A data-driven machine learning approach for brain-computer interfaces targeting lower limb neuroprosthetics

Prosthetic devices that replace a lost limb have become increasingly performant in recent years. Recent advances in both software and hardware allow for the decoding of electroencephalogram (EEG) signals to improve the control of active prostheses with brain-computer interfaces (BCI). Most BCI research is focused on the upper body. Although BCI research for the lower extremities has increased in recent years, there are still gaps in our knowledge of the neural patterns associated with lower limb movement. Therefore, the main objective of this study is to show the feasibility of decoding lower limb movements from EEG data recordings. The second aim is to investigate whether well-known neuroplastic adaptations in individuals with an amputation have an influence on decoding performance. To address this, we collected data from multiple individuals with lower limb amputation and a matched able-bodied control group. Using these data, we trained and evaluated common BCI methods that have already been proven effective for upper limb BCI. With an average test decoding accuracy of 84% for both groups, our results show that it is possible to discriminate different lower extremity movements using EEG data with good accuracy. There are no significant differences (p = 0.99) in the decoding performance of these movements between healthy subjects and subjects with lower extremity amputation. These results show the feasibility of using BCI for lower limb prosthesis control and indicate that decoding performance is not influenced by neuroplasticity-induced differences between the two groups.

P-383 Endometrial scratching: A strategy to stimulate the angiogenesis aspect of implantation in unexplained, repeated implantation failure

Study question

Does endometrial scratching serve as an angiogenic stimulator during implantation in unexplained, repeated implantation failure (uRIF) patients?

Summary answer

Endometrial scratching can reimburse and regulate genes involved in both endometrial angiogenesis and receptivity.

What is known already

The vascular endothelial growth factor (VEGF), as an angiogenic factor, is well-known for its function in a variety of physiological and pathological aspects of female reproduction. Following the embryo transfer in the In-Vitro Fertilization cycles, the most challenging clinical obstacle to overcome is RIF. Endometrial scratching is a technique considered as an option for enhancing the embryo implantation of uRIF patients by modulating the different cellular and molecular components regulating endometrial receptivity before and during implantation.

Study design, size, duration

Twenty uRIF patients were enrolled based on a randomized controlled trial (RCT) to study the expression of genes involved in endometrial angiogenesis and receptivity functions (VEGFR1, VEGFR2, COL18A1, E-cadherin, FGF1) following ES. Ten uRIF patients were randomly assigned to the intervention group (twice endometrial sampling in the follicular and luteal phases) and ten in the control group (only luteal phase sampling) prior to the ovarian stimulation cycle.

Participants/materials, setting, methods

Women who failed to conceive following three or more IVF/ICSI cycles, high-quality embryo transfer, and at least one blastocyst embryo transfer cycle met the inclusion criteria. Post-biopsy endometrial samples were divided evenly. One component was placed in 10% formalin for histology dating and another in RNALater for genomic analysis and preserved at -80 °C for RNA extraction.

Main results and the role of chance

The expression levels of VEGFR1 and VEGFR2 (both as the receptors of VEGF) were significantly increased after ES (P <0.05).

The mRNA expression level of COL18A1 was significantly decreased after ES. COL18A1 is an inhibitor of VEGF which can impede VEGF-mediated signaling and endothelial cell proliferation, via blocking of its receptor specifically VEGFR2.

The E-cadherin expression level was significantly decreased (P <0.05) in the endometrium of the intervention group after scratching. E-cadherin is a cell-cell adhesion molecule that has a pivotal role in maintaining normal epithelial architecture, establishing cell polarity, glandular differentiation, and morphogenesis.

Data showed that Fibroblast Growth Factor1 (FGF1) expression level was significantly increased in the intervention group (P <0.05). FGF1 promotes the formation of blood vessels which improves endometrial trophoblastic interaction and affects embryo implantation.

Limitations, reasons for caution

To further understand the function of these changes, it is preferable to compare the data with endometrium from a fertile group, which is ongoing.

Wider implications of the findings

On the timeline of embryo implantation, angiogenic factors (e.g., VEGFR1 and VEGFR2), their inhibitors (e.g., E-cadherin and COL18A1), and activators (e.g., FGF1) work together to establish a dynamic environment responsible for endometrial receptivity, which has been compromised in the endometrium of RIF patients.ES can reimburse and regulate these angiogenesis processes.

Trial registration number

IRCT20210316050723N1

Deep learning for biosignal control: insights from basic to real-time methods with recommendations

Biosignal control is an interaction modality that allows users to interact with electronic devices by decoding the biological signals emanating from the movements or thoughts of the user. This manner of interaction with devices can enhance the sense of agency for users and enable persons suffering from a paralyzing condition to interact with everyday devices that would otherwise be challenging for them to use. It can also improve control of prosthetic devices and exoskeletons by making the interaction feel more natural and intuitive. However, with the current state of the art, several issues still need to be addressed to reliably decode user intent from biosignals and provide an improved user experience over other interaction modalities. One solution is to leverage advances in Deep Learning (DL) methods to provide more reliable decoding at the expense of added computational complexity. This scoping review introduces the basic concepts of DL and assists readers in deploying DL methods to a real-time control system that should operate under real-world conditions. The scope of this review covers any electronic device, but with an emphasis on robotic devices, as this is the most active area of research in biosignal control. We review the literature pertaining to the implementation and evaluation of control systems that incorporate DL to identify the main gaps and issues in the field, and formulate suggestions on how to mitigate them. Additionally, we formulate guidelines on the best approach to designing, implementing and evaluating research prototypes that use DL in their biosignal control systems.

P–338 Epigenetic alterations in H19-DMR regulatory region in endometrial tissues of women with endometriosis

Study question

Is epigenetic modifications pattern in DMR region of H19 gene different in endometrial tissues of women with endometriosis in compare to normal endometrium?

Summary answer

The methylation level in DMR region of H19 gene was significantly lower in the endometriosis group.

What is known already

Endometriosis is characterized by the growth of endometrial-like tissue outside the uterus and has been considered as an epigenetic disease. The lncRNA H19 and insulin-like growth factor–2 (IGF2) genes form a reciprocally imprinted cluster (IGF2/H19). The expression of these two genes is regulated by imprinting control region (ICR). The ICR region is located between these genes and is a differentially methylated region (DMR). The H19 and IGF2 genes are involved in regulating cellular growth and differentiation and might be targeted by MeCP2 (a marker of DNA methylation) for subsequent epigenetic modifications through DMR regulatory region.

Study design, size, duration

In this case-control study, 12 endometrial samples (eutopic) and 12 endometriotic lesions (ectopic) of women with endometriosis and 12 endometrial control samples were analyzed. Control samples were obtained from women who had no evidence of endometriosis during diagnostic laparoscopy. Control and eutopic endometrial samples were obtained by pipelle. Ectopic samples were obtained during laparoscopy. All women signed the informed consent form and did not receive any hormonal treatments during the last three months.

Participants/materials, setting, methods

After endometrial tissues collection, gene expression levels of IGF2 and H19 were evaluated using real-time PCR . The occupancy of MeCP2 on two subregions within DMR region of H19 gene was investigated using chromatin immunoprecipitation (ChIP) followed by real-time PCR. One-way ANOVA was used for data analysis. P value less than 0.05 was considered statistically significant.

Main results and the role of chance

Gene expression profile of H19 and IGF2 was decreased in eutopic and ectopic endometrial lesions of endometriosis group compared with control ones. The decrease in gene expression of H19 in ectopic samples was significant in compared to the control ones while it was nearly significant in compared to the eutopic samples (p = 0.01, p = 0.056, respectively). The ChIP analysis revealed that MeCP2 incorporation in region II (between −3945 and –3818 bp)within DMR region of H19 gene was significantly decreased in eutopic samples compare to control group (p = 0.02) while its decrease was nearly significant in ectopic samples (p = 0.056). However, this DNA methylation profile was not significantly different between eutopic and ectopic endometrial samples in endometriosis in group. Incorporation of MeCP2 in region I (between −2230 and –2103 bp)within DMR region of H19 gene was not significantly different between the eutopic, ectopic and control samples (p > 0.05). (data was presented at 21th Royan International Congress).

Limitations, reasons for caution

The main limitations of this study is its small sample size. For getting more information, we need to monitor this DNA methylation profile in a large number of women with and without endometriosis. Also, more investigations are required to clarify the further epigenetic modifications in this region.

Wider implications of the findings: It seems that reduced expression of IGF2 may be due to hypomethylation of H19-DMR region II while this hypomethylation has no effect on H19 expression in endometriosis. As previously was shown , hypomethylation of H19-DMR causes decrease of IGF2 expression and increase in H19 expression.

Trial registration number

Not applicable

P–341 Epigenetic role of the H2BK5ac histone modification on the expression of ALX1 and PDHX genes in the endometriotic tissues and normal endometrium

Study question

Evolution of the ALX1 and PDHX genes expression and incorporation of H2BK5ac mark on the promoter of these genes in endometriotic tissues versus normal endometrium

Summary answer

Lower incorporation of H2BK5ac mark in ALX1 and PDHX promoters can because to downregulation of these genes in endometriotic tissues compared to normal endometrium.

What is known already

Endometriosis is considered as multifactorial disease affected by genetic, hormonal, and environmental factors. Recent evidences suggest the role of epigenetic mechanisms in this disease. Aristaless-like homeobox1 (ALX1) and Pyruvate Dehydrogenase Protein X (PDHX) genes are considered in this study. Studies show that upregulation of the ALX1 gene cause cell proliferation, migration, and invasion in cancer cells. PDHX is involved in cellular metabolism and acts as a tumor suppressor gene while maintaining normal homeostasis. It is Hypothesized that H2BK5ac which is known as a dynamic marker in promoter regions of active genes, may be involved in regulation of these gene expression.

Study design, size, duration

Ten eutopic and ectopic endometrium tissue, as well as ten normal endometrium, were collected. Ectopic biopsies were obtained using diagnostic laparoscopy, while the endometrial control samples and eutopic samples were collected via pipelle.

Participants/materials, setting, methods

RNA extraction and cDNA synthesis were done then the expression of ALX1 and PDHX genes evaluated by quantitative real-time PCR. Promoter regions of mentioned genes investigated for the incorporation of the epigenetic mark of H2BK5ac using Chromatin immunoprecipitation (ChIP) followed by real-time PCR. Data analysis performed using One-way ANOVA analysis (SPSS software) considered the significant level of P < 0.05.

Main results and the role of chance

Results showed that the expression of ALX1 was significantly decreased in eutopic endometrial samples compared to normal endometrium (p = 0.007). Also, there was a significant reduction in PDHX mRNA level in the eutopic and ectopic samples vs. normal endometrium (p = .017 and p =.021, respectively). The chromatin immunoprecipitation real-time PCR (ChIP PCR) analyses showed significantly lower incorporation of H2BK5ac epigenetic mark in ALX1 promoter in eutopic endometrial samples compared to normal endometrium (p = 0.007). Also, reduced incorporation of H2BK5ac at the PDHX promoter region was observed in both eutopic and ectopic endometrial samples compared to normal endometrium (p = 0.004 and p = 0.003, respectively).

Limitations, reasons for caution

The main limitation of our study is the low number of samples.

Wider implications of the findings: Our results suggest that the marked lower levels of H2BK5ac in regulatory regions of ALX1and PDHX might lead to deregulation of these genes in tissue endometriotic samples.

Trial registration number

‘not applicable’ for non-clinical trials

An embedded implementation based on adaptive filter bank for brain-computer interface systems

BACKGROUND

Brain-computer interface (BCI) is a new communication pathway for users with neurological deficiencies. The implementation of a BCI system requires complex electroencephalography (EEG) signal processing including filtering, feature extraction and classification algorithms. Most of current BCI systems are implemented on personal computers. Therefore, there is a great interest in implementing BCI on embedded platforms to meet system specifications in terms of time response, cost effectiveness, power consumption, and accuracy.

NEW-METHOD

This article presents an embedded-BCI (EBCI) system based on a Stratix-IV field programmable gate array. The proposed system relays on the weighted overlap-add (WOLA) algorithm to perform dynamic filtering of EEG-signals by analyzing the event-related desynchronization/synchronization (ERD/ERS). The EEG-signals are classified, using the linear discriminant analysis algorithm, based on their spatial features.

RESULTS

The proposed system performs fast classification within a time delay of 0.430 s/trial, achieving an average accuracy of 76.80% according to an offline approach and 80.25% using our own recording. The estimated power consumption of the prototype is approximately 0.7 W.

COMPARISON-WITH-EXISTING-METHOD

Results show that the proposed EBCI system reduces the overall classification error rate for the three datasets of the BCI-competition by 5% compared to other similar implementations. Moreover, experiment shows that the proposed system maintains a high accuracy rate with a short processing time, a low power consumption, and a low cost.

CONCLUSIONS

Performing dynamic filtering of EEG-signals using WOLA increases the recognition rate of ERD/ERS patterns of motor imagery brain activity. This approach allows to develop a complete prototype of a EBCI system that achieves excellent accuracy rates.