Abstract
Epilepsy affects approximately 1% of the world's population. Semiology of epileptic seizures contain major clinical signs to classify epilepsy syndromes currently evaluated by epileptologists by simple visual inspection of video. There is a necessity to create automatic and semiautomatic methods for seizure detection and classification to better support patient monitoring management and diagnostic decisions. One of the current promising approaches are the marker-less computer-vision techniques. In this paper an end-to-end deep learning approach is proposed for binary classification of Frontal vs. Temporal Lobe Epilepsies based solely on seizure videos. The system utilizes infrared (IR) videos of the seizures as it is used 24/7 in hospitals' epilepsy monitoring units. The architecture employs transfer learning from large object detection "static" and human action recognition "dynamic" datasets such as ImageNet and Kinectics-400, to extract and classify the clinically known spatiotemporal features of seizures. The developed classification architecture achieves a 5-fold cross-validation f1-score of 0.844 +/- 0.042. This architecture has the potential to support physicians with diagnostic decisions and might be applied for online applications in epilepsy monitoring units. Furthermore, it may be jointly used in the near future with synchronized scene depth 3D information and EEG from the seizures.

Abstract
Though Motor Imagery (MI) stroke rehabilitation effectively promotes neural reorganization, current therapeutic methods are immeasurable and their repetitiveness can be demotivating. In this work, a real-time electroencephalogram (EEG) based MI-BCI (Brain Computer Interface) system with a virtual reality (VR) game as a motivational feedback has been developed for stroke rehabilitation. If the subject successfully hits one of the targets, it explodes and thus providing feedback on a successfully imagined and virtually executed movement of hands or feet. Novel classification algorithms with deep learning (DL) and convolutional neural network (CNN) architecture with a unique trial onset detection technique was used. Our classifiers performed better than the previous architectures on datasets from PhysioNet offline database. It provided fine classification in the real-time game setting using a 0.5 second 16 channel input for the CNN architectures. Ten participants reported the training to be interesting, fun and immersive. "It is a bit weird, because it feels like it would be my hands", was one of the comments from a test person. The VR system induced a slight discomfort and a moderate effort for MI activations was reported. We conclude that MI-BCI-VR systems with classifiers based on DL for real-time game applications should be considered for motivating MI stroke rehabilitation. © 2019 Association for Computing Machinery.

Abstract
Epilepsy is a major neurological disorder affecting approximately 1% of the world population, where seizure semiology is an essential tool for clinical evaluation of seizures. This includes qualitative visual inspection of videos from the seizures in epilepsy monitoring units by epileptologists. In order to support this clinical diagnosis process, promising deep learning-based systems were proposed. However, these indicate that video datasets of epileptic seizures are still rare and limited in size. In order to enable the full potential of AI systems for epileptic seizure diagnosis support and research, a novel collaborative development framework is proposed for a scalable DL-assisted clinical research and diagnosis support of epileptic seizures. The designed cloud-based approach integrates our deployed and tested NeuroKinect data acquisition pipeline into an MLOps framework to scale data set extension and analysis to a multi-clinical utilization. The proposed development framework incorporates an MLOps approach, to ensure convenient collaboration between clinicians and data scientists, providing continuous advantages to both user groups. It addresses methods for efficient utilization of HW, SW and human resources. In the future, the system is going to be expanded with several AI-based tools. Such as DL-based automated 3D motion capture (MoCap), 3D movement analysis support, quantitative seizure semiology analysis tools, video-based MOI and seizure classification. © 2021 IEEE

Abstract
Seizure semiology is a well-established method to classify epileptic seizure types, but requires a significant amount of resources as long-term Video-EEG monitoring needs to be visually analyzed. Therefore, computer vision based diagnosis support tools are a promising approach. In this article, we utilize infrared (IR) and depth (3D) videos to show the feasibility of a 24/7 novel object and action recognition based deep learning (DL) monitoring system to differentiate between epileptic seizures in frontal lobe epilepsy (FLE), temporal lobe epilepsy (TLE) and non-epileptic events. Based on the largest 3Dvideo-EEG database in the world (115 seizures/+680,000 video-frames/427GB), we achieved a promising cross-subject validation f1-score of 0.833 +/- 0.061 for the 2 class (FLE vs. TLE) and 0.763 +/- 0.083 for the 3 class (FLE vs. TLE vs. non-epileptic) case, from 2 s samples, with an automated semi-specialized depth (Acc.95.65%) and Mask R-CNN (Acc.96.52%) based cropping pipeline to pre-process the videos, enabling a near-real-time seizure type detection and classification tool. Our results demonstrate the feasibility of our novel DL approach to support 24/7 epilepsy monitoring, outperforming all previously published methods.

Abstract
Clinical in-bed video-based human motion analysis is a very relevant computer vision topic for several relevant biomedical applications. Nevertheless, the main public large datasets (e.g. ImageNet or 3DPW) used for deep learning approaches lack annotated examples for these clinical scenarios. To address this issue, we introduce BlanketSet, an RGB-IRD action recognition dataset of sequences performed in a hospital bed. This dataset has the potential to help bridge the improvements attained in more general large datasets to these clinical scenarios. Information on how to access the dataset is available at rdm.inesctec.pt/dataset/nis-2022-004.

Abstract
Human motion analysis has seen drastic improvements recently, however, due to the lack of representative datasets, for clinical in-bed scenarios it is still lagging behind. To address this issue, we implemented BlanketGen, a pipeline that augments videos with synthetic blanket occlusions. With this pipeline, we generated an augmented version of the pose estimation dataset 3DPW called BlanketGen3DPW. We then used this new dataset to fine-tune a Deep Learning model to improve its performance in these scenarios with promising results. Code and further information are available at https://gitlab.inesctec.pt/brain-lab/brainlab-public/blanket-gen-releases.