Dataset Information

Deep Learning Provides Exceptional Accuracy to ECoG-Based Functional Language Mapping for Epilepsy Surgery.

ABSTRACT: The success of surgical resection in epilepsy patients depends on preserving functionally critical brain regions, while removing pathological tissues. Being the gold standard, electro-cortical stimulation mapping (ESM) helps surgeons in localizing the function of eloquent cortex through electrical stimulation of electrodes placed directly on the cortical brain surface. Due to the potential hazards of ESM, including increased risk of provoked seizures, electrocorticography based functional mapping (ECoG-FM) was introduced as a safer alternative approach. However, ECoG-FM has a low success rate when compared to the ESM. In this study, we address this critical limitation by developing a new algorithm based on deep learning for ECoG-FM and thereby we achieve an accuracy comparable to ESM in identifying eloquent language cortex. In our experiments, with 11 epilepsy patients who underwent presurgical evaluation (through deep learning-based signal analysis on 637 electrodes), our proposed algorithm obtained an accuracy of 83.05% in identifying language regions, an exceptional 23% improvement with respect to the conventional ECoG-FM analysis (?60%). Our findings have demonstrated, for the first time, that deep learning powered ECoG-FM can serve as a stand-alone modality and avoid likely hazards of the ESM in epilepsy surgery. Hence, reducing the potential for developing post-surgical morbidity in the language function.

SUBMITTER: RaviPrakash H

PROVIDER: S-EPMC7218144 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep Learning Provides Exceptional Accuracy to ECoG-Based Functional Language Mapping for Epilepsy Surgery.

RaviPrakash Harish H Korostenskaja Milena M Castillo Eduardo M EM Lee Ki H KH Salinas Christine M CM Baumgartner James J Anwar Syed M SM Spampinato Concetto C Bagci Ulas U

Frontiers in neuroscience 20200506

The success of surgical resection in epilepsy patients depends on preserving functionally critical brain regions, while removing pathological tissues. Being the gold standard, electro-cortical stimulation mapping (ESM) helps surgeons in localizing the function of eloquent cortex through electrical stimulation of electrodes placed directly on the cortical brain surface. Due to the potential hazards of ESM, including increased risk of provoked seizures, electrocorticography based functional mappin ...[more]

PMID: 32435182

Similar Datasets

Project description:BackgroundDeep learning-based head and neck lymph node level (HN_LNL) autodelineation is of high relevance to radiotherapy research and clinical treatment planning but still underinvestigated in academic literature. In particular, there is no publicly available open-source solution for large-scale autosegmentation of HN_LNL in the research setting.MethodsAn expert-delineated cohort of 35 planning CTs was used for training of an nnU-net 3D-fullres/2D-ensemble model for autosegmentation of 20 different HN_LNL. A second cohort acquired at the same institution later in time served as the test set (n = 20). In a completely blinded evaluation, 3 clinical experts rated the quality of deep learning autosegmentations in a head-to-head comparison with expert-created contours. For a subgroup of 10 cases, intraobserver variability was compared to the average deep learning autosegmentation accuracy on the original and recontoured set of expert segmentations. A postprocessing step to adjust craniocaudal boundaries of level autosegmentations to the CT slice plane was introduced and the effect of autocontour consistency with CT slice plane orientation on geometric accuracy and expert rating was investigated.ResultsBlinded expert ratings for deep learning segmentations and expert-created contours were not significantly different. Deep learning segmentations with slice plane adjustment were rated numerically higher (mean, 81.0 vs. 79.6, p = 0.185) and deep learning segmentations without slice plane adjustment were rated numerically lower (77.2 vs. 79.6, p = 0.167) than manually drawn contours. In a head-to-head comparison, deep learning segmentations with CT slice plane adjustment were rated significantly better than deep learning contours without slice plane adjustment (81.0 vs. 77.2, p = 0.004). Geometric accuracy of deep learning segmentations was not different from intraobserver variability (mean Dice per level, 0.76 vs. 0.77, p = 0.307). Clinical significance of contour consistency with CT slice plane orientation was not represented by geometric accuracy metrics (volumetric Dice, 0.78 vs. 0.78, p = 0.703).ConclusionsWe show that a nnU-net 3D-fullres/2D-ensemble model can be used for highly accurate autodelineation of HN_LNL using only a limited training dataset that is ideally suited for large-scale standardized autodelineation of HN_LNL in the research setting. Geometric accuracy metrics are only an imperfect surrogate for blinded expert rating.

Project description:Mapping brain functions is crucial for neurosurgical planning in patients with drug-resistant seizures. However, presurgical language mapping using either functional or structural networks can be challenging, especially in children. In fact, most of the evidence on this topic derives from cross-sectional or retrospective studies in adults submitted to anterior temporal lobectomy. In this prospective study, we used fMRI and DTI to explore patterns of language representation, their predictors and impact on cognitive performances in 29 children and young adults (mean age at surgery: 14.6 ± 4.5 years) with focal lesional epilepsy. In 20 of them, we also assessed the influence of epilepsy surgery on language lateralization. All patients were consecutively enrolled at a single epilepsy surgery center between 2009 and 2015 and assessed with preoperative structural and functional 3T brain MRI during three language tasks: Word Generation (WG), Rhyme Generation (RG) and a comprehension task. We also acquired DTI data on arcuate fasciculus in 24 patients. We first assessed patterns of language representation (relationship of activations with the epileptogenic lesion and Laterality Index (LI)) and then hypothesized a causal model to test whether selected clinical variables would influence the patterns of language representation and the ensuing impact of the latter on cognitive performances. Twenty out of 29 patients also underwent postoperative language fMRI. We analyzed possible changes of fMRI and DTI LIs and their clinical predictors. Preoperatively, we found atypical language lateralization in four patients during WG task, in one patient during RG task and in seven patients during the comprehension task. Diffuse interictal EEG abnormalities predicted a more atypical language representation on fMRI (p = 0.012), which in turn correlated with lower attention (p = 0.036) and IQ/GDQ scores (p = 0.014). Postoperative language reorganization implied shifting towards atypical language representation. Abnormal postoperative EEG (p = 0.003) and surgical failures (p = 0.015) were associated with more atypical language lateralization, in turn correlating with worsened fluency. Neither preoperative asymmetry nor postoperative DTI LI changes in the arcuate fasciculus were observed. Focal lesional epilepsy associated with diffuse EEG abnormalities may favor atypical language lateralization and worse cognitive performances, which are potentially reversible after successful surgery.

Project description:We have provided 3-D and 4D mapping of speech and language function based upon the results of direct cortical stimulation and event-related modulation of electrocorticography signals. Patients estimated to have right-hemispheric language dominance were excluded. Thus, 100 patients who underwent two-stage epilepsy surgery with chronic electrocorticography recording were studied. An older group consisted of 84 patients at least 10 years of age (7367 artefact-free non-epileptic electrodes), whereas a younger group included 16 children younger than age 10 (1438 electrodes). The probability of symptoms transiently induced by electrical stimulation was delineated on a 3D average surface image. The electrocorticography amplitude changes of high-gamma (70-110 Hz) and beta (15-30 Hz) activities during an auditory-naming task were animated on the average surface image in a 4D manner. Thereby, high-gamma augmentation and beta attenuation were treated as summary measures of cortical activation. Stimulation data indicated the causal relationship between (i) superior-temporal gyrus of either hemisphere and auditory hallucination; (ii) left superior-/middle-temporal gyri and receptive aphasia; (iii) widespread temporal/frontal lobe regions of the left hemisphere and expressive aphasia; and (iv) bilateral precentral/left posterior superior-frontal regions and speech arrest. On electrocorticography analysis, high-gamma augmentation involved the bilateral superior-temporal and precentral gyri immediately following question onset; at the same time, high-gamma activity was attenuated in the left orbitofrontal gyrus. High-gamma activity was augmented in the left temporal/frontal lobe regions, as well as left inferior-parietal and cingulate regions, maximally around question offset, with high-gamma augmentation in the left pars orbitalis inferior-frontal, middle-frontal, and inferior-parietal regions preceded by high-gamma attenuation in the contralateral homotopic regions. Immediately before verbal response, high-gamma augmentation involved the posterior superior-frontal and pre/postcentral regions, bilaterally. Beta-attenuation was spatially and temporally correlated with high-gamma augmentation in general but with exceptions. The younger and older groups shared similar spatial-temporal profiles of high-gamma and beta modulation; except, the younger group failed to show left-dominant activation in the rostral middle-frontal and pars orbitalis inferior-frontal regions around stimulus offset. The human brain may rapidly and alternately activate and deactivate cortical areas advantageous or obtrusive to function directed toward speech and language at a given moment. Increased left-dominant activation in the anterior frontal structures in the older age group may reflect developmental consolidation of the language system. The results of our functional mapping may be useful in predicting, across not only space but also time and patient age, sites specific to language function for presurgical evaluation of focal epilepsy.

Project description:Language lateralization in patients with focal epilepsy frequently diverges from the left-lateralized pattern that prevails in healthy right-handed people, but the mechanistic explanations are still a matter of debate. Here, we debate the complex interaction between focal epilepsy, language lateralization, and functional neuroimaging techniques by introducing the case of a right-handed patient with unaware focal seizures preceded by aphasia, in whom video-EEG and PET examination suggested the presence of focal cortical dysplasia in the right superior temporal gyrus, despite a normal structural MRI. The functional MRI for language was inconclusive, and the neuropsychological evaluation showed mild deficits in language functions. A bilateral stereo-EEG was proposed confirming the right superior temporal gyrus origin of seizures, revealing how ictal aphasia emerged only once seizures propagated to the left superior temporal gyrus and confirming, by cortical mapping, the left lateralization of the posterior language region. Stereo-EEG-guided radiofrequency thermocoagulations of the (right) focal cortical dysplasia not only reduced seizure frequency but led to the normalization of the neuropsychological assessment and the "restoring" of a classical left-lateralized functional MRI pattern of language. This representative case demonstrates that epileptiform activity in the superior temporal gyrus can interfere with the functioning of the contralateral homologous cortex and its associated network. In the case of presurgical evaluation in patients with epilepsy, this interference effect must be carefully taken into consideration. The multimodal language lateralization assessment reported for this patient further suggests the sensitivity of different explorations to this interference effect. Finally, the neuropsychological and functional MRI changes after thermocoagulations provide unique cues on the network pathophysiology of focal cortical dysplasia and the role of diverse techniques in indexing language lateralization in complex scenarios.

Dataset Information

Deep Learning Provides Exceptional Accuracy to ECoG-Based Functional Language Mapping for Epilepsy Surgery.

Publications

Deep Learning Provides Exceptional Accuracy to ECoG-Based Functional Language Mapping for Epilepsy Surgery.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets