Particle Swarm Optimization for Positioning the Coil of Transcranial Magnetic Stimulation

Li, Congsheng; Yang, Lei; He, Luyang; Wu, Tongning

doi:10.1155/2019/9461018

Cited by 7 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second application of EF modelling is to guide the selection of TMS parameters for stimulating brain areas that do not produce directly measurable responses. Studies using subject-specific anatomical models have shown that stimulation can be optimised individually or in a group of subjects (Opitz et al, 2016;Gomez-Tames et al, 2018;Li et al, 2019). In future, this may allow personalised stimulation protocols for rehabilitation or therapy.…”

Section: Discussionmentioning

confidence: 99%

“…Individualised computation of the induced EF became more important in other cortical regions, which had higher inter-subject variability of the cortical folding. Li et al (2019) used an optimisation technique to reduce the number of computations to determine the optimal TMS coil configuration to target specific brain regions. Up to 11 iterations of EF computations were required for high accuracy in 13 head models under this test.…”

Section: Guiding Tms Dosementioning

confidence: 99%

See 1 more Smart Citation

Review on biophysical modelling and simulation studies for transcranial magnetic stimulation

2020

View full text Add to dashboard Cite

Transcranial magnetic stimulation (TMS) is a technique for noninvasively stimulating a brain area for therapeutic, rehabilitation treatments and neuroscience research. Despite our understanding of the physical principles and experimental developments pertaining to TMS, it is difficult to identify the exact brain target as the generated dosage exhibits a non-uniform distribution owing to the complicated and subject-dependent brain anatomy and the lack of biomarkers that can quantify the effects of TMS in most cortical areas. Computational dosimetry has progressed significantly and enables TMS assessment by computation of the induced electric field (the primary physical agent known to activate the brain neurons) in a digital representation of the human head. In this review, TMS dosimetry studies are summarised, clarifying the importance of the anatomical and human biophysical parameters and computational methods. This review shows that there is a high consensus on the importance of a detailed cortical folding representation and an accurate modelling of the surrounding cerebrospinal fluid. Recent studies have also enabled the prediction of individually optimised stimulation based on magnetic resonance imaging of the patient/subject and have attempted to understand the temporal effects of TMS at the cellular level by incorporating neural modelling. These efforts, together with the fast deployment of personalised TMS computations, will permit the adoption of TMS dosimetry as a standard procedure in clinical procedures.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Guiding Tms Dosementioning

confidence: 99%

Review on biophysical modelling and simulation studies for transcranial magnetic stimulation

2020

View full text Add to dashboard Cite

show abstract

“…In this study, the lesion area (2 × 2 cm) was surrounded by four 3 × 3 cm stimulation VOIs ( Figure 2 ). Each VOI corresponded to a search domain (4 × 4 cm) for optimizing the coil position ( 31 ). The center of the search domain overlapped with the center of the corresponding VOI.…”

Section: Methodsmentioning

confidence: 99%

“…From what has been discussed above, the primary aim is to stimulate a more precise “hot spot” to acquire the E-field as high as possible for a stronger stimulation effect, which is truly helpful for activating neurons around the lesion. Some studies established comprehensive brain atlas of stimulation sites for quick operations to improve TMS stimulation accuracy ( 28 , 29 ), whereas others used several heuristic algorithms, such as the fast computational auxiliary dipole method (ADM) ( 30 ) and particle swarm optimization (PSO) ( 31 , 32 ), to regulate the position or current configuration of the coil to improve the overall E-field in the voxel of interest (VOI); thus, achieving optimal neural regulation. However, both these coil location optimization algorithms are based on a healthy brain.…”

Section: Introductionmentioning

confidence: 99%

Genetic Algorithm for TMS Coil Position Optimization in Stroke Treatment

Jiang²,

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

Transcranial magnetic stimulation (TMS), a non-invasive technique to stimulate human brain, has been widely used in stroke treatment for its capability of regulating synaptic plasticity and promoting cortical functional reconstruction. As shown in previous studies, the high electric field (E-field) intensity around the lesion helps in the recovery of brain function, thus the spatial location and angle of coil truly matter for the significant correlation with therapeutic effect of TMS. But, the error caused by coil placement in current clinical setting is still non-negligible and a more precise coil positioning method needs to be proposed. In this study, two kinds of real brain stroke models of ischemic stroke and hemorrhagic stroke were established by inserting relative lesions into three human head models. A coil position optimization algorithm, based on the genetic algorithm (GA), was developed to search the spatial location and rotation angle of the coil in four 4 × 4 cm search domains around the lesion. It maximized the average intensity of the E-field in the voxel of interest (VOI). In this way, maximum 17.48% higher E-field intensity than that of clinical TMS stimulation was obtained. Besides, our method also shows the potential to avoid unnecessary exposure to the non-target regions. The proposed algorithm was verified to provide an optimal position after nine iterations and displayed good robustness for coil location optimization between different stroke models. To conclude, the optimized spatial location and rotation angle of the coil for TMS stroke treatment could be obtained through our algorithm, reducing the intensity and duration of human electromagnetic exposure and presenting a significant therapeutic potential of TMS for stroke.

show abstract

“…Compared with multi-objective evolutionary algorithms (MOEAs) that use non-dominated sorting and sharing, the NSGA-II can find a much better spread of solutions and better convergence near the true Pareto-optimal front for most problems. In addition, compared with traditional signal objective optimization algorithms, such as GA and PSO [32], another advantage of NSGA-II is its multi-objective optimization. Existing literature on insider trading identification has hitherto set the identification accuracy as the single optimization objective, with the identification efficiency not being treated as the optimization objective.…”

Section: Introductionmentioning

confidence: 99%

Identification of Insider Trading Using Extreme Gradient Boosting and Multi-Objective Optimization

Wang

et al. 2019

Information

View full text Add to dashboard Cite

Illegal insider trading identification presents a challenging task that attracts great interest from researchers due to the serious harm of insider trading activities to the investors’ confidence and the sustainable development of security markets. In this study, we proposed an identification approach which integrates XGboost (eXtreme Gradient Boosting) and NSGA-II (Non-dominated Sorting Genetic Algorithm II) for insider trading regulation. First, the insider trading cases that occurred in the Chinese security market were automatically derived, and their relevant indicators were calculated and obtained. Then, the proposed method trained the XGboost model and it employed the NSGA-II for optimizing the parameters of XGboost by using multiple objective functions. Finally, the testing samples were identified using the XGboost with optimized parameters. Its performances were empirically measured by both identification accuracy and efficiency over multiple time window lengths. Results of experiments showed that the proposed approach successfully achieved the best accuracy under the time window length of 90-days, demonstrating that relevant features calculated within the 90-days time window length could be extremely beneficial for insider trading regulation. Additionally, the proposed approach outperformed all benchmark methods in terms of both identification accuracy and efficiency, indicating that it could be used as an alternative approach for insider trading regulation in the Chinese security market. The proposed approach and results in this research is of great significance for market regulators to improve their supervision efficiency and accuracy on illegal insider trading identification.

show abstract

Particle Swarm Optimization for Positioning the Coil of Transcranial Magnetic Stimulation

Cited by 7 publications

References 45 publications

Review on biophysical modelling and simulation studies for transcranial magnetic stimulation

Review on biophysical modelling and simulation studies for transcranial magnetic stimulation

Genetic Algorithm for TMS Coil Position Optimization in Stroke Treatment

Identification of Insider Trading Using Extreme Gradient Boosting and Multi-Objective Optimization

Contact Info

Product

Resources

About