Serious game for radiotherapy training.

BACKGROUND: Cancer patients are often treated with radiation, therefore increasing their exposure to high energy emissions. In such cases, medical errors may be threatening or fatal, inducing the need to innovate new methods for maximum reduction of irreversible events. Training is an efficient and methodical tool to subject professionals to the real world and heavily educate them on how to perform with minimal errors. An evolving technique for this is Serious Gaming that can fulfill this purpose, especially with the rise of COVID-19 and the shift to the online world, by realistic and visual simulations built to present engaging scenarios. This paper presents the first Serious Game for Lung Cancer Radiotherapy training that embodies Biomedical Engineering principles and clinical experience to create a realistic and precise platform for coherent training. METHODS: To develop the game, thorough 3D modeling, animation, and gaming fundamentals were utilized to represent the whole clinical process of treatment, along with the scores and progress of every player. The model's goal is to output coherency and organization for students' ease of use and progress tracking, and to provide a beneficial educational experience supplementary to the users' training. It aims to also expand their knowledge and use of skills in critical cases where they must perform crucial decision-making and procedures on patients of different cases. RESULTS: At the end of this research, one of the accomplished goals consists of building a realistic model of the different equipment and tools accompanied with the radiotherapy process received by the patient on Maya 2018, including the true beam table, gantry, X-ray tube, CT Scanner, and so on. The serious game itself was then implemented on Unity Scenes with the built models to create a gamified authentic environment that incorporates the 5 main series of steps; Screening, Contouring, External Beam Planning, Plan Evaluation, Treatment, to simulate the practical workflow of an actual Oncology treatment delivery for lung cancer patients. CONCLUSION: This serious game provides an educational and empirical space for training and practice that can be used by students, trainees, and professionals to expand their knowledge and skills in the aim of reducing potential errors.

Effective connectivity analysis of iEEG and accurate localization of the epileptogenic focus at the onset of operculo-insular seizures.

Recognition of insular epilepsy may sometimes be challenging due to the rapid speed at which insular seizures can spread throughout the cortex via extensive connections to surrounding cortices. The spectrum weighted adaptive directed transfer function, a multivariate causality-based effective connectivity measure, was applied to intracranial electroencephalography recordings to identify generators of seizure activity. A non-parametric test based on surrogate data testing was used to validate statistical significance of causal relations. Outflow and inflow of seizure activity were extracted from the computed transfer matrix. Recorded data of 21 seizures from seven patients were analyzed including five who were rendered seizure-free after operculo-insular resection. Effective connectivity analysis of 7 s following electrical onset confirmed an operculo-insular seizure origin in 5 patients with a good post-operative seizure outcome, and for whom the resected region was sampled by intracranial electroencephalography contacts. Different or additional seizure foci were identified in 2 patients with a bad post-operative seizure outcome. Findings highlight the feasibility of accurate operculo-insular seizure foci localization based on quantitative approaches.

Technical Note: Kinect V2 surface filtering during gantry motion for radiotherapy applications.

PURPOSE: In radiotherapy, the Kinect V2 camera, has recently received a lot of attention concerning many clinical applications including patient positioning, respiratory motion tracking, and collision detection during the radiotherapy delivery phase. However, issues associated with such applications are related to some materials and surfaces reflections generating an offset in depth measurements especially during gantry motion. This phenomenon appears in particular when the collimator surface is observed by the camera; resulting in erroneous depth measurements, not only in Kinect surfaces itself, but also as a large peak when extracting a 1D respiratory signal from these data. METHODS: In this paper, we proposed filtering techniques to reduce the noise effect in the Kinect-based 1D respiratory signal, using a trend removal filter, and in associated 2D surfaces, using a temporal median filter. Filtering process was validated using a phantom, in order to simulate a patient undergoing radiotherapy treatment while having the ground truth. RESULTS: Our results indicate a better correlation between the reference respiratory signal and its corresponding filtered signal (Correlation coefficient of 0.76) than that of the nonfiltered signal (Correlation coefficient of 0.13). Furthermore, surface filtering results show a decrease in the mean square distance error (85%) between the reference and the measured point clouds. CONCLUSION: This work shows a significant noise compensation and surface restitution after surface filtering and therefore a potential use of the Kinect V2 camera for different radiotherapy-based applications, such as respiratory tracking and collision detection.

A Functional-Genetic Scheme for Seizure Forecasting in Canine Epilepsy.

OBJECTIVE: The objective of this work is the development of an accurate seizure forecasting algorithm that considers brain's functional connectivity for electrode selection. METHODS: We start by proposing Kmeans-directed transfer function, an adaptive functional connectivity method intended for seizure onset zone localization in bilateral intracranial EEG recordings. Electrodes identified as seizure activity sources and sinks are then used to implement a seizure-forecasting algorithm on long-term continuous recordings in dogs with naturally-occurring epilepsy. A precision-recall genetic algorithm is proposed for feature selection in line with a probabilistic support vector machine classifier. RESULTS: Epileptic activity generators were focal in all dogs confirming the diagnosis of focal epilepsy in these animals while sinks spanned both hemispheres in 2 of 3 dogs. Seizure forecasting results show performance improvement compared to previous studies, achieving average sensitivity of 84.82% and time in warning of 0.1. CONCLUSION: Achieved performances highlight the feasibility of seizure forecasting in canine epilepsy. SIGNIFICANCE: The ability to improve seizure forecasting provides promise for the development of EEG-triggered closed-loop seizure intervention systems for ambulatory implantation in patients with refractory epilepsy.

Bilateral preictal signature of phase-amplitude coupling in canine epilepsy.

Seizure forecasting would improve the quality of life of patients with refractory epilepsy. Although early findings were optimistic, no single feature has been found capable of individually characterizing brain dynamics during transition to seizure. Cross-frequency phase amplitude coupling has been recently proposed as a precursor of seizure activity. This work evaluates the existence of a statistically significant difference in mean phase amplitude coupling distribution between the preictal and interictal states of seizures in dogs with bilaterally implanted intracranial electrodes. Results show a statistically significant change (p<0.05) of phase amplitude coupling during the preictal phase. This change is correlated with the position of implanted electrodes and is more significant within high-gamma frequency bands. These findings highlight the potential benefit of bilateral iEEG analysis and the feasibility of seizure forecasting based on slow modulation of high frequency amplitude.

Bispectrum Features and Multilayer Perceptron Classifier to Enhance Seizure Prediction.

The ability to accurately forecast seizures could significantly improve the quality of life of patients with drug-refractory epilepsy. Prediction capabilities rely on the adequate identification of seizure activity precursors from electroencephalography recordings. Although a long list of features has been proposed, none of these is able to independently characterize the brain states during transition to a seizure. This work assessed the feasibility of using the bispectrum, an advanced signal processing technique based on higher order statistics, as a precursor of seizure activity. Quantitative features were extracted from the bispectrum and passed through two statistical tests to check for significant differences between preictal and interictal recordings. Results showed statistically significant differences (p < 0.05) between preictal and interictal states using all bispectrum-extracted features. We used normalized bispectral entropy, normalized bispectral squared entropy, and mean of magnitude as inputs to a 5-layer multilayer perceptron classifier and achieved respective held-out test accuracies of 78.11%, 72.64%, and 73.26%.

Preterm labour detection by use of a biophysical marker: the uterine electrical activity.

BACKGROUND: The electrical activity of the uterine muscle is representative of uterine contractility. Its characterization may be used to detect a potential risk of preterm delivery in women, even at an early gestational stage. METHODS: We have investigated the effect of the recording electrode position on the spectral content of the signal by using a mathematical model of the women's abdomen. We have then compared the simulated results to actual recordings. On signals with noise reduced with a dedicated algorithm, we have characterized the main frequency components of the signal spectrum in order to compute parameters indicative of different situations: preterm contractions resulting nonetheless in term delivery (i.e. normal contractions) and preterm contractions leading to preterm delivery (i.e. high-risk contractions). A diagnosis system permitted us to discriminate between these different categories of contractions. As the position of the placenta seems to affect the frequency content of electrical activity, we have also investigated in monkeys, with internal electrodes attached on the uterus, the effect of the placenta on the spectral content of the electrical signals. RESULTS: In women, the best electrode position was the median vertical axis of the abdomen. The discrimination between high risk and normal contractions showed that it was possible to detect a risk of preterm labour as early as at the 27th week of pregnancy (Misclassification Rate range: 11-19.5%). Placental influence on electrical signals was evidenced in animal recordings, with higher energy content in high frequency bands, for signals recorded away from the placenta when compared to signals recorded above the placental insertion. However, we noticed, from pregnancy to labour, a similar evolution of the frequency content of the signal towards high frequencies, whatever the relative position of electrodes and placenta. CONCLUSION: On human recordings, this study has proved that it is possible to detect, by non-invasive abdominal recordings, a risk of preterm birth as early as the 27th week of pregnancy. On animal signals, we have evidenced that the placenta exerts a local influence on the characteristics of the electrical activity of the uterus. However, these differences have a small influence on premature delivery risk diagnosis when using proper diagnosis tools.

A Genetic-Based Feature Selection Approach in the Identification of Left/Right Hand Motor Imagery for a Brain-Computer Interface.

Electroencephalography is a non-invasive measure of the brain electrical activity generated by millions of neurons. Feature extraction in electroencephalography analysis is a core issue that may lead to accurate brain mental state classification. This paper presents a new feature selection method that improves left/right hand movement identification of a motor imagery brain-computer interface, based on genetic algorithms and artificial neural networks used as classifiers. Raw electroencephalography signals are first preprocessed using appropriate filtering. Feature extraction is carried out afterwards, based on spectral and temporal signal components, and thus a feature vector is constructed. As various features might be inaccurate and mislead the classifier, thus degrading the overall system performance, the proposed approach identifies a subset of features from a large feature space, such that the classifier error rate is reduced. Experimental results show that the proposed method is able to reduce the number of features to as low as 0.5% (i.e., the number of ignored features can reach 99.5%) while improving the accuracy, sensitivity, specificity, and precision of the classifier.

Kinect2 - respiratory movement detection study.

Radiotherapy is one of the main cancer treatments. It consists in irradiating tumor cells to destroy them while sparing healthy tissue. The treatment is planned based on Computed Tomography (CT) and is delivered over fractions during several days. One of the main challenges is replacing patient in the same position every day to irradiate the tumor volume while sparing healthy tissues. Many patient positioning techniques are available. They are both invasive and not accurate performed using tattooed marker on the patient's skin aligned with a laser system calibrated in the treatment room or irradiating using X-ray. Currently systems such as Vision RT use two Time of Flight cameras. Time of Flight cameras have the advantage of having a very fast acquisition rate allows the real time monitoring of patient movement and patient repositioning. The purpose of this work is to test the Microsoft Kinect2 camera for potential use for patient positioning and respiration trigging. This type of Time of Flight camera is non-invasive and costless which facilitate its transfer to clinical practice.

Kmeans-ICA based automatic method for ocular artifacts removal in a motorimagery classification.

Electroencephalogram (EEG) recordings aroused as inputs of a motor imagery based BCI system. Eye blinks contaminate the spectral frequency of the EEG signals. Independent Component Analysis (ICA) has been already proved for removing these artifacts whose frequency band overlap with the EEG of interest. However, already ICA developed methods, use a reference lead such as the ElectroOculoGram (EOG) to identify the ocular artifact components. In this study, artifactual components were identified using an adaptive thresholding by means of Kmeans clustering. The denoised EEG signals have been fed into a feature extraction algorithm extracting the band power, the coherence and the phase locking value and inserted into a linear discriminant analysis classifier for a motor imagery classification.

Mathematical modeling of electrical activity of uterine muscle cells.

The uterine electrical activity is an efficient parameter to study the uterine contractility. In order to understand the ionic mechanisms responsible for its generation, we aimed at building a mathematical model of the uterine cell electrical activity based upon the physiological mechanisms. First, based on the voltage clamp experiments found in the literature, we focus on the principal ionic channels and their cognate currents involved in the generation of this electrical activity. Second, we provide the methodology of formulations of uterine ionic currents derived from a wide range of electrophysiological data. The model is validated step by step by comparing simulated voltage-clamp results with the experimental ones. The model reproduces successfully the generation of single spikes or trains of action potentials that fit with the experimental data. It allows analyzing ionic channels implications. Likewise, the calcium-dependent conductance influences significantly the cellular oscillatory behavior.