Search

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. [ABSTRACT FROM AUTHOR]

Objective: To test the feasibility and reliability of intracranial electrophysiological recordings in an acute status epilepticus model on laboratory swine., Method: Intrahippocampal injection of kainic acid (KA) was performed on 17 male Bama pigs ( Sus scrofa domestica ) weighing between 25 and 35 kg. Two stereoelectroencephalography (SEEG) electrodes with a total of 16 channels were implanted bilaterally along the sensorimotor cortex to the hippocampus. Brain electrical activity was recorded 2 h daily for 9-28 days. Three KA dosages were tested to evaluate the quantities capable of evoking status epilepticus. Local field potentials (LFPs) were recorded and compared before and after the KA injection. We quantified the epileptic patterns, including the interictal spikes, seizures, and high-frequency oscillations (HFOs), up to 4 weeks after the KA injection. Test-retest reliability using intraclass correlation coefficients (ICCs) were performed on interictal HFO rates to evaluate the recording stability of this model., Results: The KA dosage test suggested that a 10 μl (1.0 μg/μl) intrahippocampal injection could successfully evoke status epilepticus lasting from 4 to 12 h. At this dosage, eight pigs (50% of total) had prolonged epileptic events (tonic-chronic seizures + interictal spikes n  = 5, interictal spikes alone n  = 3) in the later 4 weeks of the video-SEEG recording period. Four pigs (25% of total) had no epileptic activities, and another four (25%) had lost the cap or did not complete the experiments. Animals that showed epileptiform events were grouped as E + ( n  = 8) and the four animals showing no signs of epileptic events were grouped as E- ( n  = 4). A total of 46 electrophysiological seizures were captured in the 4-week post-KA period from 4 E + animals, with the earliest onset on day 9. The seizure durations ranged from 12 to 45 s. A significant increase of hippocampal HFOs rate (num/min) was observed in the E+ group during the post-KA period (weeks 1, 2,4, p  < 0.05) compared to the baseline. But the E-showed no change or a decrease (in week 2, p  = 0.43) compared to their baseline rate. The between-group comparison showed much higher HFO rates in E + vs. E - ( F  = 35, p  < 0.01). The high ICC value [ICC (1, k ) = 0.81, p  < 0.05] quantified from the HFO rate suggested that this model had a stable measurement of HFOs during the four-week post-KA periods., Significance: This study measured intracranial electrophysiological activity in a swine model of KA-induced mesial temporal lobe epilepsy (mTLE). Using the clinical SEEG electrode, we distinguished abnormal EEG patterns in the swine brain. The high test-retest reliability of HFO rates in the post-KA period suggests the utility of this model for studying mechanisms of epileptogenesis. The use of swine may provide satisfactory translational value for clinical epilepsy research., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Zhu, Wang, Li, Bragin, Cao and Cheng.)

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., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Zhang, Luo, Zhao, Zhu, Jiang, Wang, Mo and Zeng.)

The objective of this study was to develop a computational algorithm capable of locating artifacts and identifying epileptic seizures, which specifically implementing in clinical stereoelectroencephalography (SEEG) recordings. Based on the nonstationary nature and broadband features of SEEG signals, a comprehensive strategy combined with the complex wavelet transform (CWT) and multi-layer thresholding method was implemented for both noise reduction and seizure detection. The artifacts removal pipeline integrated edge artifact removal, discrete spectrum analysis, and peak density evaluation. For automatic seizure detection, integrated power analysis and multi-dynamic thresholding were applied. The F1score was applied to evaluate overall performance of the algorithm. The algorithm was tested using expert-marked, double-blinded, clinical SEEG data from seven patients undergoing presurgical evaluation. This approach achieved the F1 score of 0.86 for noise reduction and 0.88 for seizure detection. This offline-approach method with minimum parameter tuning procedures and no prior information required, proved to be a feasible and solid solution for clinical SEEG data evaluation. Moreover, the algorithm can be improved with additional tuning and implemented with machine learning postprocessing pipelines.

We performed a dynamic study of arachnoid cysts (ACs) using magnetic resonance cisternography (MRC) and proposed a classification of ACs.Twenty-three suitable patients in our hospital entered into this study according to our inclusion criteria. MRC images were collected in all the subjects at 1 and 24 hours after the administration of intrathecal gadolinium-diethylenetriamine penta-acetic acid (Gd-DTPA). We allocate the enrolled patients into 2 groups, MRC group and surgery group. The MRC results were considered before treatment in 1 group (MRC group, 13 patients), whereas another group was surgically treated without considering the MRC results (surgery group, 10 patients). We calculated the enhanced area of cyst using modified MacDonald Criteria from the images and measured the surrounding subarachnoid area as the reference.We found that it was practically useful to quantify 3 types of ACs, complete communicating, incomplete communicating, and noncommunicating, according to MRC results in this study. All the subjects in both groups are closely observed before the treatment and the follow-up using the MRI examination. In the surgery group, 5 patients were found that the area of cysts shrank in the follow-up stage. However, there was no significant difference in the percentage shrinkage area between the 2 groups.We concluded that MRC with Gd-DTPA as a contrast agent is of significant clinical value for the diagnosis and treatment of children with intracranial ACs. This classification based on dynamic MRC is useful for making surgical recommendations.