Brain Arteriovenous Malformations Located in Language Area: Surgical Outcomes and Risk Factors for Postoperative Language Deficits

Emotion recognition of EEG signals based on contrastive learning graph convolutional model

Objective.Electroencephalogram (EEG) signals offer invaluable insights into the complexities of emotion generation within the brain. Yet, the variability in EEG signals across individuals presents a formidable obstacle for empirical implementations. Our research addresses these challenges innovatively, focusing on the commonalities within distinct subjects' EEG data.Approach.We introduce a novel approach named Contrastive Learning Graph Convolutional Network (CLGCN). This method captures the distinctive features and crucial channel nodes related to individuals' emotional states. Specifically, CLGCN merges the dual benefits of CL's synchronous multisubject data learning and the GCN's proficiency in deciphering brain connectivity matrices. Understanding multifaceted brain functions and their information interchange processes is realized as CLGCN generates a standardized brain network learning matrix during a dataset's learning process.Main results.Our model underwent rigorous testing on the Database for Emotion Analysis using Physiological Signals (DEAP) and SEED datasets. In the five-fold cross-validation used for dependent subject experimental setting, it achieved an accuracy of 97.13% on the DEAP dataset and surpassed 99% on the SEED and SEED_IV datasets. In the incremental learning experiments with the SEED dataset, merely 5% of the data was sufficient to fine-tune the model, resulting in an accuracy of 92.8% for the new subject. These findings validate the model's efficacy.Significance.This work combines CL with GCN, improving the accuracy of decoding emotional states from EEG signals and offering valuable insights into uncovering the underlying mechanisms of emotional processes in the brain.

Quantitative evaluation of the hemodynamic differences between ruptured and unruptured cerebral arteriovenous malformations using angiographic parametric imaging-derived radiomics features

PURPOSE

Imaging features of cerebral arteriovenous malformations (AVMs) are mainly interpreted according to demographic and qualitative anatomical characteristics. This study aimed to use angiographic parametric imaging (API)-derived radiomics features to explore whether these features extracted from digital subtraction angiography (DSA) were associated with the hemorrhagic presentation of AVMs.

METHODS

Patients with AVM were retrospectively evaluated. Among them, 80% were randomly assigned to a training dataset, and the remaining 20% were assigned to an independent test dataset. Radiomics features were extracted from DSA by API. Then, informative features were selected from radiomics features and clinical features using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. A model was constructed based on the selected features to classify the dichotomous hemorrhagic presentation in the training dataset. The model performance was evaluated in the test dataset with confusion matrix-related metrics.

RESULTS

A total of 529 consecutive patients with AVMs between July 2011 and December 2020 were included in this study. After being selected by the LASSO algorithm and analyzed by multivariable logistic regression, three clinical features, namely, age (p = 0.01), nidus size (p < 0.001), and venous drainage patterns (p < 0.001), and four radiomics features were used to construct a model in the training dataset. On the independent test dataset, the model demonstrated a sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 0.852, 0.844, 0.881, 0.809, and 0.849, respectively.

CONCLUSION

The radiomics features extracted from DSA by API could be potential indicators for the hemorrhagic presentation of AVMs.

Roles of fMRI and Wada tests in the presurgical evaluation of language functions in temporal lobe epilepsy

Surgical treatment of pharmacoresistant temporal lobe epilepsy (TLE) carries risks for language function that can significantly affect the quality of life. Predicting the risks of decline in language functions before surgery is, consequently, just as important as predicting the chances of becoming seizure-free. The intracarotid amobarbital test, generally known as the Wada test (WT), has been traditionally used to determine language lateralization and to estimate their potential decline after surgery. However, the test is invasive and it does not localize the language functions. Therefore, other noninvasive methods have been proposed, of which functional magnetic resonance (fMRI) has the greatest potential. Functional MRI allows localization of language areas. It has good concordance with the WT for language lateralization, and it is of predictive value for postsurgical naming outcomes. Consequently, fMRI has progressively replaced WT for presurgical language evaluation. The objective of this manuscript is to review the most relevant aspects of language functions in TLE and the current role of fMRI and WT in the presurgical evaluation of language. First, we will provide context by revising the language network distribution and the effects of TLE on them. Then, we will assess the functional outcomes following various forms of TLE surgery and measures to reduce postoperative language decline. Finally, we will discuss the current indications for WT and fMRI and the potential usefulness of the resting-state fMRI technique.

Grading scale based on arcuate fasciculus segmentation to predict postoperative language outcomes of brain arteriovenous malformations

OBJECTIVE

The long-term postoperative language outcomes for brain arteriovenous malformations (bAVMs) have not been well characterised. With fibres scattered in the Broca's, Wernicke's and Geschwind's area, the arcuate fasciculus (AF) is considered as a crucial structure of language function. This study aimed to observe the language outcomes, determine the risk factors and construct a grading system for long-term postoperative language deficits (LDs) in patients with bAVMs involving the AF (AF-bAVMs).

METHODS

We retrospectively reviewed 135 patients with AF-bAVMs. Based on the course of the AF and our clinical experience, three boundary lines were drawn to divide the AF into segments I, II, III and IV in spatial order from the frontal lobe to the temporal lobe. Surgery-related LD evaluations were performed 1 week (short term) and at the last follow-up (long term) after surgery. Finally, based on multivariable logistic regression analysis, a grading system was constructed to predict long-term postoperative LD. The predictive accuracy was assessed using the area under the receiver operating characteristic curve (AUC).

RESULTS

Sixty-two (45.9%) patients experienced short-term postoperative LD. After a mean follow-up of 50.2±24.9 months, long-term LD was found in 14 (10.4%) patients. Nidus size (p=0.007), LD history (p=0.009) and segment II involvement (p=0.030) were independent risk factors for short-term LD. Furthermore, segment II involvement (p=0.002), anterior choroidal artery (AChA) feeding (p=0.001), patient age (p=0.023) and LD history (p=0.001) were independent risk factors for long-term LD. A grading system was developed by combining the risk factors for long-term LD; its predictive accuracy was 0.921.

CONCLUSIONS

The involvement of the trunk of the AF between Broca's area and the inferior parietal lobule, a nidus supplied by the AChA, older patient age and history of LD were associated with long-term postoperative LD. The grading system combining these factors demonstrated favourable predictive accuracy for long-term language outcomes.

Chinese Cerebrovascular Neurosurgery Society and Chinese Interventional & Hybrid Operation Society, of Chinese Stroke Association Clinical Practice Guidelines for Management of Brain Arteriovenous Malformations in Eloquent Areas

Aim: The aim of this guideline is to present current and comprehensive recommendations for the management of brain arteriovenous malformations (bAVMs) located in eloquent areas. Methods: An extended literature search on MEDLINE was performed between Jan 1970 and May 2020. Eloquence-related literature was further screened and interpreted in different subcategories of this guideline. The writing group discussed narrative text and recommendations through group meetings and online video conferences. Recommendations followed the Applying Classification of Recommendations and Level of Evidence proposed by the American Heart Association/American Stroke Association. Prerelease review of the draft guideline was performed by four expert peer reviewers and by the members of Chinese Stroke Association. Results: In total, 809 out of 2,493 publications were identified to be related to eloquent structure or neurological functions of bAVMs. Three-hundred and forty-one publications were comprehensively interpreted and cited by this guideline. Evidence-based guidelines were presented for the clinical evaluation and treatment of bAVMs with eloquence involved. Topics focused on neuroanatomy of activated eloquent structure, functional neuroimaging, neurological assessment, indication, and recommendations of different therapeutic managements. Fifty-nine recommendations were summarized, including 20 in Class I, 30 in Class IIa, 9 in Class IIb, and 2 in Class III. Conclusions: The management of eloquent bAVMs remains challenging. With the evolutionary understanding of eloquent areas, the guideline highlights the assessment of eloquent bAVMs, and a strategy for decision-making in the management of eloquent bAVMs.

Plasticity in language cortex and white matter tracts after resection of dominant inferior parietal lobule arteriovenous malformations: a combined fMRI and DTI study

OBJECTIVE

The dominant inferior parietal lobe (IPL) contains cortical and subcortical structures that serve language processing. A high incidence of postoperative short-term aphasia and good potential for language reorganization have been observed. The authors' goal was to study the plasticity of the language cortex and language-related fibers in patients with brain arteriovenous malformations (BAVMs) located in the IPL.

METHODS

A total of 6 patients who underwent microsurgical treatment of an IPL BAVM were prospectively recruited between September 2016 and May 2018. Blood oxygen level-dependent functional MRI (BOLD-fMRI) and diffusion tensor imaging (DTI) were performed within 1 week before and 6 months after microsurgery. Language-related white matter (WM) eloquent fiber tracts and their contralateral homologous fiber tracts were tracked. The Western Aphasia Battery was administered to assess language function. The authors determined the total number of fibers and mean fractional anisotropy (FA) indices for each individual tract. In addition, they calculated the laterality index (LI) between the activated language cortex voxels in the lesional and contralesional hemispheres and compared these indices between the preoperative and postoperative fMR and DT images.

RESULTS

Of the 6 patients with IPL BAVMs, all experienced postoperative short-term language deficits, and 5 (83.3%) recovered completely at 6 months after surgery. Five patients (83.3%) had right homologous reorganization of BOLD signal activations in both Broca's and Wernicke's areas. More fibers were observed in the arcuate fasciculus (AF) in the lesional hemisphere than in the contralesional hemisphere (1905 vs 254 fibers, p = 0.035). Six months after surgery, a significantly increased number of fibers was seen in the right hemispheric AF (249 fibers preoperatively vs 485 postoperatively, p = 0.026). There were significantly more nerve fibers in the postoperative left inferior frontooccipital fasciculus (IFOF) (874 fibers preoperatively vs 1186 postoperatively, p = 0.010). A statistically significant increase in right hemispheric dominance of Wernicke's area was observed. The overall functional LI showed functional lateralization of Wernicke's area in the right hemisphere (LI ≤ -0.20) in all patients.

CONCLUSIONS

The authors' findings provide evidence for the functional reorganization by recruiting the right hemispheric homologous region of Broca's and Wernicke's areas, right hemispheric AFs, and left hemispheric IFOFs following resection of IPL BAVMs.Clinical trial registration no.: NCT02868008 (clinicaltrials.gov).