We hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze spectro-temporal features or complex, non-stationary features of EEG signals. If so, seizure detection could benefit from convolutional neural networks because their visual recognition ability is comparable to that of humans. We explored image-based seizure detection by applying convolutional neural networks to long-term EEG that included epileptic seizures. After filtering, EEG data were divided into short segments based on a given time window and converted into plot EEG images, each of which was classified by convolutional neural networks as ‘seizure’ or ‘non-seizure’. These resultant labels were then used to design a clinically practical index for seizure detection. The best true positive rate was obtained using a 1-s time window. The median true positive rate of convolutional neural networks labelling by seconds was 74%, which was higher than that of commercially available seizure detection software (20% by BESA and 31% by Persyst). For practical use, the median of detected seizure rate by minutes was 100% by convolutional neural networks, which was higher than the 73.3% by BESA and 81.7% by Persyst. The false alarm of convolutional neural networks' seizure detection was issued at 0.2 per hour, which appears acceptable for clinical practice. Moreover, we demonstrated that seizure detection improved when training was performed using EEG patterns similar to those of testing data, suggesting that adding a variety of seizure patterns to the training dataset will improve our method. Thus, artificial visual recognition by convolutional neural networks allows for seizure detection, which otherwise currently relies on skillful visual inspection by expert epileptologists during clinical diagnosis.
Background and Purpose: We analyzed the ability of a machine learning approach that uses diffusion tensor imaging (DTI) structural connectomes to determine lateralization of epileptogenicity in temporal lobe epilepsy (TLE).Materials and Methods: We analyzed diffusion tensor and 3-dimensional (3D) T 1 -weighted images of 44 patients with TLE (right, 15, left, 29; mean age, 33.0 « 11.6 years) and 14 age-matched controls. We constructed a whole brain structural connectome for each subject, calculated graph theoretical network measures, and used a support vector machine (SVM) for classification among 3 groups (right TLE versus controls, left TLE versus controls, and right TLE versus left TLE) following a feature reduction process with sparse linear regression.Results: In left TLE, we found a significant decrease in local efficiency and the clustering coefficient in several brain regions, including the left posterior cingulate gyrus, left cuneus, and both hippocampi. In right TLE, the right hippocampus showed reduced nodal degree, clustering coefficient, and local efficiency. With use of the leave-one-out crossvalidation strategy, the SVM classifier achieved accuracy of 75.9 to 89.7% for right TLE versus controls, 74.4 to 86.0% for left TLE versus controls, and 72.7 to 86.4% for left TLE versus right TLE.Conclusion: Machine learning of graph theoretical measures from the DTI structural connectome may give support to lateralization of the TLE focus. The present good discrimination between left and right TLE suggests that, with further refinement, the classifier should improve presurgical diagnostic confidence.
Gamma oscillations are physiological phenomena that reflect perception and cognition, and involve parvalbumin-positive γ-aminobutyric acid-ergic interneuron function. The auditory steady-state response (ASSR) is the most robust index for gamma oscillations, and it is impaired in patients with neuropsychiatric disorders such as schizophrenia and autism. Although ASSR reduction is known to vary in terms of frequency and time, the neural mechanisms are poorly understood. We obtained high-density electrocorticography recordings from a wide area of the cortex in 8 patients with refractory epilepsy. In an ASSR paradigm, click sounds were presented at frequencies of 20, 30, 40, 60, 80, 120, and 160 Hz. We performed time-frequency analyses and analyzed intertrial coherence, event-related spectral perturbation, and high-gamma oscillations. We demonstrate that the ASSR is globally distributed among the temporal, parietal, and frontal cortices. The ASSR was composed of time-dependent neural subcircuits differing in frequency tuning. Importantly, the frequency tuning characteristics of the late-latency ASSR varied between the temporal/frontal and parietal cortex, suggestive of differentiation along parallel auditory pathways. This large-scale survey of the cortical ASSR could serve as a foundation for future studies of the ASSR in patients with neuropsychiatric disorders.
Recognition of faces and written words is associated with category-specific brain activation in the ventral occipitotemporal cortex (vOT). However, topological and functional relationships between face-selective and word-selective vOT regions remain unclear. In this study, we collected data from patients with intractable epilepsy who underwent high-density recording of surface field potentials in the vOT. "Faces" and "letterstrings" induced outstanding category-selective responses among the 24 visual categories tested, particularly in high-γ band powers. Strikingly, within-hemispheric analysis revealed alternation of face-selective and letterstring-selective zones within the vOT. Two distinct face-selective zones located anterior and posterior portions of the mid-fusiform sulcus whereas letterstring-selective zones alternated between and outside of these 2 face-selective zones. Further, a classification analysis indicated that activity patterns of these zones mostly represent dedicated categories. Functional connectivity analysis using Granger causality indicated asymmetrically directed causal influences from face-selective to letterstring-selective regions. These results challenge the prevailing view that different categories are represented in distinct contiguous regions in the vOT.
SUMMARYObjective: Resective surgery for mesial temporal lobe epilepsy (MTLE) with a correspondent lesion has been established as an effective and safe procedure. Surgery for temporal lobe epilepsies with bilateral hippocampal sclerosis or without correspondent lesions, however, carries a higher risk of devastating memory decline, underscoring the importance of establishing the memory-dominant side preoperatively and adopting the most appropriate procedure. In this study, we focused on high gamma activities (HGAs) in the parahippocampal gyri and investigated the relationship between memory-related HGAs and memory outcomes after hippocampal transection (HT), a hippocampal counterpart to neocortical multiple subpial transection. The transient nature of memory worsening after HT provided us with a rare opportunity to compare HGAs and clinical outcomes without risking permanent memory disorders. Methods: We recorded electrocorticography from parahippocampal gyri of 18 patients with temporal lobe epilepsy while they executed picture naming and recognition tasks. Memory-related HGA was quantified by calculating differences in power amplification of electrocorticography signals in a high gamma range (60-120 Hz) between the two tasks. We compared memory-related HGAs from correctly recognized and rejected trials (hit-HGA and reject-HGA). Using hit-HGA, we determined HGA-dominant sides and compared them with memory outcomes after HT performed on seven patients. Results: We observed memory-related HGA mainly between 500 and 600 msec poststimulus. Hit-HGA was significantly higher than reject-HGA. Three patients who had surgery on the HGA-dominant side experienced transient memory worsening postoperatively. The postoperative memory functions of the other four patients remained unchanged. Significance: Parahippocampal HGA was indicated to reflect different memory processes and be compatible with the outcomes of HT, suggesting that HGA could provide predictive information on whether the mesial temporal lobe can be resected without causing memory worsening. This preliminary study suggests a refined surgical strategy for atypical MTLE based on reliable memory lateralization.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.