"Within a minute" detection of focal cortical dysplasia

The new era of artificial intelligence in neuroradiology: current research and promising tools

Radiology has a number of characteristics that make it an especially suitable medical discipline for early artificial intelligence (AI) adoption. These include having a well-established digital workflow, standardized protocols for image storage, and numerous well-defined interpretive activities. The more than 200 commercial radiologic AI-based products recently approved by the Food and Drug Administration (FDA) to assist radiologists in a number of narrow image-analysis tasks such as image enhancement, workflow triage, and quantification, corroborate this observation. However, in order to leverage AI to boost efficacy and efficiency, and to overcome substantial obstacles to widespread successful clinical use of these products, radiologists should become familiarized with the emerging applications in their particular areas of expertise. In light of this, in this article we survey the existing literature on the application of AI-based techniques in neuroradiology, focusing on conditions such as vascular diseases, epilepsy, and demyelinating and neurodegenerative conditions. We also introduce some of the algorithms behind the applications, briefly discuss a few of the challenges of generalization in the use of AI models in neuroradiology, and skate over the most relevant commercially available solutions adopted in clinical practice. If well designed, AI algorithms have the potential to radically improve radiology, strengthening image analysis, enhancing the value of quantitative imaging techniques, and mitigating diagnostic errors.

A deep learning model for brain segmentation across pediatric and adult populations

Automated quantification of brain tissues on MR images has greatly contributed to the diagnosis and follow-up of neurological pathologies across various life stages. However, existing solutions are specifically designed for certain age ranges, limiting their applicability in monitoring brain development from infancy to late adulthood. This retrospective study aims to develop and validate a brain segmentation model across pediatric and adult populations. First, we trained a deep learning model to segment tissues and brain structures using T1-weighted MR images from 390 patients (age range: 2-81 years) across four different datasets. Subsequently, the model was validated on a cohort of 280 patients from six distinct test datasets (age range: 4-90 years). In the initial experiment, the proposed deep learning-based pipeline, icobrain-dl, demonstrated segmentation accuracy comparable to both pediatric and adult-specific models across diverse age groups. Subsequently, we evaluated intra- and inter-scanner variability in measurements of various tissues and structures in both pediatric and adult populations computed by icobrain-dl. Results demonstrated significantly higher reproducibility compared to similar brain quantification tools, including childmetrix, FastSurfer, and the medical device icobrain v5.9 (p-value< 0.01). Finally, we explored the potential clinical applications of icobrain-dl measurements in diagnosing pediatric patients with Cerebral Visual Impairment and adult patients with Alzheimer's Disease.

Development and prospective clinical validation of a convolutional neural network for automated detection and segmentation of focal cortical dysplasias

PURPOSE

Focal cortical dysplasias (FCDs) are a leading cause of drug-resistant epilepsy. Early detection and resection of FCDs have favorable prognostic implications for postoperative seizure freedom. Despite advancements in imaging methods, FCD detection remains challenging. House et al. (2021) introduced a convolutional neural network (CNN) for automated FCD detection and segmentation, achieving a sensitivity of 77.8%. However, its clinical applicability was limited due to a low specificity of 5.5%. The objective of this study was to improve the CNN's performance through data-driven training and algorithm optimization, followed by a prospective validation on daily-routine MRIs.

MATERIAL AND METHODS

A dataset of 300 3 T MRIs from daily clinical practice, including 3D T1 and FLAIR sequences, was prospectively compiled. The MRIs were visually evaluated by two neuroradiologists and underwent morphometric assessment by two epileptologists. The dataset included 30 FCD cases (11 female, mean age: 28.1 ± 10.1 years) and a control group of 150 normal cases (97 female, mean age: 32.8 ± 14.9 years), along with 120 non-FCD pathological cases (64 female, mean age: 38.4 ± 18.4 years). The dataset was divided into three subsets, each analyzed by the CNN. Subsequently, the CNN underwent a two-phase-training process, incorporating subset MRIs and expert-labeled FCD maps. This training employed both classical and continual learning techniques. The CNN's performance was validated by comparing the baseline model with the trained models at two training levels.

RESULTS

In prospective validation, the best model trained using continual learning achieved a sensitivity of 90.0%, specificity of 70.0%, and accuracy of 72.0%, with an average of 0.41 false positive clusters detected per MRI. For FCD segmentation, an average Dice coefficient of 0.56 was attained. The model's performance improved in each training phase while maintaining a high level of sensitivity. Continual learning outperformed classical learning in this regard.

CONCLUSIONS

Our study presents a promising CNN for FCD detection and segmentation, exhibiting both high sensitivity and specificity. Furthermore, the model demonstrates continuous improvement with the inclusion of more clinical MRI data. We consider our CNN a valuable tool for automated, examiner-independent FCD detection in daily clinical practice, potentially addressing the underutilization of epilepsy surgery in drug-resistant focal epilepsy and thereby improving patient outcomes.

Machine Learning and Artificial Intelligence Applications to Epilepsy: a Review for the Practicing Epileptologist

PURPOSE OF REVIEW

Machine Learning (ML) and Artificial Intelligence (AI) are data-driven techniques to translate raw data into applicable and interpretable insights that can assist in clinical decision making. Some of these tools have extremely promising initial results, earning both great excitement and creating hype. This non-technical article reviews recent developments in ML/AI in epilepsy to assist the current practicing epileptologist in understanding both the benefits and limitations of integrating ML/AI tools into their clinical practice.

RECENT FINDINGS

ML/AI tools have been developed to assist clinicians in almost every clinical decision including (1) predicting future epilepsy in people at risk, (2) detecting and monitoring for seizures, (3) differentiating epilepsy from mimics, (4) using data to improve neuroanatomic localization and lateralization, and (5) tracking and predicting response to medical and surgical treatments. We also discuss practical, ethical, and equity considerations in the development and application of ML/AI tools including chatbots based on Large Language Models (e.g., ChatGPT). ML/AI tools will change how clinical medicine is practiced, but, with rare exceptions, the transferability to other centers, effectiveness, and safety of these approaches have not yet been established rigorously. In the future, ML/AI will not replace epileptologists, but epileptologists with ML/AI will replace epileptologists without ML/AI.

Diagnostic Accuracy of Epilepsy-dedicated MRI with Post-processing

PURPOSE

To evaluate the diagnostic accuracy of epilepsy-dedicated 3 Tesla MRI including post-processing by correlating MRI, histopathology, and postsurgical seizure outcomes.

METHODS

3 Tesla-MRI including a magnetization-prepared two rapid acquisition gradient echo (MP2RAGE) sequence for post-processing using the morphometric analysis program MAP was acquired in 116 consecutive patients with drug-resistant focal epilepsy undergoing resection surgery. The MRI, histopathology reports and postsurgical seizure outcomes were recorded from the patient's charts.

RESULTS

The MRI and histopathology were concordant in 101 and discordant in 15 patients, 3 no hippocampal sclerosis/gliosis only lesions were missed on MRI and 1 of 28 focal cortical dysplasia (FCD) type II associated with a glial scar was considered a glial scar only on MRI. In another five patients, MRI was suggestive of FCD, the histopathology was uneventful but patients were seizure-free following surgery. The MRI and histopathology were concordant in 20 of 21 glioneuronal tumors, 6 cavernomas, and 7 glial scars. Histopathology was negative in 10 patients with temporal lobe epilepsy, 4 of them had anteroinferior meningoencephaloceles. Engel class IA outcome was reached in 71% of patients.

CONCLUSION

The proposed MRI protocol is highly accurate. No hippocampal sclerosis/gliosis only lesions are typically MRI negative. Small MRI positive FCD can be histopathologically missed, most likely due to sampling errors resulting from insufficient harvesting of tissue.

Preoperative Detection of Subtle Focal Cortical Dysplasia in Children by Combined Arterial Spin Labeling, Voxel-Based Morphometry, Electroencephalography-Synchronized Functional MRI, Resting-State Regional Homogeneity, and 18F-fluorodeoxyglucose Positron Emission Tomography

BACKGROUND

Focal cortical dysplasia (FCD) causes drug-resistant epilepsy in children that can be cured surgically, but the lesions are often unseen by imaging.

OBJECTIVE

To assess the efficiency of arterial spin labeling (ASL), voxel-based-morphometry (VBM), fMRI electroencephalography (EEG), resting-state regional homogeneity (ReHo), 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET), and their combination in detecting pediatric FCD.

METHODS

We prospectively included 10 children for whom FCD was localized by surgical resection. They underwent 3T MR acquisition with concurrent EEG, including ASL perfusion, resting-state BOLD fMRI (allowing the processing of EEG-fMRI and ReHo), 3D T1-weighted images processed using VBM, and FDG PET-CT coregistered with MRI. Detection was assessed visually and by comparison with healthy controls (for ASL and VBM).

RESULTS

Eight children had normal MRI, and 2 had asymmetric sulci. Using MR techniques, FCD was accurately detected by ASL for 6/10, VBM for 5/10, EEG-fMRI for 5/8 (excluding 2 with uninterpretable results), and ReHo for 4/10 patients. The combination of ASL, VBM, and ReHo allowed correct FCD detection for 9/10 patients. FDG PET alone showed higher accuracy than the other techniques (7/9), and its combination with VBM allowed correct FCD detection for 8/9 patients. The detection efficiency was better for patients with asymmetric sulci (2/2 for all techniques), but advanced MR techniques and PET were useful for MR-negative patients (7/8).

CONCLUSION

A combination of multiple imaging techniques, including PET, ASL, and VBM analysis of T1-weighted images, is effective in detecting subtle FCD in children.

Prognostic analysis in children with focal cortical dysplasia II undergoing epilepsy surgery: Clinical and radiological factors

OBJECTIVE

The aim of this study was to investigate the value of clinical profiles and radiological findings in assessing postsurgical outcomes in children with focal cortical dysplasia (FCD) II while exploring prognostic predictors of this disease.

METHODS

We retrospectively reviewed 50 patients with postoperative pathologically confirmed FCD II from January 2016 to June 2021. The clinical profiles and preoperative radiological findings were measured and analyzed. The patients were classified into four classes based on the Engel Class Outcome System at the last follow-up. For the analysis, the patients were divided into two categories based on Engel I and Engel II-IV, namely, seizure-free and non-seizure-free groups. Qualitative and quantitative factors were subsequently compared by groups using comparative statistics. Receiver operating characteristic (ROC) curves were used to identify the predictors of prognosis in children with FCD II.

RESULTS

Thirty-seven patients (74%) had Engel class I outcomes. The minimum postsurgical follow-up was 1 year. At the epilepsy onset, patients who attained seizure freedom were older and less likely to have no apparent lesions on the preoperative MRI ("MRI-negative"). The non-seizure-free group exhibited a higher gray matter signal intensity ratio (GR) on 3D T1-MPRAGE images (p = 0.006), with a lower GR on T2WI images (p = 0.003) and FLAIR images (p = 0.032). The ROC curve indicated that the model that combined the GR value of all MRI sequences (AUC, 0.87; 95% CI, 0.77-0.97; p < 0.001; 86% sensitivity, 85% specificity) was able to predict prognosis accurately.

CONCLUSION

A lower age at the onset or the MRI-negative finding of FCD lesions suggests a poor prognosis for children with FCD II. The model consisting of GR values from three MRI sequences facilitates the prognostic assessment of FCD II patients with subtle MRI abnormalities to prevent worse outcomes.

MRI of focal cortical dysplasia

Focal cortical dysplasia (FCD) are histopathologically categorized in ILAE type I to III. Mild malformations of cortical development (mMCD) including those with oligodendroglial hyperplasia (MOGHE) are to be integrated into this classification yet. Only FCD type II have distinctive MRI and molecular genetics alterations so far. Subtle FCD including FCD type II located in the depth of a sulcus are often overlooked requiring the use of dedicated sequences (MP2RAGE, FLAWS, EDGE) and/or voxel (VBM)- or surface-based (SBM) postprocessing. The added value of 7 Tesla MRI has to be proven yet.