No evidence for an association of voxel-based morphometry with short-term non-motor outcomes in deep brain stimulation for Parkinson's disease.

Deep brain stimulation of the subthalamic nucleus (STN-DBS) is an established therapy in advanced Parkinson's disease (PD). Motor and non-motor outcomes, however, show considerable inter-individual variability. Preoperative morphometry-based metrics have recently received increasing attention to explain treatment effects. As evidence for the prediction of non-motor outcomes is limited, we sought to investigate the association between metrics of voxel-based morphometry and short-term non-motor outcomes following STN-DBS in this prospective open-label study. Forty-nine PD patients underwent structural MRI and a comprehensive clinical assessment at preoperative baseline and 6-month follow-up. Voxel-based morphometry was used to assess associations between cerebral volume and non-motor outcomes corrected for multiple comparisons using a permutation-based approach. We replicated existing results associating volume loss of the superior frontal cortex with subpar motor outcomes. Overall non-motor burden, however, was not significantly associated with morphometric features, limiting its use as a marker to inform patient selection and holistic preoperative counselling.

Neurostimulation for Advanced Parkinson Disease and Quality of Life at 5 Years: A Nonrandomized Controlled Trial.

Importance: Deep brain stimulation of the subthalamic nucleus (STN-DBS) improves quality of life (QOL) in patients with advanced Parkinson disease (PD). However, controlled studies with more than 3 years of follow-up are lacking. Objective: To investigate the long-term effects of STN-DBS on QOL compared with standard-of-care medication (MED). Design, Setting, and Participants: In this prospective, observational, quasi-experimental, longitudinal nonrandomized controlled trial, 183 patients were screened for eligibility and 167 were enrolled from March 1, 2011, to May 31, 2017, at 3 European university centers. Propensity score matching for demographic and clinical characteristics was applied to 108 patients with PD (62 in the STN-DBS group and 46 in the MED group), resulting in a well-balanced, matched subcohort of 25 patients per group. Data analysis was performed from September 2022 to January 2023. Exposure: Treatment for PD of STN-DBS or MED. Main Outcomes and Measures: Assessments included Parkinson's Disease Questionnaire 8 (PDQ-8), Unified PD Rating Scale-motor examination, Scales for Outcomes in PD-activities of daily living (ADL) and motor complications, and levodopa-equivalent daily dose. Within-group longitudinal outcome changes, between-group differences, and correlations of change scores were analyzed. Results: The study population in the analysis included 108 patients (mean [SD] age, 63.7 [8.3] years; 66 [61.1%] male). At 5-year follow-up, PDQ-8 and ADL worsened only in the MED group (PDQ-8 change, -10.9; 95% CI, -19.0 to -2.7; P = .01; ADL change: -2.0; 95% CI, -3.1 to -0.8; P = .002), whereas both outcomes remained stable in the STN-DBS group (PDQ-8 change, -4.3; 95% CI, -13.2 to 4.7; P = .34; ADL change, -0.8; 95% CI, -2.5 to 1.0; P = .38). Changes in PDQ-8 and ADL correlated moderately (rs = .40, P = .008). Furthermore, STN-DBS outcomes were favorable for motor complications (median difference in change scores between STN-DBS and MED, -2.0; 95% CI, -4.0 to -1.0; P = .003), mobility (-1.0; 95% CI, -2.0 to 0; P = .03), and levodopa-equivalent daily dose reduction (-821.4; 95% CI, -1111.9 to -530.8; P < .001). Conclusions and Relevance: This study provides evidence of differences in QOL outcomes at 5-year follow-up between STN-DBS (stable) and MED (worsened), mainly driven by the favorable effect of STN-DBS on mobility (class IIb evidence). The association between changes in QOL and ADL, but not motor impairment or complications, highlights the relative importance of ADL outcomes for long-term DBS assessments. Trial Registration: German ClinicalTrials Registry: DRKS00006735.

Stratifying quality of life outcome in subthalamic stimulation for Parkinson's disease.

BACKGROUND: Subthalamic nucleus deep brain stimulation (STN-DBS) for Parkinson's disease (PD) improves quality of life (QoL), motor and non-motor symptoms (NMS). However, in previous studies, 43%-49% of patients did not experience clinically relevant postoperative QoL improvement. To inform individualised prediction of postoperative QoL improvement, we developed a stratification analysis of QoL outcomes based on preoperative non-motor total burden, severity of motor progression and motor response in levodopa challenge tests. METHODS: This was a prospective, open-label, multicentre, international study with a 6-month follow-up. A distribution-based threshold identified 'QoL responders' in the PDQuestionnaire-8 Summary Index (PDQ-8 SI). After baseline stratification based on the NMS Scale, Hoehn and Yahr Scale and levodopa response assessed with the Unified PD Rating Scale-III, we compared postoperative QoL response between these strata. To assess the clinical usefulness and statistical feasibility of stratifications, we compared cumulative distribution function curves, respectively PDQ-8 within-stratum variation. RESULTS: All main outcomes improved postoperatively. Based on the 8.1 points threshold for clinically meaningful PDQ-8 SI improvement, only 80/161 patients were classified as 'QoL responders'. The absolute risk reductions for QoL non-response among respective non-motor, motor progression and levodopa response strata were 23%, 8% and 3%, respectively. Only non-motor stratification reduced PDQ-8 within-stratum variation compared with the overall cohort. CONCLUSIONS: Non-motor stratification, but not motor progression or levodopa response stratification, is clinically useful and statistically feasible for personalised preoperative prediction of postoperative QoL outcome of STN-DBS for PD. Our findings highlight that non-motor assessments are necessary components of a case-based, holistic approach of DBS indication evaluations geared towards optimising postoperative QoL outcomes. TRIAL REGISTRATION NUMBER: GermanClinicalTrialsRegister: #6735.

Assessing the effect of Amphistegina lobifera invasion on infralittoral benthic foraminiferal assemblages in the Sicily Channel (Central Mediterranean).

This article documents, through a quantitative approach, the negative effect of the highly invasive species Amphistegina lobifera Larsen, 1976 on native benthic foraminiferal assemblages of coastal areas in the Sicily Channel (Central Mediterranean). A nested sampling design was applied through the comparison of benthic foraminiferal community structure across three areas that are known to be at different stages of invasion (i.e. Maltese Islands - advanced, southern Sicily - medium, and eastern Sicily - early). Results suggested that both diversity and richness of benthic foraminiferal community from the Maltese Islands were strongly modified by increased abundances of A. lobifera. In contrast, this phenomenon is less evident in southern and eastern Sicily, where the invader displayed lower abundances and the community structure was more diversified. Collected data also allowed for predicting what could happen in the near future in the whole Sicily Channel, as well as in the rest of the Mediterranean Sea.

Utilizing Mixed Training and Multi-Head Attention to Address Data Shift in AI-Based Electromagnetic Solvers for Nano-Structured Metamaterials.

When designing nano-structured metamaterials with an iterative optimization method, a fast deep learning solver is desirable to replace a time-consuming numerical solver, and the related issue of data shift is a subtle yet easily overlooked challenge. In this work, we explore the data shift challenge in an AI-based electromagnetic solver and present innovative solutions. Using a one-dimensional grating coupler as a case study, we demonstrate the presence of data shift through the probability density method and principal component analysis, and show the degradation of neural network performance through experiments dealing with data affected by data shift. We propose three effective strategies to mitigate the effects of data shift: mixed training, adding multi-head attention, and a comprehensive approach that combines both. The experimental results validate the efficacy of these approaches in addressing data shift. Specifically, the combination of mixed training and multi-head attention significantly reduces the mean absolute error, by approximately 36%, when applied to data affected by data shift. Our work provides crucial insights and guidance for AI-based electromagnetic solvers in the optimal design of nano-structured metamaterials.

Generalized Dystonia Due to a Pathogenic THAP1 Variant Showing Sustained Response to Globus Pallidus Deep Brain Stimulation.

A 21-year-old woman of south Asian origin presented with cervical dystonia which had progressed over the previous three years. Her symptoms started as writer's cramp since the age of seven years. She did not respond to medications and needed botulinum toxin injection for generalised dystonia. Subsequent whole genome sequencing revealed a likely pathogenic c.98G>A p.(Cys33Tyr) heterozygous variant in the THAP1 gene. She underwent bilateral posteroventral globus pallidus interna (GPi) deep brain stimulation (Medtronic Activa PC) implantation at the age of thirty-one years. She responded well to the deep brain stimulation even after more than 8 years post-surgery though she needs botulinum toxin injection for her cervical dystonia.

Non-motor effects of deep brain stimulation in Parkinson's disease motor subtypes.

INTRODUCTION: Deep brain stimulation (DBS) is a well-established treatment for patients with Parkinson's disease (PD) improving quality of life, motor, and non-motor symptoms. However, non-motor effects in PD subtypes are understudied. We hypothesized that patients with 'postural instability and gait difficulty' (PIGD) experience more beneficial non-motor effects than 'tremor-dominant' patients undergoing DBS for PD. METHODS: In this prospective, observational, international multicentre study with a 6-month follow-up, we assessed the Non-Motor Symptom Scale (NMSS) as primary and the following secondary outcomes: Unified PD Rating Scale-motor examination (UPDRS-III), Scales for Outcomes in PD (SCOPA)-activities of daily living (ADL) and -motor complications, PDQuestionnaire-8 (PDQ-8), and levodopa-equivalent daily dose (LEDD). We analysed within-group longitudinal changes with Wilcoxon signed-rank test and Benjamini-Hochberg correction for multiple comparisons. Additionally, we explored outcome between-group differences of motor subtypes with Mann-Whitney U-tests. RESULTS: In 82 PIGD and 33 tremor-dominant patients included in this study, baseline NMSS total scores were worse in PIGD patients, both groups experienced postoperative improvements of the NMSS sleep/fatigue domain, and between-group differences in postoperative outcomes were favourable in the PIGD group for the NMSS total and miscellaneous domain scores. CONCLUSIONS: This study provides evidence of a favourable outcome of total non-motor burden in PIGD compared to tremor-dominant patients undergoing DBS for PD. These differences of clinical efficacy on non-motor aspects should be considered when advising and monitoring patients with PD undergoing DBS.

Factors associated with post traumatic hydrocephalus following decompressive craniectomy: A single-center experience.

Background: A decompressive craniectomy (DC) is a surgical procedure sometimes utilized to manage refractory intracranial hypertension following severe traumatic brain injury (sTBI). The previous studies have established a relationship between DC and post traumatic hydrocephalus (PTH). This study aimed to identify the factors responsible for developing shunt-amenable PTH in patients who underwent DC following sTBI. Methods: A review of a prospectively collected database of all patients admitted with severe TBI in a tertiary neurosurgical center in North-west England between January 2012 and May 2022 was performed. PTH was defined as evidence of progressive ventricular dilatation, clinical deterioration, and/or the eventual need for cerebrospinal fluid diversion (i.e., a ventriculoperitoneal shunt). Statistical analysis was carried out using IBM SPSS versus 28.0.1. Results: Sixty-five patients met the eligibility criteria and were included in the study. The mean age of the PTH group was 31.38 ± 14.67, while the mean age of the non-PTH group was slightly higher at 39.96 ± 14.85. No statistically significant difference was observed between the two groups' mechanisms of traumatic injury (P = 0.945). Of the predictors investigated, cerebellar hematoma (and contusions) was significantly associated with PTH (P = 0.006). Conclusion: This study concludes that cerebellar hematoma (and contusions) are associated with developing PTH in patients undergoing DC.

Decompressive Craniectomy and Shunt-Amenable Post-Traumatic Hydrocephalus: A Single-Center Experience.

Background: Prior studies have shown that decompressive craniectomy may be an independent risk factor for the development of post-traumatic hydrocephalus (PTH). It is upon this background that we chose to conduct our single-center retrospective study to establish the possibility of an association between decompressive craniectomy and PTH. Methods: A retrospective review involving a database of all patients with traumatic brain injury was undertaken. All referrals and admissions with traumatic brain injury, as defined by the Mayo Classification, from January 2012 to May 2022, were included in the subsequent analysis. Statistical analysis was carried out using IBM SPSS version 28.0.1. Results: The mean age of the cohort was 44.91 ± 19.16 with more males (82.3%) than females (17.7%). Vehicle incident/collision was the most common cause of traumatic brain injury. 84% of the cohort was alive at 30 days, 4% were noted to have an intracranial infection, and 3% underwent shunt insertion procedures, while 14% received decompressive craniotomies as part of their clinical management. There was a statistically significant association between undergoing decompressive craniectomy, and the development of PTH (odds ratio, 4.759 [95% confidence interval, 1.290-17.559]; P = 0.019). The presence of intracranial infection and insertion of an external ventricular drain insertion were also independent predictors of developing PTH. Conclusions: This study adds to the growing body of work regarding the immediate and long-term effects of the procedure. Although life-saving, PTH, needing shunt insertion, is one of the possible complications that surgeons and patients should be aware of.

1.7 µm - 1.73 µm tunable ultrafast Raman fiber laser pumped by 1.6 µm dissipative soliton pulses.

Here, we report an all-fiber tunable ultrafast Raman laser synchronously pumped by a home-made 1.6 µm dissipative soliton (DS) picosecond (ps) laser, which produces Stokes light beyond 1.7 µm. The Raman gain medium is a segment of highly germanium-doped (Ge-doped) fiber offering a high Raman gain coefficient at the target wavelength. Once the Raman conversion cavity is synchronized with the pump light, a stable 1.7 µm Raman laser (the first Stokes light) can be obtained at a low pump threshold. The maximum output power of the 1.7 µm Raman laser can reach ∼ 22.62 mW. The wavelength tuning operation is independent of tunable pump source and intra-cavity filter. By adjusting the intra-cavity delay line simply, the different spectral component within the broad Raman gain bandwidth can be selectively synchronized with the pump light so that the Raman laser wavelength can be tuned continuously from 1702.6 nm ∼ 1728.84 nm. This tunable 1.7 µm waveband ultrafast laser will have potential applications in multiphoton microscopy for e.g. deep bio-imaging.

Super-Large-Scale Hierarchically Porous Films Based on Self-Assembled Eye-Like Air Pores for High-Performance Daytime Radiative Cooling.

Metal-free polymer daytime radiative cooling coatings with hierarchical eye-like air pores are proposed and fabricated with a super-large-scale film-stretching method. The hierarchically porous film (HPF) can be further coated with polymethyl methacrylate (PMMA) micro-hemispheres, forming coated HPF (cHPF), which do not dramatically change the optical or thermal properties. The cHPF is slightly better with a lower solar absorptivity (2.4%) and a higher thermal emissivity over the atmospheric transparency window (90.1%). The low solar absorptivity is due to the strong scattering of the hierarchical eye-like air pores, while the molecular vibrations and the focusing effect of the PMMA micro-hemispheres contribute to the high emissivity. An average mid-day temperature reduction of 7.92 °C is achieved relative to the air temperature, and the average cooling power reaches 116.0 W m-2 , which are much better than the cooling performances of the commercial cooling cushion. During the day, the cHPF-covered simulated building is up to 6.47 and 4.84 °C cooler than the ambient and the white painted counterpart, respectively. The film is durable and resistant to chemical etching, and very promising to use globally, especially in warm and tropical regions.

Near-Field Radiative Heat Transfer Modulation with an Ultrahigh Dynamic Range through Mode Mismatching.

Modulating near-field radiative heat transfer (NFRHT) with a high dynamic range is challenging in nanoscale thermal science and engineering. Modulation depths [(maximum value - minimum value)/(maximum value + minimum value) × 100%] of ≈2% to ≈15.7% have been reported with matched modes, but breaking the constraint of mode matching theoretically allows for higher modulation depth. We demonstrate a modulation depth of ≈32.2% by a pair of graphene-covered SU8 heterostructures at a gap distance of ≈80 nm. Dissimilar Fermi levels tuned by bias voltages enable mismatched surface plasmon polaritons which improves the modulation. The modulation depth when switching from a matched mode to a mismatched mode is ≈4.4-fold compared to that when switching between matched modes. This work shows the importance of symmetry in polariton-mediated NFRHT and represents the largest modulation depth to date in a two-body system with fixed gap distance and temperature.

Incoherent broadband cavity-enhanced absorption spectroscopy for sensitive measurement of nutrients and microalgae.

Incoherent broadband cavity-enhanced absorption spectroscopy (IBBCEAS) can achieve sensitive measurements at trace concentrations for liquid phase marine samples. The IBBCEAS system consists of a cavity-enhancement module (CEM) and a transmission hyperspectral module (THM). The CEM has cavity-enhancement factors up to 78 at 550 nm. Measurements were obtained over a wide wavelength range (420-640 nm) with a halogen lamp, and the optical cavity was formed by two concave highly reflective mirrors (R=0.99). The minimum detectable absorption coefficient αmin of 7.3×10-7cm-1 at 550 nm corresponds to a limit of detection for nutrients of 780 pM. The spectral resolution of the THM is 3 nm in the wavelength range of 400 to 750 nm. We performed the IBBCEAS measurements for biological and chemical substances, including nutrients, microalgae, and Cy5 dye. The concentrations of nutrients in a deionized water environment and artificial seawater environment were measured at nanomolar levels; the concentration of microalgae phaeocystis was detected with 3.46×104/mL, and fluorescence substances such as Cy5 dye could be measured at 0.03 mg/L. Experimental results show that the IBBCEAS system has the capability for sensitive measurements of biological and chemical substances and has strong potential forin situ ecological marine environmental monitoring function.

Gender gap in deep brain stimulation for Parkinson's disease.

Previous studies have shown less access to deep brain stimulation (DBS) for Parkinson's disease (PD) in women compared to men raising concerns about a potential gender gap resulting from nonclinical factors or gender differences in clinical efficacy for postoperative quality of life (QoL), motor, and nonmotor symptoms (NMS) outcomes. This was a cross-sectional and a longitudinal, prospective, observational, controlled, quasi-experimental, international multicenter study. A total sample size of 505 consisted of 316 consecutively referred patients for DBS indication evaluation at the University Hospital Cologne (01/2015-09/2020) and 189 consecutively treated patients at DBS centers in the University Hospitals Cologne and Marburg, Salford's Royal Hospital Manchester, and King's College Hospital London. In the cross-sectional cohort, we examined gender proportions at referral, indication evaluations, and DBS surgery. In the longitudinal cohort, clinical assessments at preoperative baseline and 6-month follow-up after surgery included the PD Questionnaire-8, NMSScale, Scales for Outcomes in PD-motor scale, and levodopa-equivalent daily dose. Propensity score matching resulted in a pseudo-randomized sub-cohort balancing baseline demographic and clinical characteristics between women with PD and male controls. 316 patients were referred for DBS. 219 indication evaluations were positive (women n = 102, respectively n = 82). Women with PD were disproportionally underrepresented in referrals compared to the general PD population (relative risk [RR], 0.72; 95%CI, 0.56-0.91; P = 0.002), but more likely to be approved for DBS than men (RR, 1.17; 95%CI, 1.03-1.34; P = 0.029). Nonetheless, their total relative risk of undergoing DBS treatment was 0.74 (95%CI, 0.48-1.12) compared to men with PD. At baseline, women had longer disease duration and worse dyskinesia. Exploring QoL domains, women reported worse mobility and bodily discomfort. At follow-up, all main outcomes improved equally in both genders. Our study provides evidence of a gender gap in DBS for PD. Women and men with PD have distinct preoperative nonmotor and motor profiles. We advocate that more focus should be directed toward the implementation of gender equity as both genders benefit from DBS with equal clinical efficacy. This study provides Class II evidence of beneficial effects of DBS in women with PD compared to male controls.

Group size and modularity interact to shape the spread of infection and information through animal societies.

Social interactions between animals can provide many benefits, including the ability to gain useful environmental information through social learning. However, these social contacts can also facilitate the transmission of infectious diseases through a population. Animals engaging in social interactions therefore face a trade-off between the potential informational benefits and the risk of acquiring disease. Theoretical models have suggested that modular social networks, associated with the formation of groups or sub-groups, can slow spread of infection by trapping it within particular groups. However, these social structures will not necessarily impact the spread of information in the same way if its transmission follows a "complex contagion", e.g. through individuals disproportionally copying the majority (conformist learning). Here we use simulation models to demonstrate that modular networks can promote the spread of information relative to the spread of infection, but only when the network is fragmented and group sizes are small. We show that the difference in transmission between information and disease is maximised for more well-connected social networks when the likelihood of transmission is intermediate. Our results have important implications for understanding the selective pressures operating on the social structure of animal societies, revealing that highly fragmented networks such as those formed in fission-fusion social groups and multilevel societies can be effective in modulating the infection-information trade-off for individuals within them. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s00265-021-03102-4.

Optimized Colossal Near-Field Thermal Radiation Enabled by Manipulating Coupled Plasmon Polariton Geometry.

Collective optoelectronic phenomena such as plasmons and phonon polaritons can drive processes in many branches of nanoscale science. Classical physics predicts that a perfect thermal emitter operates at the black body limit. Numerous experiments have shown that surface phonon polaritons allow emission two orders of magnitude above the limit at a gap distance of ≈50 nm. This work shows that a supported multilayer graphene structure improves the state of the art by around one order of magnitude with a ≈1129-fold-enhancement at a gap distance of ≈55 nm. Coupled surface plasmon polaritons at mid- and far-infrared frequencies allow for near-unity photon tunneling across a broad swath of k-space enabling the improved result. Electric tuning of the Fermi-level allows for the detailed characterization and optimization of the colossal nanoscale heat transfer.

Inelastic hyperspectral Scheimpflug lidar for microalgae classification and quantification.

An inelastic hyperspectral Scheimpflug lidar system was developed for microalgae classification and quantification. The correction for the refraction at the air-glass-water interface was established, making our system suitable for aquatic environments. The fluorescence spectrum of microalgae was extracted by principal component analysis, and seven species of microalgae from different phyla have been classified. It was verified that when the cell density of Phaeocystis globosa was in the range of ${{1}}{{{0}}^4}\sim{{1}}{{{0}}^6}\;{\rm{cell}}\;{\rm{m}}{{\rm{L}}^{- 1}}$, the cell density had a linear relationship with the fluorescence intensity. The experimental results show our system can identify and quantify microalgae, with application prospects for microalgae monitoring in the field environment and early warning of red tides or algal blooms.

Non-motor predictors of 36-month quality of life after subthalamic stimulation in Parkinson disease.

To identify predictors of 36-month follow-up quality of life (QoL) outcome after bilateral subthalamic nucleus deep brain stimulation (STN-DBS) in Parkinson's disease (PD). In this ongoing, prospective, multicenter international study (Cologne, Manchester, London) including 73 patients undergoing STN-DBS, we assessed the following scales preoperatively and at 6-month and 36-month follow-up: PD Questionnaire-8 (PDQ-8), NMSScale (NMSS), Scales for Outcomes in PD (SCOPA)-motor examination, -activities of daily living, and -complications, and levodopa equivalent daily dose (LEDD). We analyzed factors associated with QoL improvement at 36-month follow-up based on (1) correlations between baseline test scores and QoL improvement, (2) step-wise linear regressions with baseline test scores as independent and QoL improvement as dependent variables, (3) logistic regressions and receiver operating characteristic curves using a dichotomized variable "QoL responders"/"non-responders". At both follow-ups, NMSS total score, SCOPA-motor examination, and -complications improved and LEDD was reduced significantly. PDQ-8 improved at 6-month follow-up with subsequent decrements in gains at 36-month follow-up when 61.6% of patients were categorized as "QoL non-responders". Correlations, linear, and logistic regression analyses found greater PDQ-8 improvements in patients with younger age, worse PDQ-8, and worse specific NMS at baseline, such as 'difficulties experiencing pleasure' and 'problems sustaining concentration'. Baseline SCOPA scores were not associated with PDQ-8 changes. Our results provide evidence that 36-month QoL changes depend on baseline neuropsychological and neuropsychiatric non-motor symptoms burden. These findings highlight the need for an assessment of a wide range of non-motor and motor symptoms when advising and selecting individuals for DBS therapy.

CNN-based classification of fNIRS signals in motor imagery BCI system.

Objective. Development of a brain-computer interface (BCI) requires classification of brain neural activities to different states. Functional near-infrared spectroscopy (fNIRS) can measure the brain activities and has great potential for BCI. In recent years, a large number of classification algorithms have been proposed, in which deep learning methods, especially convolutional neural network (CNN) methods are successful. fNIRS signal has typical time series properties, we combined fNIRS data and kinds of CNN-based time series classification (TSC) methods to classify BCI task.Approach. In this study, participants were recruited for a left and right hand motor imagery experiment and the cerebral neural activities were recorded by fNIRS equipment (FOIRE-3000). TSC methods are used to distinguish the brain activities when imagining the left or right hand. We have tested the overall person, single person and overall person with single-channel classification results, and these methods achieved excellent classification results. We also compared the CNN-based TSC methods with traditional classification methods such as support vector machine.Main results. Experiments showed that the CNN-based methods have significant advantages in classification accuracy: the CNN-based methods have achieved remarkable results in the classification of left-handed and right-handed imagination tasks, reaching 98.6% accuracy on overall person, 100% accuracy on single person, and in the single-channel classification an accuracy of 80.1% has been achieved with the best-performing channel.Significance. These results suggest that using the CNN-based TSC methods can significantly improve the BCI performance and also lay the foundation for the miniaturization and portability of training rehabilitation equipment.