of an automated, interpretable surface-based MRI classifier for the detection of focal cortical dysplasia.

METHODS

This was a retrospective cohort incorporating MRIs from the epilepsy surgery (FCD and MRI-negative) and neuroimaging (healthy controls) databases at Children's National Hospital (CNH), and a publicly-available FCD Type II dataset from Bonn, Germany. Clinical characteristics and outcomes were abstracted from patient records and/or existing databases. Subjects were included if they had 3T epilepsy-protocol MRI. Manually-segmented FCD masks were compared to the automated masks generated by the Multi-centre Epilepsy Lesion Detection (MELD) FCD detection algorithm. Sensitivity/specificity were calculated.

RESULTS

From CNH, 39 FCD pharmacoresistant epilepsy (PRE) patients, 19 healthy controls, and 19 MRI-negative patients were included. From Bonn, 85 FCD Type II were included, of which 68 passed preprocessing. MELD had varying performance (sensitivity) in these datasets: CNH FCD-PRE (54 %); Bonn (68 %); MRI-negative (44 %). In multivariate regression, FCD Type IIB pathology predicted higher chance of MELD automated lesion detection. All four patients who underwent resection/ablation of MELD-identified clusters achieved Engel I outcome.

SIGNIFICANCE

We validate the performance of MELD automated, interpretable FCD classifier in a diverse pediatric cohort with FCD-PRE. We also demonstrate the classifier has relatively good performance in an independent FCD Type II cohort with pediatric-onset epilepsy, as well as simulated real-world value in a pediatric population with MRI-negative PRE.

Focal cortical dysplasia lesion segmentation using multiscale transformer

OBJECTIVES

Accurate segmentation of focal cortical dysplasia (FCD) lesions from MR images plays an important role in surgical planning and decision but is still challenging for radiologists and clinicians. In this study, we introduce a novel transformer-based model, designed for the end-to-end segmentation of FCD lesions from multi-channel MR images.

METHODS

The core innovation of our proposed model is the integration of a convolutional neural network-based encoder-decoder structure with a multiscale transformer to augment the feature representation of lesions in the global field of view. Transformer pathways, composed of memory- and computation-efficient dual-self-attention modules, leverage feature maps from varying depths of the encoder to discern long-range interdependencies among feature positions and channels, thereby emphasizing areas and channels relevant to lesions. The proposed model was trained and evaluated on a public-open dataset including MR images of 85 patients using both subject-level and voxel-level metrics.

RESULTS

Experimental results indicate that our model offers superior performance both quantitatively and qualitatively. It successfully identified lesions in 82.4% of patients, with a low false-positive lesion cluster rate of 0.176 ± 0.381 per patient. Furthermore, the model achieved an average Dice coefficient of 0.410 ± 0.288, outperforming five established methods.

CONCLUSION

Integration of the transformer could enhance the feature presentation and segmentation performance of FCD lesions. The proposed model has the potential to serve as a valuable assistive tool for physicians, enabling rapid and accurate identification of FCD lesions. The source code and pre-trained model weights are available at https://github.com/zhangxd0530/MS-DSA-NET .

CRITICAL RELEVANCE STATEMENT

This multiscale transformer-based model performs segmentation of focal cortical dysplasia lesions, aiming to help radiologists and clinicians make accurate and efficient preoperative evaluations of focal cortical dysplasia patients from MR images.

KEY POINTS

The first transformer-based model was built to explore focal cortical dysplasia lesion segmentation. Integration of global and local features enhances the segmentation performance of lesions. A valuable benchmark for model development and comparative analyses was provided.

Deep learning-based automated lesion segmentation on pediatric focal cortical dysplasia II preoperative MRI: a reliable approach

OBJECTIVES

Focal cortical dysplasia (FCD) represents one of the most common causes of refractory epilepsy in children. Deep learning demonstrates great power in tissue discrimination by analyzing MRI data. A prediction model was built and verified using 3D full-resolution nnU-Net for automatic lesion detection and segmentation of children with FCD II.

METHODS

High-resolution brain MRI structure data from 65 patients, confirmed with FCD II by pathology, were retrospectively studied. Experienced neuroradiologists segmented and labeled the lesions as the ground truth. Also, we used 3D full-resolution nnU-Net to segment lesions automatically, generating detection maps. The algorithm was trained using fivefold cross-validation, with data partitioned into training (N = 200) and testing (N = 15). To evaluate performance, detection maps were compared to expert manual labels. The Dice-Sørensen coefficient (DSC) and sensitivity were used to assess the algorithm performance.

RESULTS

The 3D nnU-Net showed a good performance for FCD lesion detection at the voxel level, with a sensitivity of 0.73. The best segmentation model achieved a mean DSC score of 0.57 on the testing dataset.

CONCLUSION

This pilot study confirmed that 3D full-resolution nnU-Net can automatically segment FCD lesions with reliable outcomes. This provides a novel approach to FCD lesion detection.

CRITICAL RELEVANCE STATEMENT

Our fully automatic models could process the 3D T1-MPRAGE data and segment FCD II lesions with reliable outcomes.

KEY POINTS

• Simplified image processing promotes the DL model implemented in clinical practice. • The histopathological confirmed lesion masks enhance the clinical credibility of the AI model. • The voxel-level evaluation metrics benefit lesion detection and clinical decisions.