High-Density Electroencephalogram Facilitates the Detection of Small Stimuli in Code-Modulated Visual Evoked Potential Brain-Computer Interfaces.

In recent years, there has been a considerable amount of research on visual evoked potential (VEP)-based brain-computer interfaces (BCIs). However, it remains a big challenge to detect VEPs elicited by small visual stimuli. To address this challenge, this study employed a 256-electrode high-density electroencephalogram (EEG) cap with 66 electrodes in the parietal and occipital lobes to record EEG signals. An online BCI system based on code-modulated VEP (C-VEP) was designed and implemented with thirty targets modulated by a time-shifted binary pseudo-random sequence. A task-discriminant component analysis (TDCA) algorithm was employed for feature extraction and classification. The offline and online experiments were designed to assess EEG responses and classification performance for comparison across four different stimulus sizes at visual angles of 0.5°, 1°, 2°, and 3°. By optimizing the data length for each subject in the online experiment, information transfer rates (ITRs) of 126.48 ± 14.14 bits/min, 221.73 ± 15.69 bits/min, 258.39 ± 9.28 bits/min, and 266.40 ± 6.52 bits/min were achieved for 0.5°, 1°, 2°, and 3°, respectively. This study further compared the EEG features and classification performance of the 66-electrode layout from the 256-electrode EEG cap, the 32-electrode layout from the 128-electrode EEG cap, and the 21-electrode layout from the 64-electrode EEG cap, elucidating the pivotal importance of a higher electrode density in enhancing the performance of C-VEP BCI systems using small stimuli.

An Open Dataset for Wearable SSVEP-Based Brain-Computer Interfaces.

Brain-computer interfaces (BCIs) provide humans a new communication channel by encoding and decoding brain activities. Steady-state visual evoked potential (SSVEP)-based BCI stands out among many BCI paradigms because of its non-invasiveness, little user training, and high information transfer rate (ITR). However, the use of conductive gel and bulky hardware in the traditional Electroencephalogram (EEG) method hinder the application of SSVEP-based BCIs. Besides, continuous visual stimulation in long time use will lead to visual fatigue and pose a new challenge to the practical application. This study provides an open dataset, which is collected based on a wearable SSVEP-based BCI system, and comprehensively compares the SSVEP data obtained by wet and dry electrodes. The dataset consists of 8-channel EEG data from 102 healthy subjects performing a 12-target SSVEP-based BCI task. For each subject, 10 consecutive blocks were recorded using wet and dry electrodes, respectively. The dataset can be used to investigate the performance of wet and dry electrodes in SSVEP-based BCIs. Besides, the dataset provides sufficient data for developing new target identification algorithms to improve the performance of wearable SSVEP-based BCIs.

Volumetric tumor tracking from a single cone-beam X-ray projection image enabled by deep learning.

Radiotherapy serves as a pivotal treatment modality for malignant tumors. However, the accuracy of radiotherapy is significantly compromised due to respiratory-induced fluctuations in the size, shape, and position of the tumor. To address this challenge, we introduce a deep learning-anchored, volumetric tumor tracking methodology that employs single-angle X-ray projection images. This process involves aligning the intraoperative two-dimensional (2D) X-ray images with the pre-treatment three-dimensional (3D) planning Computed Tomography (CT) scans, enabling the extraction of the 3D tumor position and segmentation. Prior to therapy, a bespoke patient-specific tumor tracking model is formulated, leveraging a hybrid data augmentation, style correction, and registration network to create a mapping from single-angle 2D X-ray images to the corresponding 3D tumors. During the treatment phase, real-time X-ray images are fed into the trained model, producing the respective 3D tumor positioning. Rigorous validation conducted on actual patient lung data and lung phantoms attests to the high localization precision of our method at lowered radiation doses, thus heralding promising strides towards enhancing the precision of radiotherapy.

A Calibration-Free Hybrid BCI Speller System Based on High-Frequency SSVEP and sEMG.

Hybrid brain-computer interface (hBCI) systems that combine steady-state visual evoked potential (SSVEP) and surface electromyography (sEMG) signals have attracted attention of researchers due to the advantage of exhibiting significantly improved system performance. However, almost all existing studies adopt low-frequency SSVEP to build hBCI. It produces much more visual fatigue than high-frequency SSVEP. Therefore, the current study attempts to build a hBCI based on high-frequency SSVEP and sEMG. With these two signals, this study designed and realized a 32-target hBCI speller system. Thirty-two targets were separated from the middle into two groups. Each side contained 16 sets of targets with different high-frequency visual stimuli (i.e., 31-34.75 Hz with an interval of 0.25 Hz). sEMG was utilized to choose the group and SSVEP was adopted to identify intra-group targets. The filter bank canonical correlation analysis (FBCCA) and the root mean square value (RMS) methods were used to identify signals. Therefore, the proposed system allowed users to operate it without system calibration. A total of 12 healthy subjects participated in online experiment, with an average accuracy of 93.52 ± 1.66% and the average information transfer rate (ITR) reached 93.50 ± 3.10 bits/min. Furthermore, 12 participants perfectly completed the free-spelling tasks. These results of the experiments indicated feasibility and practicality of the proposed hybrid BCI speller system.

2D/3D Non-Rigid Image Registration via Two Orthogonal X-ray Projection Images for Lung Tumor Tracking.

Two-dimensional (2D)/three-dimensional (3D) registration is critical in clinical applications. However, existing methods suffer from long alignment times and high doses. In this paper, a non-rigid 2D/3D registration method based on deep learning with orthogonal angle projections is proposed. The application can quickly achieve alignment using only two orthogonal angle projections. We tested the method with lungs (with and without tumors) and phantom data. The results show that the Dice and normalized cross-correlations are greater than 0.97 and 0.92, respectively, and the registration time is less than 1.2 seconds. In addition, the proposed model showed the ability to track lung tumors, highlighting the clinical potential of the proposed method.

Facilitating Applications of SSVEP-Based BCIs by Within-Subject Information Transfer.

The steady-state visual evoked potential based brain-computer interface (SSVEP-BCI) can provide high-speed alternative and augmentative communication in real-world applications. For individuals using a long-term BCI, within-subject (i.e., cross-day and cross-electrode) transfer learning could improve the BCI performance and reduce the calibration burden. To validate the within-subject transfer learning scheme, this study designs a 40-target SSVEP-BCI. Sixteen subjects are recruited, each of whom has performed experiments on three different days and has undergone the experiments of the SSVEP-BCIs based on the dry and wet electrodes. Several transfer directions, including the cross-day directions in parallel with the cross-electrode directions, are analyzed, and it is found that the transfer learning-based approach can maintain stable performance by zero training. Compared with the fully calibrated approaches, the transfer learning-based approach can achieve significantly better or comparable performance in different transfer directions. This result verifies that the transfer learning-based scheme is well suited for implementing a high-speed zero-training SSVEP-BCI, especially the dry electrode-based SSVEP-BCI system. A validation experiment of the cross-day wet-to-dry transfer, involving nine subjects, has shown that the average accuracy is 85.97 ± 5.60% for the wet-to-dry transfer and 77.69 ± 6.42% for the fully calibrated method with dry electrodes. By leveraging the electroencephalography data acquired on different days by different electrodes via transfer learning, this study lays the foundation for facilitating the long-term usage of the SSVEP-BCI and advancing the frontier of the dry electrode-based SSVEP-BCI in real-world applications.

A deep unsupervised learning framework for the 4D CBCT artifact correction.

Objective.Four-dimensional cone-beam computed tomography (4D CBCT) has unique advantages in moving target localization, tracking and therapeutic dose accumulation in adaptive radiotherapy. However, the severe fringe artifacts and noise degradation caused by 4D CBCT reconstruction restrict its clinical application. We propose a novel deep unsupervised learning model to generate the high-quality 4D CBCT from the poor-quality 4D CBCT.Approach.The proposed model uses a contrastive loss function to preserve the anatomical structure in the corrected image. To preserve the relationship between the input and output image, we use a multilayer, patch-based method rather than operate on entire images. Furthermore, we draw negatives from within the input 4D CBCT rather than from the rest of the dataset.Main results.The results showed that the streak and motion artifacts were significantly suppressed. The spatial resolution of the pulmonary vessels and microstructure were also improved. To demonstrate the results in the different directions, we make the animation to show the different views of the predicted correction image in the supplementary animation.Significance.The proposed method can be integrated into any 4D CBCT reconstruction method and maybe a practical way to enhance the image quality of the 4D CBCT.

A Deep Unsupervised Learning Model for Artifact Correction of Pelvis Cone-Beam CT.

PURPOSE: In recent years, cone-beam computed tomography (CBCT) is increasingly used in adaptive radiation therapy (ART). However, compared with planning computed tomography (PCT), CBCT image has much more noise and imaging artifacts. Therefore, it is necessary to improve the image quality and HU accuracy of CBCT. In this study, we developed an unsupervised deep learning network (CycleGAN) model to calibrate CBCT images for the pelvis to extend potential clinical applications in CBCT-guided ART. METHODS: To train CycleGAN to generate synthetic PCT (sPCT), we used CBCT and PCT images as inputs from 49 patients with unpaired data. Additional deformed PCT (dPCT) images attained as CBCT after deformable registration are utilized as the ground truth before evaluation. The trained uncorrected CBCT images are converted into sPCT images, and the obtained sPCT images have the characteristics of PCT images while keeping the anatomical structure of CBCT images unchanged. To demonstrate the effectiveness of the proposed CycleGAN, we use additional nine independent patients for testing. RESULTS: We compared the sPCT with dPCT images as the ground truth. The average mean absolute error (MAE) of the whole image on testing data decreased from 49.96 ± 7.21HU to 14.6 ± 2.39HU, the average MAE of fat and muscle ROIs decreased from 60.23 ± 7.3HU to 16.94 ± 7.5HU, and from 53.16 ± 9.1HU to 13.03 ± 2.63HU respectively. CONCLUSION: We developed an unsupervised learning method to generate high-quality corrected CBCT images (sPCT). Through further evaluation and clinical implementation, it can replace CBCT in ART.

Artificial intelligence-based bone-enhanced magnetic resonance image-a computed tomography/magnetic resonance image composite image modality in nasopharyngeal carcinoma radiotherapy.

BACKGROUND: In the radiotherapy of nasopharyngeal carcinoma (NPC), magnetic resonance imaging (MRI) is widely used to delineate tumor area more accurately. While MRI offers the higher soft tissue contrast, patient positioning and couch correction based on bony image fusion of computed tomography (CT) is also necessary. There is thus an urgent need to obtain a high image contrast between bone and soft tissue to facilitate target delineation and patient positioning for NPC radiotherapy. In this paper, our aim is to develop a novel image conversion between the CT and MRI modalities to obtain clear bone and soft tissue images simultaneously, here called bone-enhanced MRI (BeMRI). METHODS: Thirty-five patients were retrospectively selected for this study. All patients underwent clinical CT simulation and 1.5T MRI within the same week in Shenzhen Second People's Hospital. To synthesize BeMRI, two deep learning networks, U-Net and CycleGAN, were constructed to transform MRI to synthetic CT (sCT) images. Each network used 28 patients' images as the training set, while the remaining 7 patients were used as the test set (~1/5 of all datasets). The bone structure from the sCT was then extracted by the threshold-based method and embedded in the corresponding part of the MRI image to generate the BeMRI image. To evaluate the performance of these networks, the following metrics were applied: mean absolute error (MAE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). RESULTS: In our experiments, both deep learning models achieved good performance and were able to effectively extract bone structure from MRI. Specifically, the supervised U-Net model achieved the best results with the lowest overall average MAE of 125.55 (P<0.05) and produced the highest SSIM of 0.89 and PSNR of 23.84. These results indicate that BeMRI can display bone structure in higher contrast than conventional MRI. CONCLUSIONS: A new image modality BeMRI, which is a composite image of CT and MRI, was proposed. With high image contrast of both bone structure and soft tissues, BeMRI will facilitate tumor localization and patient positioning and eliminate the need to frequently check between separate MRI and CT images during NPC radiotherapy.

Anodal occipital tDCS enhances spontaneous alpha activity.

Transcranial direct current stimulation (tDCS) is a form of brain stimulation technique that modulates neuronal excitability changes in targeted cerebral areas through a constant low current. The existing studies mainly concentrated in tDCS effects on motor cortex. The number of tDCS studies targeting visual area is sparse. And parameters of tDCS on the visual cortex are not well optimized yet. Therefore, this study explored the effect of anodal occipital tDCS in eyes-open resting state to disclose possible modulation to spontaneous brain activity by electroencephalography (EEG). Fifteen healthy subjects were involved in this study. Each subject endured sham and anodal tDCS in turn. 2 mA tDCS was applied over 21 min with Oz-Cz montage. Amplitudes of spontaneous brain activities were evaluated for each experimental condition. Compared with pre-stimulation and sham tDCS, anodal tDCS caused an obvious increment in parieto-occipital alpha activity. These results demonstrated electrophysiological changes in EEG oscillations induced by anodal occipital tDCS, and would help to improve the understanding of modulation of tDCS-induced visual cortex excitability changes in humans.

Mental Fatigue Estimation Using EEG in a Vigilance Task and Resting States.

Mental fatigue induced by long time mental work can cause deterioration in task performance and increase the risk of accidents. Recently, electroencephalogram (EEG)-based monitoring of mental fatigue has received increasing attention in the field of brain-computer interfaces (BCI). This study aims to employ EEG signals to measure the mental fatigue level by estimating reaction time (RT) in a psychomotor vigilance task (PVT). In a 36-hour sleep deprivation experiment, EEG data from 18 subjects were recorded every four hours in nine blocks, each consisting of three tasks: a 6-minute PVT task and two 3-minute resting states (eyes closed and eyes open). The mean RT in the PVT task showed a generally increasing trend during the 36-hour awake period, reflecting the increase of fatigue over time. For each task, multiple EEG features were extracted and selected to better estimate RT using a multiple linear regression (MLR) method. The correlation between predicted RT and actual RT was evaluated using a leave-one-subject-out (LOSO) validation strategy. After parameter optimization, EEG data from the PVT task obtained a mean correlation coefficient of $0.81 \pm 0.16$ across all subjects. Resting-state EEG data showed lower correlations (eyes-closed: $0.65 \pm 0.20$, eyes-open: $0.50 \pm 0.30)$ partially due to the involvement of shorter data lengths. These results demonstrate the feasibility and robustness of the EEG-based fatigue monitoring method, which could be potential for applications in operational environments.

Standardized shrinking LORETA-FOCUSS (SSLOFO): a new algorithm for spatio-temporal EEG source reconstruction.

This paper presents a new algorithm called Standardized Shrinking LORETA-FOCUSS (SSLOFO) for solving the electroencephalogram (EEG) inverse problem. Multiple techniques are combined in a single procedure to robustly reconstruct the underlying source distribution with high spatial resolution. This algorithm uses a recursive process which takes the smooth estimate of sLORETA as initialization and then employs the re-weighted minimum norm introduced by FOCUSS. An important technique called standardization is involved in the recursive process to enhance the localization ability. The algorithm is further improved by automatically adjusting the source space according to the estimate of the previous step, and by the inclusion of temporal information. Simulation studies are carried out on both spherical and realistic head models. The algorithm achieves very good localization ability on noise-free data. It is capable of recovering complex source configurations with arbitrary shapes and can produce high quality images of extended source distributions. We also characterized the performance with noisy data in a realistic head model. An important feature of this algorithm is that the temporal waveforms are clearly reconstructed, even for closely spaced sources. This provides a convenient way to estimate neural dynamics directly from the cortical sources.

Spatial resolution improvement of 3D EIT images by the shrinking sLORETA-FOCUSS algorithm.

This paper describes the use of the shrinking sLORETA-FOCUSS algorithm to improve the spatial resolution of three-dimensional (3D) EIT images. Conventional EIT yields inaccurate, low spatial resolution images, due to noise, the low sensitivity of boundary voltages to inner conductivity perturbations and a limited number of boundary voltage measurements. The focal underdetermined system solver (FOCUSS) algorithm produces a localized energy solution based on the weighted minimum-norm least-squares (MNLS) solution. It was successfully applied for the spatial resolution improvement of EIT images of simulated and tank data for a 2D homogeneous circular disc. However, due to the fact that a 3D mesh system contains many more elements, much more memory is required to store the weighting matrix. In order to extend the work to 3D, the shrinking-FOCUSS method is utilized to shrink the solution space as well as the weighting matrix in each iteration step. The solution of the standardized low resolution electromagnetic tomography algorithm (sLORETA) is adopted as the initial estimate of the shrinking-FOCUSS. The effectiveness is verified by implementing the new algorithm on tank data for a three-dimensional homogeneous sphere.

The spatial resolution improvement of EIT images by GVSPM-FOCUSS algorithm.

The focal underdetermined system solver (FOCUSS) algorithm is a recursive algorithm to find the localized energy solution. It is an initialization-dependent algorithm. The generalized vector sample pattern matching (GVSPM) method has been applied to solve the inverse problem of electrical impedance tomography (EIT) and obtain smooth reconstructed images. By combining the GVSPM solution as the initial estimation of the FOCUSS algorithm, an idea termed the GVSPM-FOCUSS method is presented in this paper to improve the spatial resolution and precision of localization for EIT images. The comparisons are carried out between the EIT images reconstructed with the GVSPM-FOCUSS method and the GVSPM method alone. The effectiveness is verified by simulated and tank data for a model of a two-dimensional homogeneous circular disk.

The application of the generalized vector sample pattern matching method for EIT image reconstruction.

This paper presents a new application of a generalized vector sample pattern matching (GVSPM) method for image reconstruction of conductivity changes in electrical impedance tomography. GVSPM is an iterative method for linear inverse problems. The key concept of the GVSPM is that the objective function is defined in terms of an angular component between the inner product of the known vector and solution of a system of equations. Comparisons are presented between images of simulated and experimental data, reconstructed using truncated singular value decomposition and GVSPM. In both cases, a normalized sensitivity matrix is constructed using the finite volume method to solve the forward problem.

Transient impact of spike on theta rhythm in temporal lobe epilepsy.

Epileptic spike is an indicator of hyper-excitability and hyper-synchrony of neural networks. While cognitive deficit in epilepsy is a common observation, how spikes transiently influence brain oscillations, especially those essential for cognitive functions, remains obscure. Here we aimed to quantify the transient impacts of sporadic spikes on theta oscillations and investigate how such impacts may evolve during epileptogenesis. Longitudinal depth EEG data were recorded in the CA1 area of pilocarpine temporal lobe epilepsy (TLE) rat models. Phase stability, a measure of synchrony, and theta power were estimated around spikes as well as in the protracted spike-free periods (FP) at least 1h after spike bursts. We found that the change in theta power did not correlate with the change in phase stability. More importantly, the impact of spikes on theta rhythm was highly time-dependent. While theta power decreased abruptly after spikes both in the latent and chronic stages, changes of theta phase stability demonstrated opposite trends in the latent and chronic stages, potentially due to the substantial reorganization of neural circuits along epileptogenesis. During FP, theta phase stability was significantly higher than the baseline level before injections, indicating that hyper-synchrony remained even hours after the spike bursts. We concluded that spikes have transient negative effects on theta rhythm, however, impacts are different during latent and chronic stages, implying that its influence on cognitive processes may also change over time during epileptogenesis.

Destructive power dynamics of alpha-theta oscillations via spike and wave in CA3.

The power dynamics of alpha-theta oscillations via inter-ictal spikes and waves (SWs) in CA3 is investigated by means of Hilbert transform and the statistical method based on CA3 channel of LFP(Local Field Potention) data sampled on total 6 rats in resting with sniffing and of iEEG data on total 10 patients in quiet wakefulness. The comparison of alpha-theta power is done between the inter-ictal groups and control groups. It is concluded that the inter-ictal SWs can disrupt the power of alpha-theta oscillations, leading to the decreased power after SW. Because the alpha-theta oscillations are related with the cognition, it is estimated that the inter-ictal SWs can negatively affecte the cognitive function during the inter-ictal dynamics, although the alpha-theta power will be recoverable in some days after injections, even exceed over the power level before injections.

EIT images with improved spatial resolution using a realistic head model.

A recursive algorithm is presented to improve the spatial resolution of 3-D Electrical Impedance Tomography (EIT) images in a four-shell realistic head model. In this algorithm, the low spatial resolution image derived from the standardized low resolution electromagnetic tomography algorithm (sLORETA) is chosen to be the initial estimate for the Focal Underdetermined System Solver (FOCUSS), and a shrinking strategy is adopted for adjusting the source space during iteration process in FOCUSS. Images are presented with improved spatial resolution and the algorithm effectiveness is verified on simulated data by setting two perturbations in the movement and visual regions of the brain.

RBF network based on artificial immune algorithm for regional head conductivity estimation.

This paper presents a novel Radial Basis Function (RBF) neural network model based on Artificial Immune principle, termed AI-based RBF, to estimate the regional head tissue conductivity. In this model, immune learning algorithm is used for determining the number and location of the centers of the hidden layer by regarding the input data of network as antigens, and the centers of the hidden layer as antibodies. The least square algorithm is adopted for achieving the weights of the output layer. With a 2-D concentric circular model of 3 layers, the higher precision and less computation time by this strategy are obtained than those by RBF model.

Tissue conductivity estimation in two-dimension head model based on support vector machine.

Estimating head tissue conductivity for each layer is a high dimensional, non-linear and ill-posed problem which is part of Electrical Impedance Tomography (EIT) inverse problem. Traditional methods have many difficulties in resolving this problem. Support Vector Machine (SVM) based on Statistical Learning Theory (SLT) is a new kind of learning method including Support Vector Classification (SVC) and Support Vector Regression (SVR). A new method using SVR is proposed to solve the problem in multi-input and multi-output system named Multi-SVM (MSVM). Tissue conductivity for each layer in 2-D head model is estimated effectively by MSVM. Compared with wavelet neural network method, MSVM not only obtains higher accuracy of learning, it also has greater generalization ability and faster computing speed as our experiment demonstrates.