Imagery Training Research Articles

Addressing the Intra-class Mode Collapse Problem using Adaptive Input Image Normalization in GAN-based X-ray Images.

Biomedical image datasets can be imbalanced due to the rarity of targeted diseases. Generative Adversarial Networks play a key role in addressing this imbalance by enabling the generation of synthetic images to augment datasets. It is important to generate synthetic images that incorporate a diverse range of features to accurately represent the distribution of features present in the training imagery. Furthermore, the absence of diverse features in synthetic images can degrade the performance of machine learning classifiers. The mode collapse problem impacts Generative Adversarial Networks' capacity to generate diversified images. Mode collapse comes in two varieties: intra-class and inter-class. In this paper, the intra-class mode collapse problem is investigated, and its subsequent impact on the diversity of synthetic X-ray images is evaluated. This work contributes an empirical demonstration of the benefits of integrating the adaptive input-image normalization for the Deep Convolutional GAN to alleviate the intra-class mode collapse problem. Results demonstrate that the DCGAN with adaptive input-image normalization outperforms DCGAN with un-normalized X-ray images as evident by the superior diversity scores.

A Pursuit of the Degree of Nonlinearity for β Oscillations under Motor Imagery.

The power of β oscillations is an essential pathological biomarker for movement disorders, parkinsonism in particular. Motor imagery training was reported to support self-regulate such β oscillations. Past studies had focused on the modulation of β oscillatory power per se, ignoring the intrinsic oscillatory characteristics-the nonlinearity of the waveform. This work applied ensemble empirical mode decomposition to decompose neural activities in multiple frequency bands without destroying the temporal characteristics of the raw signal at all scales. We explored the dynamics of the degree of nonlinearity plus the averaged power across all periods and frequency bands of interest and tested how motor imagery may or may not induce nonlinearities under various frequency bands. With motor imagery, the degree of nonlinearity for the β activity is significantly suppressed referenced to that without, of note, and the average power fails to present significant differences between segments with and without motor imagery training. Our results indicate that the degree of nonlinearity is a complementary and vital biomarker as the average power for β oscillations, thereby providing theoretical support for the possible application in motor imagery therapy. Clinical Relevance- This suggests that motor imagery can suppress irregular patterns of β oscillations for healthy, and the degree of nonlinearity is an effective feature in improving classification in training states for the MI-neurofeedback paradigm compared to that of the averaged power.

Examining the frequency variable in the imagery dose-response relationship

Imagery training is a well-known technique in sport psychology that it is often applied to improving skill performance in a range of sports. In this study, the central aim was to experimentally examine the effect of different imagery frequencies (3, 4, 5 imagery sessions per week) on basketball shooting performance. We applied a new imagery dose-response protocol, in which we varied frequency, but systematically held the other two key imagery dose variables (repetitions and duration of sessions) constant. Participants were 40 male basketball players (Mage = 20.92, SD = 3.01) who were allocated into four conditions: 3 imagery sessions per week, 4 imagery sessions per week, 5 imagery sessions per week, and a control condition. All 3 imagery conditions had 4 weeks of imagery training. For all four conditions, we measured free throw shooting (FTS) at pre-test, Week 1, 2, 3, post-test, and retention test (Week 5). Control condition participants performed their usual basketball practice with no imagery training. Results showed that the 4 imagery sessions per week condition had the highest FTS means at post-test and retention test, with FTS means that were significantly higher than the control condition at post-test and retention test. The findings and information form this study could contribute to the design of effective imagery training by supporting athletes and coaches to tailor imagery programs. Moreover, the imagery dose-response protocol utilised in this study has potential application to further examine imagery dose-response relationships.

Research on Rehabilitation Training Strategies Using Multimodal Virtual Scene Stimulation.

It is difficult for stroke patients with flaccid paralysis to receive passive rehabilitation training. Therefore, virtual rehabilitation technology that integrates the motor imagery brain-computer interface and virtual reality technology has been applied to the field of stroke rehabilitation and has evolved into a physical rehabilitation training method. This virtual rehabilitation technology can enhance the initiative and adaptability of patient rehabilitation. To maximize the deep activation of the subjects motor nerves and accelerate the remodeling mechanism of motor nerve function, this study designed a brain-computer interface rehabilitation training strategy using different virtual scenes, including static scenes, dynamic scenes, and VR scenes. Including static scenes, dynamic scenes, and VR scenes. We compared and analyzed the degree of neural activation and the recognition rate of motor imagery in stroke patients after motor imagery training using stimulation of different virtual scenes, The results show that under the three scenarios, The order of degree of neural activation and the recognition rate of motor imagery from high to low is: VR scenes, dynamic scenes, static scenes. This paper provided the research basis for a virtual rehabilitation strategy that could integrate the motor imagery brain-computer interface and virtual reality technology.

Kinesthetic motor-imagery training improves performance on lexical-semantic access.

The objective of this study was to evaluate the effect of Motor Imagery (MI) training on language comprehension. In line with literature suggesting an intimate relationship between the language and the motor system, we proposed that a MI-training could improve language comprehension by facilitating lexico-semantic access. In two experiments, participants were assigned to a kinesthetic motor-imagery training (KMI) group, in which they had to imagine making upper-limb movements, or to a static visual imagery training (SVI) group, in which they had to mentally visualize pictures of landscapes. Differential impacts of both training protocols on two different language comprehension tasks (i.e., semantic categorization and sentence-picture matching task) were investigated. Experiment 1 showed that KMI training can induce better performance (shorter reaction times) than SVI training for the two language comprehension tasks, thus suggesting that a KMI-based motor activation can facilitate lexico-semantic access after only one training session. Experiment 2 aimed at replicating these results using a pre/post-training language assessment and a longer training period (four training sessions spread over four days). Although the improvement magnitude between pre- and post-training sessions was greater in the KMI group than in the SVI one on the semantic categorization task, the sentence-picture matching task tended to provide an opposite pattern of results. Overall, this series of experiments highlights for the first time that motor imagery can contribute to the improvement of lexical-semantic processing and could open new avenues on rehabilitation methods for language deficits.

Motor Imagery Combined With Physical Training Improves Response Inhibition in the Stop Signal Task.

BackgroundMotor imagery training has a similar effect to that of physical training on motor performance. The objective of this study was to investigate the short-term effectiveness of motor imagery training on response inhibition using the stop signal task (SST).MethodsParticipants were divided into a physical training group (PT, n = 17), a motor imagery training group (MIT, n = 17), and a motor imagery combined with physical training group (MIPT, n = 17). All participants performed 10 SST training sessions over 5 days. Both stop signal reaction time (SSRT) and non-signal reaction time (NSRT) were measured before and after SST training.ResultsThere were significant interaction (time × group) and time effects, although the group effect was not statistically significant. Bonferroni post hoc analysis showed that MIPT group revealed a significantly greater change in SSRT than PT and MIT groups, while there was no significant difference between PT and MIT groups. SSRT significantly decreased after training in all groups. In NSRT, there was a significant effect of time, but there was no significant interaction effect (time × group) or group effect.ConclusionResponse inhibition could be enhanced via training, and it was most effective when motor imagery and physical training were combined. We demonstrate that motor imagery training significantly improves response inhibition and should be accompanied by physical training when performing SST.

Embodiment Comfort Levels During Motor Imagery Training Combined With Immersive Virtual Reality in a Spinal Cord Injury Patient.

Brain–machine interfaces combining visual, auditory, and tactile feedback have been previously used to generate embodiment experiences during spinal cord injury (SCI) rehabilitation. It is not known if adding temperature to these modalities can result in discomfort with embodiment experiences. Here, comfort levels with the embodiment experiences were investigated in an intervention that required a chronic pain SCI patient to generate lower limb motor imagery commands in an immersive environment combining visual (virtual reality -VR), auditory, tactile, and thermal feedback. Assessments were made pre-/ post-, throughout the intervention (Weeks 0–5), and at 7 weeks follow up. Overall, high levels of embodiment in the adapted three-domain scale of embodiment were found throughout the sessions. No significant adverse effects of VR were reported. Although sessions induced only a modest reduction in pain levels, an overall reduction occurred in all pain scales (Faces, Intensity, and Verbal) at follow up. A high degree of comfort in the comfort scale for the thermal-tactile sleeve, in both the thermal and tactile feedback components of the sleeve was reported. This study supports the feasibility of combining multimodal stimulation involving visual (VR), auditory, tactile, and thermal feedback to generate embodiment experiences in neurorehabilitation programs.

Brain Function and Upper Limb Deficit in Stroke With Motor Execution and Imagery: A Cross-Sectional Functional Magnetic Resonance Imaging Study

BackgroundMotor imagery training might be helpful in stroke rehabilitation. This study explored if a specific modulation of movement-related regions is related to motor imagery (MI) ability.MethodsTwenty-three patients with subcortical stroke and 21 age-matched controls were recruited. They were subjectively screened using the Kinesthetic and Visual Imagery Questionnaire (KVIQ). They then underwent functional magnetic resonance imaging (fMRI) while performing three repetitions of different motor tasks (motor execution and MI). Two separate runs were acquired [motor execution tasks (ME and rest) and motor imagery (MI and rest)] in a block design. For the different tasks, analyses of cerebral activation and the correlation of motor/imagery task-related activity and KVIQ scores were performed.ResultsDuring unaffected hand (UH) active grasp movement, we observed decreased activations in the contralateral precentral gyrus (PreCG), contralateral postcentral gyrus (PoCG) [p < 0.05, family wise error (FWE) corrected] and a positive correlation with the ability of FMA-UE (PreCG: r = 0.46, p = 0.028; PoCG: r = 0.44, p = 0.040). During active grasp of the affected hand (AH), decreased activation in the contralateral PoCG was observed (p < 0.05, FWE corrected). MI of the UH induced significant activations of the contralateral superior frontal gyrus, opercular region of the inferior frontal gyrus, and ipsilateral ACC and deactivation in the ipsilateral supplementary motor area (p < 0.05, AlphaSim correction). Ipsilateral anterior cingulate cortex (ACC) activity negatively correlated with MI ability (r = =–0.49, p = 0.022). Moreover, we found significant activation of the contralesional middle frontal gyrus (MFG) during MI of the AH.ConclusionOur results proved the dominant effects of MI dysfunction that exist in stroke during the processing of motor execution. In the motor execution task, the enhancement of the contralateral PreCG and PoCG contributed to reversing the motor dysfunction, while in the MI task, inhibition of the contralateral ACC can increase the impaired KVIQ ability. The bimodal balance recovery model can explain our results well. Recognizing neural mechanisms is critical to helping us formulate precise strategies when intervening with electrical or magnetic stimulation.

Intervention Platform for Action Observation and Motor Imagery Training After Stroke: Usability Test.

Action observation (AO) and motor imagery (MI) are considered as promising therapeutic approaches in the rehabilitation of patients after a stroke (PaS). Observing and mentally rehearsing motor movements stimulate the motor system in the brain and result in a positive effect on movement execution. To support patients in the early rehabilitation phase after a stroke, ANIMATE, a digital health intervention platform was developed. The platform guides the user through 6 activities of daily living by observing and imagining the corresponding movements. We conducted a scenario-based usability test with 9 PaS at a rehabilitation centre to identify existing usability issues. PaS found the app easy to use and they could interact with it without problems. Although they judged the app as useful, they stated to be not willing to use the app on a regular basis. Including features for customising ANIMATE regarding the individual rehabilitation goals and needs of PaS, as well as personalisation could help in increasing the motivation to use and the benefits of the platform.

Mental Imagery to Reduce Alcohol-related harm in patients with alcohol dependence and alcohol-related liver damaGE: the MIRAGE pilot trial protocol

IntroductionIn the UK, alcohol use is the main driver of chronic liver disease and each year results in over 1 million unplanned hospital admissions and over 25 000 deaths from...

Clinical and Neurophysiological Effects of Progressive Movement Imagery Training for Pathological Pain

Movement limitation is a common characteristic of chronic pain such that pain prevents the very movement and activity that is most likely to promote recovery. This is particularly the case for pathological pain states such as complex regional pain syndrome (CRPS). One clinical approach to CRPS that has growing evidence of efficacy involves progressive movement imagery training. Graded Motor Imagery (GMI) targets clinical and neurophysiological effects through a stepwise progression through implicit and explicit movement imagery training, mirror therapy and then functional tasks. Here we review experiences from over 20 years of clinical and research experience with GMI. We situate GMI in terms of its historical underpinnings, the benefits and outstanding challenges of its implementation, its potential application beyond CRPS. We then review the neuropathological targets of GMI and current thought on its effects on neurophysiological biomarkers. PerspectiveThis article provides an overview of our experiences with graded motor imagery training over the last 20 years focussing on the treatment of CRPS. It does both cover the theoretical underpinnings for this treatment approach, biomarkers which indicate potential changes driven by GMI, and experiences for achieving optimal treatment results.

Effectiveness of Tai Chi Yunshou motor imagery training for hemiplegic upper extremity motor function in poststroke patients: study protocol for a randomized clinical trial

BackgroundEvidence concerning the effect of Tai Chi Yunshou motor imagery training (TCY-MIT) on upper extremity motor function (UE-MF) recovery in poststroke patients is lacking, and few studies have examined the neural mechanisms of MIT. The study was designed to assess the effectiveness of TCY-MIT and its possible neural mechanisms.Methods/designThe study is an assessor-blinded, parallel, superiority, randomized clinical trial. A total of 78 eligible participants will be randomly assigned to 2 groups in a 1:1 ratio. Participants in the control group will receive (conventional rehabilitation therapies) CRTs for 40 min per day, 6 days per week, for 3 weeks. Participants in the intervention group will receive CRTs combined with TCY-MIT (30 min per day, 6 days per week, for 3 weeks). The primary outcome measure is the Fugl-Meyer Assessment of Upper Extremity. Secondary outcome measures are the Box and Block Test, muscle strength test, modified Barthel index, and Pearson correlation coefficients. All outcomes will be assessed at baseline, after completion of the intervention (1, 2, and 3 weeks), and at the end of follow-up (2 months). The outcome assessor will be blinded to the group allocation of the participants.DiscussionWe expect this assessor-blinded, parallel, superiority, randomized clinical trial to explore the effectiveness of TCY-MIT combined with CRTs compared with CRTs alone for UE-MF in poststroke patients.Trial registrationChinese Clinical Trial Registry ID: ChiCTR2100048868. Registered on 19 July 2021

Effectiveness of Motor Imagery Training to Improve Gait Abilities of Patients with Sub-Acute Stroke

Aim: To determine the effectiveness of motor imagery training to improve the lower extremity function and gait in subjects with sub-acute stroke. Methods: Forty four patients with subacute stroke with gait impairment were randomly assigned to one of two groups: motor imagery training group or muscle relaxation group. At the beginning and after six weeks of therapy, the ability to use motor imagery and lower limb performance were assessed. Results: There were substantial differences of scores between both groups, with the motor imagery group progressing more than the muscle relaxation group. Conclusion: Motor imagery may have a beneficial and effective task-specific effect on gait function in sub-acute stroke patients. Keywords: motor imagery; gait rehabilitation; sub-acute stroke patients

Changes in Functional Connectivity of Resting-state after Motor Imagery Training Detected by Eigenvector Centrality Mapping

Motor imagery training has been indicated to be effective in motor function rehabilitation and motor skill learning. The neural mechanism underlying motor training has attracted increased neuroimaging explorations. Related neuroimaging studies demonstrated that resting-state can offer the possibility to examine the neural mechanism of motor execution training. However, motor imagery training, as another part of motor training, has been few investigated. To address this issue, eigenvector centrality mapping (ECM) method was applied to explore functional connectivity of resting-state in motor imagery training. As a data-driven analysis method, although ECM can assess the computational measurement of eigenvector centrality for capturing intrinsic neural architecture on a voxel-wise level without any prior assumptions, it is still limited in application for making pseudo enhancement in some nodes or zero centrality in all nodes. In this study, we proposed an improved ECM by adding threshold, dispersion coefficient, weighted coefficient and the initial parameters referring to Google Webpage search ranking algorithm, and applied the proposed ECM to functional connectivity measure of resting-state before and after motor imagery training. The proposed ECM showed the advantage of automatic discharge weak links and the enhancement in node ordering resolution comparing with the original ECM. The results from voxel-based comparison of the centrality between the resting-state after and before motor imagery training revealed that the significantly increased eigenvector centrality was detected in the precuneus and medial frontal gyrus for the experimental group while no significant alterations were found for the control group after training. These alterations may be related to the spatial information integration and inner state modulation of motor imagery training, and further provided new insights into the understanding of the neural mechanism underlying motor imagery training.

A Randomized Controlled Trial of Motor Imagery Combined with Virtual Reality Techniques in Patients with Parkinson's Disease.

Background: Parkinson’s disease is the second most common neurological disease, affecting balance, motor function, and activities of daily living. Virtual reality and motor imagery are two emerging approaches for the rehabilitation of patients with Parkinson’s disease. This study aimed to determine the combined effects of virtual reality and motor imagery techniques with routine physical therapy on the motor function components of individuals with Parkinson’s disease. Methods: The study was a prospective, two-arm, parallel-design randomized controlled trial. Forty-four patients with idiopathic Parkinson’s disease were randomly assigned to one of two groups. Virtual reality and motor imagery were given together with physical therapy in the experimental group (N: 20), while physical therapy treatment alone was given in the control group (N: 21). Both groups received allocated treatment for 12 weeks, 3 days a week, on alternate days. Motor function was assessed at baseline, six weeks, twelve weeks, and sixteen weeks after discontinuing treatment with the Unified Parkinson’s Disease Rating Scale part III. SPSS 24 was used to analyze the data. Results: Study results indicate that the experimental group showed significant improvements in the motor function components: tremor at rest at the 6th week (p = 0.028), 12th week (p = 0.05), and 16th week (p = 0.001), rigidity at the 6th week (p = 0.03), 12th week (p = 0.000), and 16th week (p = 0.001), posture at the 12th week (p = 0.005) and 16th week (p = 0.004), and gait at the 6th week with a p-value of (p = 0.034). Conclusions: This study demonstrated that virtual reality and motor imagery training in combination with routine physical therapy can significantly improve resting tremors, rigidity, posture, gait, and body bradykinesia in individuals with PD in comparison to patients receiving only routine physical therapy.

" A Motor Imagery Training for Improving Action Cognition Results in the Reduction of Residual Symptoms after Major Depressive Disorder: A Single-Case Study"

The high rate of recurrence and residual symptoms of depression continuously motivate the search for new treatments addressing this challenging condition. In this single-case study, we reported the application of a cognitive rehabilitation skills training based on remote kinematics as a treatment for residual depression by targeting deficits of mental simulations of action. We found that the administration of Kinect-based rehabilitation training resulted in important improvements showed by significant mean baseline reductions (MBLR) of difficulty in imagining positive actions (MBLR= 54 %), negative emotions (MBLR = 36.3 %), cognitive flexibility (MBLR= 69.7 %), depressive symptoms (MBLR= 80%), and physical retardation (MBLR= 50 %). Similarly, improvements in positive affect (MBLR = 107 %) and vividness of motor imagery for positive actions were registered (MBLR= 100 %). We also found unique effects of our intervention such as reports of involuntary action simulations to distant stimuli or extended affordances. The training was well-accepted and the patient considered it was an entertaining way to do physical exercises and to get in physical and mental shape. We concluded that further scientific research of remote Kinematic interventions in depression may be warranted.

지각선호도, 심상능력, 실제심상활용의 조사연구 : 사격, 양궁, 다이빙, 체조 종목 중심으로

Purpose: The purpose of this study was to examine the tendency and match rate within one’s perceptual preference, imagery ability and the actual imagery that one uses. Methods: To achieve our goal, we surveyed 248 athletes(diving, gymnastic, shooting, archery) from high school, universities and professional fields. But 55 questionnaires were excluded by data screening. Therefore, a total of 193 questionnaires were finally used. Results: First, athletes preferred Uni-Kinethetic(K) type the most, followed by multi-modal(4 mixual modal) among the perceptual preference. Second, 37 athletes(19.2%) had high imagery abilities matching their preferred perceptual types. Third, 16 athletes(10.4%) showed matching rate of their actual use of imagery type and perceptual preference. Fourth, only 3 athletes(2.1%) showed consistency within their perceptual preference, imagery ability and actual use of imagery sensory type. Conclusion: The consistency between the athletes’ perceptual preference and their main sensory of imagery ability was not as high as expected. Particularly, the rate of athletes who high imagery ability of their perceptual preference was low. Moreover, the low percentage of athletes were actually using their preferred sensory type. These results will provide future direction for the personalized imagery training program. Furthermore, this study suggests further research on the effect of imagery training relating to individual perceptual preference.

Effectiveness of Motor Imagery Training to Improve Gait Abilities of Patients with Sub-Acute Stroke

Aim: To determine the effectiveness of motor imagery training to improve the lower extremity function and gait in subjects with sub-acute stroke. Methods: Forty four patients with subacute stroke with gait impairment were randomly assigned to one of two groups: motor imagery training group or muscle relaxation group. At the beginning and after six weeks of therapy, the ability to use motor imagery and lower limb performance were assessed. Results: There were substantial differences of scores between both groups, with the motor imagery group progressing more than the muscle relaxation group. Conclusion: Motor imagery may have a beneficial and effective task-specific effect on gait function in sub-acute stroke patients. Keywords: motor imagery; gait rehabilitation; sub-acute stroke patients

Continuous Hybrid BCI Control for Robotic Arm Using Noninvasive Electroencephalogram, Computer Vision, and Eye Tracking

The controlling of robotic arms based on brain–computer interface (BCI) can revolutionize the quality of life and living conditions for individuals with physical disabilities. Invasive electroencephalography (EEG)-based BCI has been able to control multiple degrees of freedom (DOFs) robotic arms in three dimensions. However, it is still hard to control a multi-DOF robotic arm to reach and grasp the desired target accurately in complex three-dimensional (3D) space by a noninvasive system mainly due to the limitation of EEG decoding performance. In this study, we propose a noninvasive EEG-based BCI for a robotic arm control system that enables users to complete multitarget reach and grasp tasks and avoid obstacles by hybrid control. The results obtained from seven subjects demonstrated that motor imagery (MI) training could modulate brain rhythms, and six of them completed the online tasks using the hybrid-control-based robotic arm system. The proposed system shows effective performance due to the combination of MI-based EEG, computer vision, gaze detection, and partially autonomous guidance, which drastically improve the accuracy of online tasks and reduce the brain burden caused by long-term mental activities.

The effects of imagery training on free-throw accuracy among young basketball players

Abstract Objectives The influence of mental imagery training on the performance of adolescent basketball players in free-throw task was examined using an experimental design and the results revealed significantly better improvement among players who practiced using mental imagery compared to the control group. Methods The training program was based on adjusted MIIMS imagery model, and 81 basketball players (aged 13–17) from five junior competition-level teams were divided into two groups: an experimental group and a control group, where players practiced free throws only physically. Players from both groups underwent a total of 14 training sessions at the end of practices during a 7-week period. Their performance in a free-throw task was measured pre- and post-intervention along with multiple factors that could influence changes in performance. Results Comparison of groups with both parametric and non-parametric tests revealed a significant improvement in the experimental group and non-significant improvement in the control group. Furthermore, correlation and regression analyses discovered several statistically significant factors that might influence the performance change. Conclusions The findings not only help in understanding the role of imagery in training routines of young athletes, but they also reveal several methodological implications for future research.