Neural Network Model for Estimation of the Induced Electric Field during Transcranial Magnetic Stimulation Afuwape, Oluwaponmile Olafasakin, Olumide Jiles, David Jiles, David
dc.contributor.department Ames Laboratory
dc.contributor.department Electrical and Computer Engineering
dc.contributor.department Materials Science and Engineering 2021-06-15T22:27:13.000 2021-08-14T04:21:28Z 2021-08-14T04:21:28Z Fri Jan 01 00:00:00 UTC 2021 2021-06-07
dc.description.abstract <p>Transcranial Magnetic Stimulation (TMS) is a non-invasive neuromodulation technique with applications in brain mapping and effective neuronal connectivity. In its repetitive mode, it is used for the treatment of neurological and psychiatric disorders. It functions on the principle of electromagnetic induction, where generated magnetic fields (H-field) induce electric field (E-field) that stimulates the brain’s neurons. With TMS studies, accurate estimation of the induced E-field is usually necessary. However, this requires a lot of processes, including the three-dimensional head model generation from magnetic resonance images (MRI) using the SimNIBS software and finite element analysis to calculate the induced E-field. These processes are time-consuming and computationally expensive. Additionally, with each head model’s uniqueness, outcomes cannot be generalized across a particular population as the intensity of E-field is subject-specific. In this research, the authors develop deep convolutional neural network (deep CNN) models to determine the intensity of the induced E-field directly from the patient’s MRI scan and across different coil types. We trained CNN models from anatomically realistic head models and across 16 coil types to predict the induced E-field in the brain and scalp (E-Max brain and scalp), and the volume of stimulation of the brain and scalp (V-half brain and scalp) from T1-weighted MRI scans. Using a deep CNN model, the processing time for estimating the induced E-field is significantly reduced, which is helpful both to clinicians and researchers as the need to create subject-specific anatomical head structures is eliminated. Also, there will be no need for additional stimulation sessions with the different coil types for TMS patients as the deep CNN model can predict the outcome from each coil type. The other advantage of the deep CNN model is that the E-field from the different coil types can be compared simultaneously.</p>
dc.description.comments <p>This is a manuscript of an article published as Afuwape, Oluwaponmile F., Olumide O. Olafasakin, and David C. Jiles. "Neural Network Model for Estimation of the Induced Electric Field during Transcranial Magnetic Stimulation." <em>IEEE Transactions on Magnetics</em> (2021). DOI: <a href="" target="_blank">10.1109/TMAG.2021.3086761</a>. Posted with permission.</p>
dc.format.mimetype application/pdf
dc.identifier archive/
dc.identifier.articleid 1316
dc.identifier.contextkey 23368015
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath ece_pubs/312
dc.language.iso en
dc.source.bitstream archive/|||Fri Jan 14 23:31:41 UTC 2022
dc.source.uri 10.1109/TMAG.2021.3086761
dc.subject.disciplines Biomedical
dc.subject.disciplines Materials Science and Engineering
dc.subject.disciplines Neurosciences
dc.subject.keywords Deep Convolutional Neural Network (Deep CNN)
dc.subject.keywords Induced Electric Field
dc.subject.keywords MRI Scans
dc.subject.keywords Transcranial Magnetic Stimulation (TMS)
dc.title Neural Network Model for Estimation of the Induced Electric Field during Transcranial Magnetic Stimulation
dc.type article
dc.type.genre article
dspace.entity.type Publication
relation.isAuthorOfPublication cb9622ce-98bb-47c3-bc98-8ac772e1c44e
relation.isOrgUnitOfPublication 25913818-6714-4be5-89a6-f70c8facdf7e
relation.isOrgUnitOfPublication a75a044c-d11e-44cd-af4f-dab1d83339ff
relation.isOrgUnitOfPublication bf9f7e3e-25bd-44d3-b49c-ed98372dee5e
Original bundle
Now showing 1 - 1 of 1
652.57 KB
Adobe Portable Document Format