Detecting Glaucoma With a Portable Brain-Computer Interface for Objective Assessment of Visual Function Loss

The TsiogkaSpaeth grid for detection of neurological visual field defects: a validation study

BACKGROUND

The TsiogkaSpaeth (TS) grid is a new, low-cost, and easy to access portable test for visual field (VF) screening which could be used by clinicians in everyday clinical practice. Our study aimed to determine the validity of an innovative screening grid test for identifying neurological disease-associated VF defects.

METHODS

We enrolled two groups of participants: We assessed the one eye of ten consecutive adult patients with different types of neurological disease associated VF defects and ten eyes of controls in each group. The TS grid test was performed in each group. Sensitivity, specificity, and positive and negative predictive values of the TS grid scotoma area were assessed using the 24-2 VF Humphrey field analyzer (HFA) as the reference standard.

RESULTS

Sensitivity and specificity of the TS grid test were 100% and 90.91%, respectively. The area under curve was 0.9545 with 95% CI 0.87-1.00. There was a significant correlation between the number of missed locations on the TS grid test and the visual field index of the HFA 24-2 (r = 0.9436, P < .0001).

CONCLUSION

The sensitivity and specificity of the TS grid test were high in detecting VF defects in neurological disease. The TS grid test appears to be a reliable, low-cost, and easily accessed alternative to traditional VF tests in diagnosing typical neurological patterns of visual field defects. It would be useful in screening subjects for neurologically derived ocular morbidity in everyday clinical practice and in remote areas deprived of specialized health care services.

Objective detection of visual field defects with multifrequency VEPs

PURPOSE

To correlate multifrequency pattern reversal VEPs in quadrants (QmfrVEPs) with perimetric field losses for objective detection of visual field losses.

METHODS

QmfrVEP measurements were performed using four LED-based checkerboard stimulators to stimulate the four quadrants of the visual field. QmfrVEPs were measured monocularly in 5 normal subjects and in 5 glaucoma patients who showed losses in conventional Octopus perimetry. The pattern reversal frequency varied slightly between the stimulators: (11.92, 12.00, 12.08 and 12.16 reversals/sec). The responses to the different stimuli were identified by discrete Fourier analysis. VEPs were recorded using different electrode configurations, and the recording with the highest signal-to-noise ratio (SNR) was used for further analysis.

RESULTS

QmfrVEP responses from the different quadrants can be reliably measured and separated using the 0.08 reversals/sec interstimulus reversal frequency differences. The signal-to-noise ratio in the four quadrants was significantly correlated with the equivalent visual field losses obtained with perimetry (Spearman rank correlation: P < 0.001). In the five glaucoma patients, the SNR was reduced in 15 out of the 16 quadrants with a perimetric defect, in comparison to the results in quadrants of healthy subjects. This confirms the sensitivity of the procedure.

CONCLUSION

QmfrVEP responses can be measured reliably. This pilot study suggests that high SNR values exclude visual field defects and that focal defects can be identified in glaucoma patients.

TRIAL REGISTRATION

www.

CLINICALTRIALS

gov . NCT00494923.

A general dual-pathway network for EEG denoising

Introduction

Scalp electroencephalogram (EEG) analysis and interpretation are crucial for tracking and analyzing brain activity. The collected scalp EEG signals, however, are weak and frequently tainted with various sorts of artifacts. The models based on deep learning provide comparable performance with that of traditional techniques. However, current deep learning networks applied to scalp EEG noise reduction are large in scale and suffer from overfitting.

Methods

Here, we propose a dual-pathway autoencoder modeling framework named DPAE for scalp EEG signal denoising and demonstrate the superiority of the model on multi-layer perceptron (MLP), convolutional neural network (CNN) and recurrent neural network (RNN), respectively. We validate the denoising performance on benchmark scalp EEG artifact datasets.

Results

The experimental results show that our model architecture not only significantly reduces the computational effort but also outperforms existing deep learning denoising algorithms in root relative mean square error (RRMSE)metrics, both in the time and frequency domains.

Discussion

The DPAE architecture does not require a priori knowledge of the noise distribution nor is it limited by the network layer structure, which is a general network model oriented toward blind source separation.

A data expansion technique based on training and testing sample to boost the detection of SSVEPs for brain-computer interfaces

Objective.Currently, steady-state visual evoked potentials (SSVEPs)-based brain-computer interfaces (BCIs) have achieved the highest interaction accuracy and speed among all BCI paradigms. However, its decoding efficacy depends deeply on the number of training samples, and the system performance would have a dramatic drop when the training dataset decreased to a small size. To date, no study has been reported to incorporate the unsupervised learning information from testing trails into the construction of supervised classification model, which is a potential way to mitigate the overfitting effect of limited samples.Approach.This study proposed a novel method for SSVEPs detection, i.e. cyclic shift trials (CSTs), which could combine unsupervised learning information from test trials and supervised learning information from train trials. Furthermore, since SSVEPs are time-locked and phase-locked to the onset of specific flashes, CST could also expand training samples on the basis of its regularity and periodicity. In order to verify the effectiveness of CST, we designed an online SSVEP-BCI system, and tested this system combined CST with two common classification algorithms, i.e. extended canonical correlation analysis and ensemble task-related component analysis.Main results.CST could significantly enhance the signal to noise ratios of SSVEPs and improve the performance of systems especially for the condition of few training samples and short stimulus time. The online information transfer rate could reach up to 236.19 bits min-1using 36 s calibration time of only one training sample for each category.Significance.The proposed CST method can take full advantages of supervised learning information from training samples and unsupervised learning information of testing samples. Furthermore, it is a data expansion technique, which can enhance the SSVEP characteristics and reduce dependence on sample size. Above all, CST is a promising method to improve the performance of SSVEP-based BCI without any additional experimental burden.

Endpoints for clinical trials in ophthalmology

With the identification of novel targets, the number of interventional clinical trials in ophthalmology has increased. Visual acuity has for a long time been considered the gold standard endpoint for clinical trials, but in the recent years it became evident that other endpoints are required for many indications including geographic atrophy and inherited retinal disease. In glaucoma the currently available drugs were approved based on their IOP lowering capacity. Some recent findings do, however, indicate that at the same level of IOP reduction, not all drugs have the same effect on visual field progression. For neuroprotection trials in glaucoma, novel surrogate endpoints are required, which may either include functional or structural parameters or a combination of both. A number of potential surrogate endpoints for ophthalmology clinical trials have been identified, but their validation is complicated and requires solid scientific evidence. In this article we summarize candidates for clinical endpoints in ophthalmology with a focus on retinal disease and glaucoma. Functional and structural biomarkers, as well as quality of life measures are discussed, and their potential to serve as endpoints in pivotal trials is critically evaluated.

Electroencephalogram-Driven Machine-Learning Scenario for Assessing Impulse Control Disorder Comorbidity in Parkinson's Disease Using a Low-Cost, Custom LEGO-Like Headset

Patients with Parkinson's disease (PD) may develop cognitive symptoms of impulse control disorders (ICDs) when chronically treated with dopamine agonist (DA) therapy for motor deficits. Motor and cognitive comorbidities critically increase the disability and mortality of the affected patients. This study proposes an electroencephalogram (EEG)-driven machine-learning scenario to automatically assess ICD comorbidity in PD. We employed a classic Go/NoGo task to appraise the capacity of cognitive and motoric inhibition with a low-cost, custom LEGO-like headset to record task-relevant EEG activity. Further, we optimized a support vector machine (SVM) and support vector regression (SVR) pipeline to learn discriminative EEG spectral signatures for the detection of ICD comorbidity and the estimation of ICD severity, respectively. With a dataset of 21 subjects with typical PD, 9 subjects with PD and ICD comorbidity (ICD), and 25 healthy controls (HC), the study results showed that the SVM pipeline differentiated subjects with ICD from subjects with PD with an accuracy of 66.3% and returned an around-chance accuracy of 53.3% for the classification of PD versus HC subjects without the comorbidity concern. Furthermore, the SVR pipeline yielded significantly higher severity scores for the ICD group than for the PD group and resembled the ICD vs. PD distinction according to the clinical questionnaire scores, which was barely replicated by random guessing. Without a commercial, high-precision EEG product, our demonstration may facilitate deploying a wearable computer-aided diagnosis system to assess the risk of DA-triggered cognitive comorbidity in patients with PD in their daily environment.

Test-retest repeatability of the imo binocular random single-eye test and Humphrey monocular test in patients with glaucoma

PURPOSE

To evaluate the reproducibility of the imo binocular random single-eye test (BRSET) and Humphrey Field Analyzer (HFA) monocular test in patients with glaucoma.

STUDY DESIGN

Retrospective observational study.

METHODS

We measured the visual fields (VF) of patients with glaucoma using the BRSET and HFA. All tests were repeated two months later. Mean sensitivity (MS), mean deviation (MD), sensitivity at each test location, and reliability indices were compared between the test days. Wilcoxon signed-rank test, interclass correlation coefficient (ICC), correlation coefficients, and Bland-Altman plots were generated for analysis.

RESULTS

We analyzed the VFs of 46 patients with glaucoma. There were no test-retest differences for MS and MD, and ICCs were > 0.9 for MS and MD in both perimeters. Inter-test correlations for MS and MD were high. The limits of agreement (LoAs) (lower, upper limit) between test days for MS were (- 3.4, 4.0) for BRSET and (-3.3, 3.0) for HFA. The LoA for MD was (- 3.3, 3.8) for BRSET and (- 3.2, 2.9) for HFA. Sensitivity at each testing location was more variable between testing days for BRSET than for HFA. For reliability indices, LoAs between testing days were wider for BRSET than for HFA.

CONCLUSION

The imo BRSET showed similar reproducibility to HFA in MS and MD. However, sensitivity at each test location varied more for BRSET than for HFA. Further studies are needed to verify the reproducibility of the imo BRSET.

The Effect of Muscle Artifact Reduction Methods on Few-channel SSVEPs during Head Movements

Brain-computer interfaces (BCIs) with steady-state visual evoked potentials (SSVEPs) caused by flickering stimuli have caught attention as communication tools between human brains and external machines through a head-mounted display (HMD). When applying SSVEP-based BCIs to real-life environments, the head must be moved to watch the stimuli displayed in an HMD, which generates muscular artifacts and significantly reduces BCI performance. In this study, we examined four-class SSVEP identification accuracies by using four artifact reduction methods in the situation of moving the head for both simulation and real datasets. In the simulation dataset, we found that artifact subspace reconstruction (ASR) and multi-scale dictionary learning (MSDL) showed better results especially at low signal-to-noise ratio. In the real dataset, we observed that reducing muscular artifacts resulted in performance degradation for independent component analysis-based methods, while ASR and MSDL showed relatively limited degradation and in some cases improved performance. Our future work is to improve ASR and MSDL for high performance with real data and to apply them to an online SSVEP-based BCI where the user moves his/her head.

GDNet-EEG: An attention-aware deep neural network based on group depth-wise convolution for SSVEP stimulation frequency recognition

Background

Steady state visually evoked potentials (SSVEPs) based early glaucoma diagnosis requires effective data processing (e.g., deep learning) to provide accurate stimulation frequency recognition. Thus, we propose a group depth-wise convolutional neural network (GDNet-EEG), a novel electroencephalography (EEG)-oriented deep learning model tailored to learn regional characteristics and network characteristics of EEG-based brain activity to perform SSVEPs-based stimulation frequency recognition.

Method

Group depth-wise convolution is proposed to extract temporal and spectral features from the EEG signal of each brain region and represent regional characteristics as diverse as possible. Furthermore, EEG attention consisting of EEG channel-wise attention and specialized network-wise attention is designed to identify essential brain regions and form significant feature maps as specialized brain functional networks. Two publicly SSVEPs datasets (large-scale benchmark and BETA dataset) and their combined dataset are utilized to validate the classification performance of our model.

Results

Based on the input sample with a signal length of 1 s, the GDNet-EEG model achieves the average classification accuracies of 84.11, 85.93, and 93.35% on the benchmark, BETA, and combination datasets, respectively. Compared with the average classification accuracies achieved by comparison baselines, the average classification accuracies of the GDNet-EEG trained on a combination dataset increased from 1.96 to 18.2%.

Conclusion

Our approach can be potentially suitable for providing accurate SSVEP stimulation frequency recognition and being used in early glaucoma diagnosis.

Launching Your VR Neuroscience Laboratory

The proliferation and refinement of affordable virtual reality (VR) technologies and wearable sensors have opened new frontiers in cognitive and behavioral neuroscience. This chapter offers a broad overview of VR for anyone interested in leveraging it as a research tool. In the first section, it examines the fundamental functionalities of VR and outlines important considerations that inform the development of immersive content that stimulates the senses. In the second section, the focus of the discussion shifts to the implementation of VR in the context of the neuroscience lab. Practical advice is offered on adapting commercial, off-the-shelf devices to a researcher's specific purposes. Further, methods are explored for recording, synchronizing, and fusing heterogeneous forms of data obtained through the VR system or add-on sensors, as well as for labeling events and capturing game play. The reader should come away with an understanding of fundamental considerations that need to be addressed in order to launch a successful VR neuroscience research program.

Fixed template network and dynamic template network: novel network designs for decoding steady-state visual evoked potentials

Objective. Decomposition methods are efficient to decode steady-state visual evoked potentials (SSVEPs). In recent years, the brain-computer interface community has also been developing deep learning networks for decoding SSVEPs. However, there is no clear evidence that current deep learning models outperform decomposition methods on the SSVEP decoding tasks. Many studies lacked the comparison with state-of-the-art decomposition methods in a fair environment.Approach. This study proposed a novel network design motivated by the works of decomposition methods. Fixed template network (FTN) and dynamic template network (DTN) are two novel networks combining the advantages of fixed templates and subject-specific templates. This study also proposed a data augmentation method for SSVEPs. This study compared the intra-subject classification performance of DTN and FTN with that of state-of-the-art decomposition methods on three public SSVEP datasets.Main results. The results show that both FTN and DTN achieved the suboptimal classification performance compared with state-of-the-art decomposition methods.Significance. Both network designs could enhance the decoding performance of SSVEPs, making them promising networks for improving the practicality of SSVEP-based applications.

Preferential Loss of Contrast Decrement Responses in Human Glaucoma

Purpose

The purpose of this study was to determine whether glaucoma in human patients produces preferential damage to OFF visual pathways, as suggested by animal experimental models, patient electroretinogram (ERG), and retinal imaging data.

Methods

Steady-state visual evoked potentials (SSVEPs) were recorded monocularly from 50 patients with glaucoma and 28 age-similar controls in response to equal Weber contrast increments and decrements presented using 2.73 hertz (Hz) sawtooth temporal waveforms.

Results

The eyes of patients with glaucoma were separated into mild (better than -6 decibel [dB] mean deviation; n = 28) and moderate to severe (worse than -6 dB mean deviation, n = 22) groups based on their Humphrey 24-2 visual field measurements. Response amplitudes and phases from the two glaucoma-severity groups were compared to controls at the group level. SSVEP amplitudes were depressed in both glaucoma groups, more so in the moderate to severe glaucoma group. The differences between controls and the moderate-severe glaucoma groups were more statistically reliable for decrements than for increments. Mean responses to decremental sawtooth stimuli were larger than those to increments in controls and in the mild glaucoma but not in the moderate to severe glaucoma group at the first harmonic. OFF/decrement responses at the first harmonic were faster in controls, but not in patients.

Conclusions

The observed pattern of preferential loss of decremental responses in human glaucoma is consistent with prior reports of selective damage to OFF retinal ganglion cells in murine models and in data from human ERG and retinal imaging. These data motivate pursuit of SSVEP as a biomarker for glaucoma progression.

Rapid Campimetry-A Novel Screening Method for Glaucoma Diagnosis

One of the most important functions of the retina-the enabling of perception of fast movements-is largely suppressed in standard automated perimetry (SAP) and kinetic perimetry (Goldmann) due to slow motion and low contrast between test points and environment. Rapid campimetry integrates fast motion (=10°/4.7 s at 40 cm patient-monitor distance) and high contrast into the visual field (VF) examination in order to facilitate the detection of absolute scotomas. A bright test point moves on a dark background through the central 10° VF. Depending on the distance to the fixation point, the test point automatically changes diameter (≈0.16° to ≈0.39°). This method was compared to SAP (10-2 program) for six subjects with glaucoma. Rapid campimetry proved to be comparable and possibly better than 10-2 SAP in identifying macular arcuate scotomas. In four subjects, rapid campimetry detected a narrow arcuate absolute scotoma corresponding to the nerve fiber course, which was not identified as such with SAP. Rapid campimetry promises a fast screening method for the detection of absolute scotomas in the central 10° visual field, with a potential for cloud technologies and telemedical applications. Our proof-of-concept study motivates systematic testing of this novel method in a larger cohort.

Assessing the Effect of the Refresh Rate of a Device on Various Motion Stimulation Frequencies Based on Steady-State Motion Visual Evoked Potentials

The refresh rate is one of the important parameters of visual presentation devices, and assessing the effect of the refresh rate of a device on motion perception has always been an important direction in the field of visual research. This study examined the effect of the refresh rate of a device on the motion perception response at different stimulation frequencies and provided an objective visual electrophysiological assessment method for the correct selection of display parameters in a visual perception experiment. In this study, a flicker-free steady-state motion visual stimulation with continuous scanning frequency and different forms (sinusoidal or triangular) was presented on a low-latency LCD monitor at different refresh rates. Seventeen participants were asked to observe the visual stimulation without head movement or eye movement, and the effect of the refresh rate was assessed by analyzing the changes in the intensity of their visual evoked potentials. The results demonstrated that an increased refresh rate significantly improved the intensity of motion visual evoked potentials at stimulation frequency ranges of 7-28 Hz, and there was a significant interaction between the refresh rate and motion frequency. Furthermore, the increased refresh rate also had the potential to enhance the ability to perceive similar motion. Therefore, we recommended using a refresh rate of at least 120 Hz in motion visual perception experiments to ensure a better stimulation effect. If the motion frequency or velocity is high, a refresh rate of≥240 Hz is also recommended.

Improving Transfer Performance of Deep Learning with Adaptive Batch Normalization for Brain-computer Interfaces. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021;2021:5800-5803. [PMID: 34892438 DOI: 10.1109/embc46164.2021.9629529] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Recently, transfer learning and deep learning have been introduced to solve intra- and inter-subject variability problems in Brain-Computer Interfaces. However, the generalization ability of these BCIs is still to be further verified in a cross-dataset scenario. This study compared the transfer performance of manifold embedded knowledge transfer and pre-trained EEGNet with three preprocessing strategies. This study also introduced AdaBN for target domain adaptation. The results showed that EEGNet with Riemannian alignment and AdaBN could achieve the best transfer accuracy about 65.6% on the target dataset. This study may provide new insights into the design of transfer neural networks for BCIs by separating source and target batch normalization layers in the domain adaptation process.

Glaucoma Screening Using an iPad-Based Visual Field Test in a West African Population

PURPOSE

To investigate the performance of the Melbourne Rapid Fields (MRF) for use in clinic-based visual field testing in a low-resource setting.

DESIGN

Prospective cross-sectional study.

PARTICIPANTS

One hundred and three participants (66 patients with glaucoma and 37 control participants) attending a clinical appointment at the Tema Eye Center, Tema, Ghana.

METHODS

Patients with glaucoma and control participants underwent MRF and Humphrey Field Analyzer (HFA) testing.

MAIN OUTCOME MEASURES

Mean deviation (MD), pattern standard deviation (PSD), reliability parameters, sensitivity, specificity, and area under the receiver operating characteristic curve.

RESULTS

Mean MD was less negative and mean PSD was more positive on the MRF than the HFA in both groups (all P < 0.001). False-positive and false-negative rates were comparable between methods (P = 0.09 and P = 0.35, respectively). In patients with glaucoma, MD and PSD from the 2 devices were correlated strongly (r = 0.84; P < 0.001) and moderately (r = 0.61; P < 0.001), respectively. Agreement analysis revealed that MRF tended to generate significantly higher MD (bias, 3.3 ± 4.1 dB; P = 0.03) and PSD (bias, 1.9 ± 2.8 dB; P = 0.03) with wide limits of agreement. For detecting moderate to advanced glaucoma, the sensitivity was 60.9% for the MRF and 78.3% for the HFA (P = 0.10); respective specificities were 86.5% and 83.8% (P = 0.76).

CONCLUSIONS

The MRF underestimated MD and overestimated PSD values compared with the HFA. Agreement biases were significant, suggesting a weak agreement between the 2 devices. However, the MRF showed potential for screening in a low-resource setting, particularly for detecting moderate to advanced glaucoma.

Non-invasive electrophysiology in glaucoma, structure and function-a review

Glaucoma, its early diagnosis, and monitoring of interventions remain an ongoing challenge. We here review developments in functional assessment and its relation to morphology, evaluating recent insights in electrophysiology in glaucoma and highlighting how glaucoma research and diagnostics benefit from combined approaches of OCT and electrophysiological investigations. After concise overviews of OCT and non-invasive electrophysiology in glaucoma, we evaluate commonalities and complementarities of OCT and electrophysiology for our understanding of glaucoma. As a specific topic, the dynamic range (floor effects) of the various techniques is discussed.

Enhancing transfer performance across datasets for brain-computer interfaces using a combination of alignment strategies and adaptive batch normalization

Objective. Recently, transfer learning (TL) and deep learning (DL) have been introduced to solve intra- and inter-subject variability problems in brain-computer interfaces (BCIs). However, current TL and DL algorithms are usually validated within a single dataset, assuming that data of the test subjects are acquired under the same condition as that of training (source) subjects. This assumption is generally violated in practice because of different acquisition systems and experimental settings across studies and datasets. Thus, the generalization ability of these algorithms needs further validations in a cross-dataset scenario, which is closer to the actual situation. This study compared the transfer performance of pre-trained deep-learning models with different preprocessing strategies in a cross-dataset scenario.Approach. This study used four publicly available motor imagery datasets, each was successively selected as a source dataset, and the others were used as target datasets. EEGNet and ShallowConvNet with four preprocessing strategies, namely channel normalization, trial normalization, Euclidean alignment, and Riemannian alignment, were trained with the source dataset. The transfer performance of pre-trained models was validated on the target datasets. This study also used adaptive batch normalization (AdaBN) for reducing interval covariate shift across datasets. This study compared the transfer performance of using the four preprocessing strategies and that of a baseline approach based on manifold embedded knowledge transfer (MEKT). This study also explored the possibility and performance of fusing MEKT and EEGNet.Main results. The results show that DL models with alignment strategies had significantly better transfer performance than the other two preprocessing strategies. As an unsupervised domain adaptation method, AdaBN could also significantly improve the transfer performance of DL models. The transfer performance of DL models that combined AdaBN and alignment strategies significantly outperformed MEKT. Moreover, the generalizability of EEGNet models that combined AdaBN and alignment strategies could be further improved via the domain adaptation step in MEKT, achieving the best generalization ability among multiple datasets (BNCI2014001: 0.788, PhysionetMI: 0.679, Weibo2014: 0.753, Cho2017: 0.650).Significance. The combination of alignment strategies and AdaBN could easily improve the generalizability of DL models without fine-tuning. This study may provide new insights into the design of transfer neural networks for BCIs by separating source and target batch normalization layers in the domain adaptation process.

Telehealth and Screening Strategies in the Diagnosis and Management of Glaucoma

Telehealth has become a viable option for glaucoma screening and glaucoma monitoring due to advances in technology. The ability to measure intraocular pressure without an anesthetic and to take optic nerve photographs without pharmacologic pupillary dilation using portable equipment have allowed glaucoma screening programs to generate enough data for assessment. At home, patients can perform visual acuity testing, web-based visual field testing, rebound tonometry, and video visits with the physician to monitor for glaucomatous progression. Artificial intelligence will enhance the accuracy of data interpretation and inspire confidence in popularizing telehealth for glaucoma.

Review of brain encoding and decoding mechanisms for EEG-based brain-computer interface

A brain-computer interface (BCI) can connect humans and machines directly and has achieved successful applications in the past few decades. Many new BCI paradigms and algorithms have been developed in recent years. Therefore, it is necessary to review new progress in BCIs. This paper summarizes progress for EEG-based BCIs from the perspective of encoding paradigms and decoding algorithms, which are two key elements of BCI systems. Encoding paradigms are grouped by their underlying neural meachanisms, namely sensory- and motor-related, vision-related, cognition-related and hybrid paradigms. Decoding algorithms are reviewed in four categories, namely decomposition algorithms, Riemannian geometry, deep learning and transfer learning. This review will provide a comprehensive overview of both modern primary paradigms and algorithms, making it helpful for those who are developing BCI systems.

Detection of fixation points using a small visual landmark for brain-computer interfaces

Objective.The speed of visual brain-computer interfaces (v-BCIs) has been greatly improved in recent years. However, the traditional v-BCI paradigms require users to directly gaze at the intensive flickering items, which would cause severe problems such as visual fatigue and excessive visual resource consumption in practical applications. Therefore, it is imperative to develop a user-friendly v-BCI.Approach.According to the retina-cortical relationship, this study developed a novel BCI paradigm to detect the fixation point of eyes using a small visual stimulus that subtended only 0.6° in visual angle and was out of the central visual field. Specifically, the visual stimulus was treated as a landmark to judge the eccentricity and polar angle of the fixation point. Sixteen different fixation points were selected around the visual landmark, i.e. different combinations of two eccentricities (2° and 4°) and eight polar angles (0,π4,π2,3π4,π,5π4,3π2and7π4). Twelve subjects participated in this study, and they were asked to gaze at one out of the 16 points for each trial. A multi-class discriminative canonical pattern matching (Multi-DCPM) algorithm was proposed to decode the user's fixation point.Main results.We found the visual stimulation landmark elicited different spatial event-related potential patterns for different fixation points. Multi-DCPM could achieve an average accuracy of 66.2% with a standard deviation of 15.8% for the classification of the sixteen fixation points, which was significantly higher than traditional algorithms (p⩽0.001). Experimental results of this study demonstrate the feasibility of using a small visual stimulus as a landmark to track the relative position of the fixation point.Significance.The proposed new paradigm provides a potential approach to alleviate the problem of irritating stimuli in v-BCIs, which can broaden the applications of BCIs.

Objective assessment of impulse control disorder in patients with Parkinson's disease using a low-cost LEGO-like EEG headset: a feasibility study

Background

Patients with Parkinson’s disease (PD) can develop impulse control disorders (ICDs) while undergoing a pharmacological treatment for motor control dysfunctions with a dopamine agonist (DA). Conventional clinical interviews or questionnaires can be biased and may not accurately diagnose at the early stage. A wearable electroencephalogram (EEG)-sensing headset paired with an examination procedure can be a potential user-friendly method to explore ICD-related signatures that can detect its early signs and progression by reflecting brain activity.

Methods

A stereotypical Go/NoGo test that targets impulse inhibition was performed on 59 individuals, including healthy controls, patients with PD, and patients with PD diagnosed by ICDs. We conducted two Go/NoGo sessions before and after the DA-pharmacological treatment for the PD and ICD groups. A low-cost LEGO-like EEG headset was used to record concurrent EEG signals. Then, we used the event-related potential (ERP) analytical framework to explore ICD-related EEG abnormalities after DA treatment.

Results

After the DA treatment, only the ICD-diagnosed PD patients made more behavioral errors and tended to exhibit the deterioration for the NoGo N2 and P3 peak amplitudes at fronto-central electrodes in contrast to the HC and PD groups. Particularly, the extent of the diminished NoGo-N2 amplitude was prone to be modulated by the ICD scores at Fz with marginal statistical significance (r = − 0.34, p = 0.07).

Conclusions

The low-cost LEGO-like EEG headset successfully captured ERP waveforms and objectively assessed ICD in patients with PD undergoing DA treatment. This objective neuro-evidence could provide complementary information to conventional clinical scales used to diagnose ICD adverse effects.

Enhancement for P300-speller classification using multi-window discriminative canonical pattern matching

Objective.P300s are one of the most studied event-related potentials (ERPs), which have been widely used for brain-computer interfaces (BCIs). Thus, fast and accurate recognition of P300s is an important issue for BCI study. Recently, there emerges a lot of novel classification algorithms for P300-speller. Among them, discriminative canonical pattern matching (DCPM) has been proven to work effectively, in which discriminative spatial pattern (DSP) filter can significantly enhance the spatial features of P300s. However, the pattern of ERPs in space varies with time, which was not taken into consideration in the traditional DCPM algorithm.Approach.In this study, we developed an advanced version of DCPM, i.e. multi-window DCPM, which contained a series of time-dependent DSP filters to fine-tune the extraction of spatial ERP features. To verify its effectiveness, 25 subjects were recruited and they were asked to conduct the typical P300-speller experiment.Main results.As a result, multi-window DCPM achieved the character recognition accuracy of 91.84% with only five training characters, which was significantly better than the traditional DCPM algorithm. Furthermore, it was also compared with eight other popular methods, including SWLDA, SKLDA, STDA, BLDA, xDAWN, HDCA, sHDCA and EEGNet. The results showed multi-window DCPM preformed the best, especially using a small calibration dataset. The proposed algorithm was applied to the BCI Controlled Robot Contest of P300 paradigm in 2019 World Robot Conference, and won the first place.Significance.These results demonstrate that multi-window DCPM is a promising method for improving the performance and enhancing the practicability of P300-speller.

Usefulness of virtual reality-based training to diagnose strabismus

To study the usefulness of virtual reality (VR)-based training for diagnosing strabismus. Fourteen residents in ophthalmology performed at least 30 VR training sessions to diagnose esotropia and exotropia. Examinations of real patients with esotropia or exotropia before and after the VR training were video-recorded and presented to a strabismus expert to assess accuracy and performance scores for measuring the deviation angle and diagnosing strabismus with anonymization. A feedback survey regarding the usefulness and ease of use of the VR application was conducted for participants. The mean age of the 14 ophthalmology residents (10 men and 4 women), was 29.7 years. Before VR training, participants showed a mean accuracy score of 14.50 ± 5.45 and a performance score of 9.64 ± 4.67 for measuring the deviation angle and diagnosing strabismus in real patients with strabismus. After VR training, they showed a significantly improved accuracy score of 22.14 ± 4.37 (p = 0.012) and a performance score of 15.50 ± 1.99 (p = 0.011). According to the survey, most participants agreed on the usefulness of VR applications. This study suggests that VR-based training improved ophthalmology residents’ clinical diagnostic skills for strabismus in a short period.

Intraocular Pressure Telemetry for Managing Glaucoma during the COVID-19 Pandemic

PURPOSE

To evaluate in glaucoma patients the feasibility and use of remote monitoring of intraocular pressure (IOP) with an implanted telemetry sensor during the coronavirus disease 2019 (COVID-19) lockdown.

DESIGN

Cross-sectional study.

PARTICIPANTS

Patients previously implanted with a telemetric IOP sensor (Eyemate; Implandata GmbH) were included.

METHODS

Intraocular pressure measurements acquired by the patients during the lockdown were collected by physicians who were located remotely. A questionnaire was sent to 10 participating study centers to evaluate the clinical impact of remote monitoring of IOP via the IOP sensor system.

MAIN OUTCOME MEASURES

Number of patients who obtained home IOP measurements.

RESULTS

Data were available from all centers and from 37 eyes of 37 patients (16 patients with a sulcus-based sensor and 21 patients with a suprachoroidal sensor). Thirty-four patients obtained IOP measurements during the lockdown. Mean age of the patients was 69.3 ± 9.6 years, and 48.6% were women. A total of 8415 IOP measurements from 370 measurement days were obtained. Based on remote IOP measurements, treatment was changed in 5 patients. In another 5 patients, treatment change was considered when physicians received the IOP measurements after the lockdown. Nine of the 10 study centers judged remote IOP measurements to have a clinical impact.

CONCLUSIONS

These results show the feasibility of patient-acquired measurement of IOP in conjunction with remote IOP monitoring by physicians with an implantable sensor. The data obtained impacted clinical decision making, including adjustment of ocular hypotensive therapy and avoiding unnecessary office visits during the COVID-19 pandemic.

The era of artificial intelligence and virtual reality: transforming surgical education in ophthalmology

Training the modern ophthalmic surgeon is a challenging process. Microsurgical education can benefit from innovative methods to practice surgery in low-risk simulations, assess and refine skills in the operating room through video content analytics, and learn at a distance from experienced surgeons. Developments in emerging technologies may allow us to pursue novel forms of instruction and build on current educational models. Artificial intelligence, which has already seen numerous applications in ophthalmology, may be used to facilitate surgical tracking and evaluation. Within immersive technology, growth in the space of virtual reality head-mounted displays has created intriguing possibilities for operating room simulation and observation. Here, we explore the applications of these technologies and comment on their future in ophthalmic surgical education.

A Multifocal SSVEPs-based Brain-Computer Interface with Less Calibration Time

For the past few years, electroencephalogram (EEG)-based brain-computer interfaces (BCIs) have gotten tremendous progress and attracted increasing attention. To broaden the application of BCIs, researchers have focused on the increasement of the BCI instruction number in recent years. However, with a large number of instructions, the BCI calibration time will be too long to be accepted in practical usage. This study proposed a new coding method based on multifocal steady-state visual evoked potentials (mfSSVEPs), in which 16 targets were binary coded by 4 frequencies. Notably, the training data needed for calibration corresponded to only five out of the sixteen targets. Five volunteers were recruited to test this paradigm. Task-related component analysis combined with a probabilistic model were employed for target recognition. As a result, the accuracy could reach as high as 93.1% with 1s-length data. The highest information transfer rate (ITR) was 101.1 bits/min with an average of 73.9 bits/min. The results indicate that this new paradigm is promising to encode a large BCI instruction set with less trainings.

Using Enhanced Depth Imaging Optical Coherence Tomography-Derived Parameters to Discriminate between Eyes with and without Glaucoma: A Cross-Sectional Comparative Study

INTRODUCTION

New technologies have been developed in order to decrease interpersonal influence and subjectivity during the glaucoma diagnosis process. Enhanced depth imaging spectral-domain OCT (EDI OCT) has turned up as a favorable tool for deep optic nerve head (ONH) structures assessment.

OBJECTIVE

A prospective cross-sectional study was conducted to compare the diagnostic performance of different EDI OCT-derived parameters to discriminate between eyes with and without glaucoma.

MATERIAL AND METHODS

The following ONH parameters were measured: lamina cribrosa (LC) thickness and area; prelaminar neural tissue (PLNT) thickness and area; average Bruch's membrane opening - minimum rim width (BMO-MRW), superior BMO-MRW, and inferior BMO-MRW. Peripapillary retinal nerve fiber layer (pRNFL) thickness was also obtained.

RESULTS

Seventy-three participants were included. There were no significant differences between AUCs for average BMO-MRW (0.995), PLNT area (0.968), and average pRNFL thickness (0.975; p ≥ 0.089). However, AUCs for each of these 3 parameters were significantly larger than LC area AUC (0.701; p ≤ 0.001). Sensitivities at 80% specificity were: PLNT area = 92.3%, average BMO-MRW = 97.4%, and average pRNFL thickness = 94.9%.

CONCLUSIONS

Comparing the diagnostic performance of different EDI OCT ONH parameters to discriminate between eyes with and without glaucoma, we found better results for neural tissue-based indexes (BMO-MRW and PLNT area) compared to laminar parameters. In this specific population, these neural tissue-based parameters (including PLNT area, which was investigated by the first time in the present study) had a diagnostic performance comparable to that of the conventional pRNFL thickness protocol.

Robustness analysis of decoding SSVEPs in humans with head movements using a moving visual flicker

OBJECTIVE

The emergence of mobile electroencephalogram (EEG) platforms have expanded the use cases of brain-computer interfaces (BCIs) from laboratory-oriented experiments to our daily life. In challenging situations where humans' natural behaviors such as head movements are unrestrained, various artifacts could deteriorate the performance of BCI applications. This paper explored the effect of muscular artifacts generated by participants' head movements on the signal characteristics and classification performance of steady-state visual evoked potentials (SSVEPs).

APPROACH

A moving visual flicker was employed to induce not only SSVEPs but also horizontal and vertical head movements at controlled speeds, leading to acquiring EEG signals with intensity-manipulated muscular artifacts. To properly induce neck muscular activities, a laser light was attached to participants' heads to give visual feedback; the laser light indicates the direction of the head independently from eye movements. The visual stimulus was also modulated by four distinct frequencies (10, 11, 12, and 13 Hz). The amplitude and signal-to-noise ratio (SNR) were estimated to quantify the effects of head movements on the signal characteristics of the elicited SSVEPs. The frequency identification accuracy was also estimated by using well-established decoding algorithms including calibration-free and fully-calibrated approaches.

MAIN RESULTS

The amplitude and SNR of SSVEPs tended to deteriorate when the participants moved their heads, and this tendency was significantly stronger in the vertical head movements than in the horizontal movements. The frequency identification accuracy also deteriorated in proportion to the speed of head movements. Importantly, the accuracy was significantly higher than its chance-level regardless of the level of artifact contamination and algorithms.

SIGNIFICANCE

The results suggested the feasibility of decoding SSVEPs in humans freely moving their head directions, facilitating the real-world applications of mobile BCIs.

Semi-simulation Experiments for Quantifying the Performance of SSVEP-based BCI after Reducing Artifacts from Trapezius Muscles

Muscular artifacts often contaminate electroencephalograms (EEGs) and deteriorate the performance of brain-computer interfaces (BCIs). Although many artifact reduction techniques are available, most of the studies have focused on their reduction ability (i.e. reconstruction errors), and it has been missing to evaluate their effect on the performance of BCIs. This study aims at evaluating the performance of a state-of-the-art muscular artifact reduction technique on a scenario of a steady-state visual evoked potentials (SSVEPs)based BCI. The performance was evaluated based on a semisimulation setting using a benchmark dataset of SSVEPs artificially contaminated by muscular artifacts acquired from the trapezius. Our results showed that combining the artifact reduction method and the classification algorithm based on the task-related component analysis gained improved classification accuracy. Interestingly, the artifact reduction setting minimizing the reconstruction errors, i.e. elaborately recovering the true EEG waveforms, was inconsistent to the one maximizing the classification performance. The results suggest that artifact reduction methods should be tuned so as to tomaximize performance of BCIs.

Cost-efficient and Custom Electrode-holder Assembly Infrastructure for EEG Recordings

Mobile electroencephalogram (EEG)-sensing technologies have rapidly progressed and made the access of neuroelectrical brain activity outside the laboratory in everyday life more realistic. However, most existing EEG headsets exhibit a fixed design, whereby its immobile montage in terms of electrode density and coverage inevitably poses a great challenge with applicability and generalizability to the fundamental study and application of the brain-computer interface (BCI). In this study, a cost-efficient, custom EEG-electrode holder infrastructure was designed through the assembly of primary components, including the sensor-positioning ring, inter-ring bridge, and bridge shield. It allows a user to (re)assemble a compact holder grid to accommodate a desired number of electrodes only to the regions of interest of the brain and iteratively adapt it to a given head size for optimal electrode-scalp contact and signal quality. This study empirically demonstrated its easy-to-fabricate nature by a low-end fused deposition modeling (FDM) 3D printer and proved its practicability of capturing event-related potential (ERP) and steady-state visual-evoked potential (SSVEP) signatures over 15 subjects. This paper highlights the possibilities for a cost-efficient electrode-holder assembly infrastructure with replaceable montage, flexibly retrofitted in an unlimited fashion, for an individual for distinctive fundamental EEG studies and BCI applications.

Transferring Shared Responses Across Electrode Montages for Facilitating Calibration in High-Speed Brain Spellers

Recent studies have shown that using the user's average steady-state visual evoked responses (SSVEPs) as the template to template-matching methods could significantly improve the accuracy and speed of the SSVEP-based brain- computer interface (BCI). However, collecting the pilot data for each individual can be time-consuming. To resolve this practical issue, this study aims to explore the feasibility of leveraging pre- recorded datasets from the same users by transferring common electroencephalogram (EEG) responses across different sessions with the same or different electrode montages. The proposed method employs spatial filtering techniques including response averaging, canonical correlation analysis (CCA), and task- related component analysis (TRCA) to project scalp EEG recordings onto a shared response domain. The transferability was evaluated by using 40-class SSVEPs recorded from eight subjects with nine electrodes on two different days. Three subsets of electrode montages were selected to simulate different scenarios such as identical, partly overlapped, and non-overlapped electrode placements across two sessions. The target identification accuracy of the proposed methods with transferred training data significantly outperformed a conventional training-free algorithm. The result suggests training data required in the BCI speller could be transferred from different EEG montages and/or headsets.

Facilitating Calibration in High-Speed BCI Spellers via Leveraging Cross-Device Shared Latent Responses

OBJECTIVE

This paper proposes a novel device-to-device transfer-learning algorithm for reducing the calibration cost in a steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) speller by leveraging electroencephalographic (EEG) data previously acquired by different EEG systems.

METHODS

The transferring is done by projecting the scalp-channel EEG signals onto a shared latent domain across devices. Three spatial filtering techniques, including channel averaging, canonical correlation analysis (CCA), and task-related component analysis (TRCA), were employed to extract the shared responses from different devices. The transferred data were integrated into a template-matching-based algorithm to detect SSVEPs. To evaluate its transferability, this paper conducted two sessions of simulated online BCI experiments with ten subjects using 40 visual stimuli modulated by joint frequency-phase coding method. In each session, two different EEG devices were used: first, the Quick-30 system (Cognionics, Inc.) with dry electrodes, and second, the ActiveTwo system (BioSemi, Inc.) with wet electrodes.

RESULTS

The proposed method with CCA- and TRCA-based spatial filters achieved significantly higher classification accuracy compared with the calibration-free standard CCA-based method.

CONCLUSION

This paper validated the feasibility and effectiveness of the proposed method in implementing calibration-free SSVEP-based BCIs.

SIGNIFICANCE

The proposed method has great potentials to enhance practicability and usability of real-world SSVEP-based BCI applications by leveraging user-specific data recorded in previous sessions even with different EEG systems and montages.

Precision medicine to prevent glaucoma-related blindness

PURPOSE OF REVIEW

Approximately 10% of patients become blind despite using evidence-based guidelines developed from clinical trials and epidemiology studies. Our purpose is to review opportunities to decrease glaucoma-related blindness using the emerging principles of precision medicine.

RECENT FINDINGS

The current review focuses on three topics: first, candidate biomarkers for angle-based surgeries, second, head-mounted display (HMD) technology for vision and testing, and third, glaucoma risk alleles discovered by genome-wide association studies. First, in angle-based surgeries, tracers injected into the anterior chamber or Schlemm's canal have allowed visualization of aqueous veins. We describe an innovative use of optical coherence tomography angiography to visualize aqueous veins in a case with 6-year successful outcome following catheter-based trabeculotomy. Second, HMD technology can augment perceived vision and can be used for perimetry testing. Third, developing genetic risk scores that characterize patients who are at highest risk for blindness is a priority. Such biomarker risk scores will integrate genome-wide association study-based risk alleles for glaucoma along with well known demographic and clinical risk factors.

SUMMARY

As we gain more knowledge, precision medicine will enable clinicians to decrease glaucoma-related blindness by providing more timely interventions to those patients who are at highest risk for progression to blindness. VIDEO ABSTRACT: http://links.lww.com/COOP/A29.

Comparison of head-mounted perimeter (imo®) and Humphrey Field Analyzer

Purpose

The head-mounted automated perimeter imo^® is a new portable perimeter that does not require a dark room and can be used to examine patients in any setting. In this study, imo 24plus (1-2) AIZE examinations were compared with previous Humphrey Field Analyzer (HFA) 30-2 (SITA standard) examinations within the same patient.

Patients and methods

imo examinations (either head-mounted [i-H] or fixed [i-F] type) were performed in patients with glaucoma or suspected glaucoma who had already experienced HFA five or more times. Measurement time and correlations of mean deviation (MD) and visual field index (VFI) values were compared between groups for HFA, i-H, i-F, and imo total (i-T). Fixation loss (FL), false-positive (FP), and false-negative (FN) detection rates were compared. The percentage of binocular random single-eye tests under possible non-occlusion conditions using imo was determined. Mann–Whitney U test was performed, and Spearman’s rank-order correlation coefficient was calculated.

Results

The inclusion period was July to December 2016. Among 273 subjects (543 eyes), 147 (292 eyes) were tested with i-H type and 126 (251 eyes) with i-F type. Mean MD values for HFA and i-T were -6.1±7.8 and -6.2±7.1 dB, respectively. Mean measurement times for HFA, i-H, i-F, and i-T were 15.23±2.07, 10.47±2.11, 11.04±2.31, and 10.54±2.19 minutes, respectively (P<0.01 for HFA vs i-H/i-F). Total mean measurement time was shorter by 30.8% for i-T vs HFA. Correlation coefficients of MD and VFI were R²>0.81 for HFA vs i-H and i-F. FP and FN detection rates were significantly higher with i-T than HFA; there was no significant difference in FL. Binocular random single-eye tests were possible in 85% of cases.

Conclusion

imo reduced measurement time by 30.8%. imo VFI and MD values were highly correlated with HFA. As i-F and i-H types produced similar results, imo can be used in accordance with the patient’s situation.

Novel Means of Clinical Visual Function Testing among Glaucoma Patients, Including Virtual Reality

Computed perimetry remains the gold standard of visual field measurement among glaucoma patients. However, several emerging technologies, made possible by advances in computer programming, smartphone, tablet, or virtual reality, allow alternative means of visual function assessment. These new visual tests may one day have a useful complementary role in visual field testing and to bridge the gap between perimetry and daily experience. Many of these emerging technologies have distinct practical advantages over Ganzfield bowl-based computed perimetry. This paper outlines a discussion of some of these emerging techniques in visual function assessment in glaucoma.

EEG-Based Brain-Computer Interfaces

Brain-computer interfaces (BCIs) provide a direct communication channel between human brain and output devices. Due to advantages such as non-invasiveness, ease of use, and low cost, electroencephalography (EEG) is the most popular method for current BCIs. This chapter gives an overview of the current EEG-based BCIs for the main purpose of communication and control. This chapter first provides a taxonomy of the EEG-based BCI systems by categorizing them into three major groups: (1) BCIs based on event-related potentials (ERPs), (2) BCIs based on sensorimotor rhythms, and (3) hybrid BCIs. Next, this chapter describes challenges and potential solutions in developing practical BCI systems toward high communication speed, convenient system use, and low user variation. Then this chapter briefly reviews both medical and non-medical applications of current BCIs. Finally, this chapter concludes with a summary of current stage and future perspectives of the EEG-based BCI technology.

New Technologies for Glaucoma Detection

This review describes some of the most recent advances in the development and application of new technologies for detecting and managing glaucoma, including imaging, visual function testing, and tonometry. The widespread availability of mobile technology in the developing world is improving health care delivery, for example, with smartphones and mobile applications that allow patient data to be assessed remotely by health care providers.

Six-month Longitudinal Comparison of a Portable Tablet Perimeter With the Humphrey Field Analyzer

PURPOSE

To establish the medium-term repeatability of the iPad perimetry app Melbourne Rapid Fields (MRF) compared to Humphrey Field Analyzer (HFA) 24-2 SITA-standard and SITA-fast programs.

DESIGN

Multicenter longitudinal observational clinical study.

METHODS

Sixty patients (stable glaucoma/ocular hypertension/glaucoma suspects) were recruited into a 6-month longitudinal clinical study with visits planned at baseline and at 2, 4, and 6 months. At each visit patients undertook visual field assessment using the MRF perimetry application and either HFA SITA-fast (n = 21) or SITA-standard (n = 39). The primary outcome measure was the association and repeatability of mean deviation (MD) for the MRF and HFA tests. Secondary measures were the point-wise threshold and repeatability for each test, as well as test time.

RESULTS

MRF was similar to SITA-fast in speed and significantly faster than SITA-standard (MRF 4.6 ± 0.1 minutes vs SITA-fast 4.3 ± 0.2 minutes vs SITA-standard 6.2 ± 0.1 minutes, P < .001). Intraclass correlation coefficients (ICC) between MRF and SITA-fast for MD at the 4 visits ranged from 0.71 to 0.88. ICC values between MRF and SITA-standard for MD ranged from 0.81 to 0.90. Repeatability of MRF MD outcomes was excellent, with ICC for baseline and the 6-month visit being 0.98 (95% confidence interval: 0.96-0.99). In comparison, ICC at 6-month retest for SITA-fast was 0.95 and SITA-standard 0.93. Fewer points changed with the MRF, although for those that did, the MRF gave greater point-wise variability than did the SITA tests.

CONCLUSIONS

MRF correlated strongly with HFA across 4 visits over a 6-month period, and has good test-retest reliability. MRF is suitable for monitoring visual fields in settings where conventional perimetry is not readily accessible.