There is a lack of multi-session P300 datasets for Brain-Computer Interfaces (BCI). Publicly available datasets are usually limited by small number of participants with few BCI sessions. In this sense, the lack of large, comprehensive datasets with various individuals and multiple sessions has limited advances in the development of more effective data processing and analysis methods for BCI systems. This is particularly evident to explore the feasibility of deep learning methods that require large datasets. Here we present the BCIAUT-P300 dataset, containing 15 autism spectrum disorder individuals undergoing 7 sessions of P300-based BCI joint-attention training, for a total of 105 sessions. The dataset was used for the 2019 IFMBE Scientific Challenge organized during MEDICON 2019 where, in two phases, teams from all over the world tried to achieve the best possible object-detection accuracy based on the P300 signals. This paper presents the characteristics of the dataset and the approaches followed by the 9 finalist teams during the competition. The winner obtained an average accuracy of 92.3% with a convolutional neural network based on EEGNet. The dataset is now publicly released and stands as a benchmark for future P300-based BCI algorithms based on multiple session data.

Brain electrical activity in acute ischemic stroke is related to the hypoperfusion of cerebral tissue as manifestation of neurovascular coupling. EEG could be applicable for bedside functional monitoring in emergency settings. We aimed to investigate the relation between hyper-acute ischemic stroke EEG changes, measured with bedside wireless-EEG, and hypoperfused core-penumbra CT-perfusion (CTP) volumes. In addition, we investigated the association of EEG and CTP parameters with neurological deficit measured by NIHSS. We analyzed and processed EEG, CTP and clinical data of 31 anterior acute ischemic stroke patients registered within 4.5 h from symptom onset. Delta/alpha ratio (DAR), (delta + theta)/(alpha + beta) ratio (DTABR) and relative delta power correlated directly (ρ = 0.72; 0.63; 0.65, respectively), while alpha correlated inversely (ρ = − 0.66) with total hypoperfused volume. DAR, DTBAR and relative delta and alpha parameters also correlated with ischemic core volume (ρ = 0.55; 0.50; 0.59; − 0.51, respectively). The same EEG parameters and CTP volumes showed significant relation with NIHSS at admission. The multivariate stepwise regression showed that DAR was the strongest predictor of NIHSS at admission (p < 0.001). The results of this study showed that hyper-acute alterations of EEG parameters are highly related to the extent of hypoperfused tissue highlighting the value of quantitative EEG as a possible complementary tool in the evaluation of stroke severity and its potential role in acute ischemic stroke monitoring.

Owing to the large inter-subject variability, early post-stroke prognosis is challenging, and objective biomarkers that can provide further prognostic information are still needed. The relation between quantitative EEG parameters in pre-thrombolysis hyper-acute phase and outcomes has still to be investigated. Hence, possible correlations between early EEG biomarkers, measured on bedside wireless EEG, and short-term/long-term functional and morphological outcomes were investigated in thrombolysis-treated strokes. EEG with a wireless device was performed in 20 patients with hyper-acute (< 4.5 h from onset) anterior ischemic stroke before reperfusion treatment. The correlations between outcome parameters (i.e., 7-day/12-month National Institutes of Health Stroke Scale NIHSS, 12-month modified Rankin Scale mRS, final infarct volume) and the pre-treatment EEG parameters were studied. Relative delta power and alpha power, delta/alpha (DAR), and (delta+theta)/(alpha+beta) (DTABR) ratios significantly correlated with NIHSS 7-day (rho = 0.80, − 0.81, 0.76, 0.75, respectively) and NIHSS 12-month (0.73, − 0.78, 0.74, 0.73, respectively), as well as with final infarct volume (0.75, − 0.70, 0.78, 0.62, respectively). A good outcome in terms of mRS ≤ 2 at 12 months was associated with DAR parameter (p = 0.008). The neurophysiological biomarkers obtained by non-invasive and portable technique as wireless EEG in the early pre-treatment phase may contribute as objective parameters to the short/long-term outcome prediction pivotal to better establish the treatment strategies.Graphical abstract

The use of deep learning for OCT image classification could enhance the diagnosis and monitoring of retinal diseases. However, challenges like variability in retinal abnormalities, noise, and artifacts in OCT images limit its clinical use. Our study aimed to evaluate the performance of various deep learning (DL) architectures in classifying retinal pathologies versus healthy cases based on OCT images, under data scarcity and label noise. We examined five DL architectures: ResNet18, ResNet34, ResNet50, VGG16, and InceptionV3. Fine-tuning of the pre-trained models was conducted on 5526 OCT images and reduced subsets down to 21 images to evaluate performance under data scarcity. The performance of models fine-tuned on subsets with label noise levels of 10%, 15%, and 20% was evaluated. All DL architectures achieved high classification accuracy (> 90%) with training sets of 345 or more images. InceptionV3 achieved the highest classification accuracy (99%) when trained on the entire training set. However, classification accuracy decreased and variability increased as sample size decreased. Label noise significantly affected model accuracy. Compensating for labeling errors of 10%, 15%, and 20% requires approximately 4, 9, and 14 times more images in the training set to reach the performance of 345 correctly labeled images. The results showed that DL models fine-tuned on sets of 345 or more OCT images can accurately classify retinal pathologies versus healthy controls. Our findings highlight that while mislabeling errors significantly impact classification performance in OCT analysis, this can be effectively mitigated by increasing the training sample size. By addressing data scarcity and labeling errors, our research aims to improve the real-world application and accuracy of retinal disease management.

The study reports the performance of Parkinson’s disease (PD) patients to operate Motor-Imagery based Brain-Computer Interface (MI-BCI) and compares three selected pre-processing and classification approaches. The experiment was conducted on 7 PD patients who performed a total of 14 MI-BCI sessions targeting lower extremities. EEG was recorded during the initial calibration phase of each session, and the specific BCI models were produced by using Spectrally weighted Common Spatial Patterns (SpecCSP), Source Power Comodulation (SPoC) and Filter-Bank Common Spatial Patterns (FBCSP) methods. The results showed that FBCSP outperformed SPoC in terms of accuracy, and both SPoC and SpecCSP in terms of the false-positive ratio. The study also demonstrates that PD patients were capable of operating MI-BCI, although with lower accuracy.