Genetic algorithm search for the worst‐case MRI RF exposure for a multiconfiguration implantable fixation system modeled using artificial neural networks

Zheng, Jianfeng; Lan, Qianlong; Kainz, Wolfgang; Long, Stuart A.; Ji, Chen

doi:10.1002/mrm.28319

Cited by 9 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The entire applied process relied on electromagnetic simulations, and, recently, in order to avoid the required computational time and memory requirements, novel machine learning methods have been proposed for the assessment of MRI RF heating. Specifically, the application of neural networks has been proposed to predict the worst-case heating of orthopedic fixation plates in the MRI environment, with the only input being the geometric properties of the implant [57]. Additionally, deep learning has been applied to predict the SAR values at the tip of conductive leads along clinically relevant cardiac and DBS paths during 1.5 T and 3 T MRI [58][59][60].…”

Section: Discussionmentioning

confidence: 99%

Computational Investigation of the Factors That Affect Tangential Electric Fields along Cardiac Lead Paths inside MRI Birdcage Coils

Tsanidis,

Samaras

2024

Applied Sciences

View full text Add to dashboard Cite

The medical imaging of a patient with a cardiac implantable electronic device (CIED) inside a magnetic resonance imaging (MRI) scanner carries the risk of tissue heating at the tip of the implant lead. In this work, we numerically assessed the impact of various factors, namely the resonant frequency, the imaging position, the implant position inside the human body and the coil configuration, on the induced tangential electric field along 10,080 cardiac lead paths at 1140 different scanning scenarios. During this comparative process, a function was considered based on the induced electrical potential at the tip of the lead. The input power of each coil was adjusted to generate constant B1+RMS at the iso-center or to limit the global SAR to the values provided in the safety guidelines IEC 60601-33. The values of the function were higher for higher static field and longer coil lengths when assessing the cases of a constrained B1+RMS, and the trend was reversed considering the limiting SAR values. Moreover, the electric field was higher as the imaging landmark approached the thorax and the neck. It was also shown that both the choice regarding the insertion vein of the lead and the positioning of the implantable pulse generator (IPG) affected the induced tangential electric field along the paths. In particular, when the CIED lead was inserted into the left axillary vein instead of entering into the right subclavian vein, the electrical potential at the tip could be on average lower by 1.6 dB and 2.1 dB at 1.5 T and 3 T, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Computational Investigation of the Factors That Affect Tangential Electric Fields along Cardiac Lead Paths inside MRI Birdcage Coils

Tsanidis,

Samaras

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Pre-assessment of heating is essential to determine the risk/benefit ratio of MRI exams in these patients and is typically performed through phantom experiments or full-wave electromagnetic simulations both of which being substantially time-consuming. Machine learning has been recently proposed as a promising tool for fast screening and determination of worst-case heating scenarios of orthopedic implants in MRI enviromnent [ 16 , 17 ]. Here we report results of a proof-of-concept simulation study to assess the applicability of machine learning to predict RF heating of elongated implants, such as leads in active electronic devices, during MRI at 1.5 T. We tested the hypothesis that a feedforward neural network could be trained to predict the local SAR at tips of implanted leads when only the knowledge of lead’s trajectory within the MRI RF coil and the features of RF coil are at hand.…”

Section: Discussionmentioning

confidence: 99%

“…Novel machine learning methods have been recently proposed as a paradigm shift in the assessment of MRI RF heating. Pioneering work by Chen group has shown that neural networks can predict the worst-case heating of orthopedic fixation plates in MRI environment when only the knowledge of implant’s geometrical features is at hand [ 16 , 17 ]. In their work, however, the implant’s position was predetermined within the MRI RF coil and thus, the effect of variation in electric field exposure due to changes in implant’s location and orientation was not investigated.…”

Section: Introductionmentioning

confidence: 99%

Predicting RF Heating of Conductive Leads During Magnetic Resonance Imaging at 1.5 T: A Machine Learning Approach

Zheng

Chen

Nguyen

et al. 2021

2021 43rd Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

The number of patients with active implantable medical devices continues to rise in the United States and around the world. It is estimated that 50-75% of patients with conductive implants will need magnetic resonance imaging (MRI) in their lifetime. A major risk of performing MRI in patients with elongated conductive implants is the radiofrequency (RF) heating of the tissue surrounding the implant's tip due to the antenna effect. Currently, applying fullwave electromagnetic simulation is the standard way to predict the interaction of MRI RF fields with the human body in the presence of conductive implants; however, these simulations are notoriously extensive in terms of memory requirement and computational time. Here we present a proof-of-concept simulation study to demonstrate the feasibility of applying machine learning to predict MRI-induced power deposition in the tissue surrounding conductive wires. We generated 600 clinically relevant trajectories of leads as observed in patients with cardiac conductive implants and trained a feedforward neural network to predict the 1g-averaged SAR at the lead tips knowing only the background field of MRI RF coil and coordinates of points along the lead trajectory. Training of the network was completed in 11.54 seconds and predictions were made within a second with R 2 = 0.87 and Root Mean Squared Error (RMSE) = 14.5 W/kg. Our results suggest that machine learning could provide a promising approach for safety assessment of MRI in patients with conductive leads. ClinicalRelevance-Machine learning can potentially allow real-time assessment of MRI RF safety in patients with conductive leads when only the knowledge of lead's trajectory (image-based) and MRI RF coil features (vendor-specific) are in hand.

show abstract

“…Recent research has employed machine learning (ML) to predict subject-specific local specific absorption rate (SAR) from B 1 + maps [ 9 ] and SAR distributions from anatomical MRI images [ 10 ]. Neural networks (NNs) have also been utilized to predict SAR during MRI of orthopedic fixation plates based on their geometric features [ 11 ], [ 12 ]. Our group has previously trained a NN to predict trajectory-specific SAR of DBS leads using the distribution of the tangential component of the incident electric field along each lead trajectory [ 1 ], [ 13 ].…”

Section: Introductionmentioning

confidence: 99%

Rapid prediction of MRI-induced RF heating of active implantable medical devices using machine learning

Vu,

Sanpitak,

Bhusal

et al. 2023

2023 45th Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

The interaction between an active implantable medical device and magnetic resonance imaging (MRI) radiofrequency (RF) fields can cause excessive tissue heating. Existing methods for predicting RF heating in the presence of an implant rely on either extensive phantom experiments or electromagnetic (EM) simulations with varying degrees of approximation of the MR environment, the patient, or the implant. On the contrary, fast MR thermometry techniques can provide a reliable real-time map of temperature rise in the tissue in the vicinity of conductive implants. In this proof-of-concept study, we examined whether a machine learning (ML) based model could predict the temperature increase in the tissue near the tip of an implanted lead after several minutes of RF exposure based on only a few seconds of experimentally measured temperature values. We performed phantom experiments with a commercial deep brain stimulation (DBS) system to train a fully connected feedforward neural network (NN) to predict temperature rise after ~3 minutes of scanning at a 3 T scanner using only data from the first 5 seconds. The NN effectively predicted ΔT max —R 2 = 0.99 for predictions in the test dataset. Our model also showed potential in predicting RF heating for other various scenarios, including a DBS system at a different field strength (1.5 T MRI, R 2 = 0.87), different field polarization (1.2 T vertical MRI, R 2 = 0.79), and an unseen implant (cardiac leads at 1.5 T MRI, R 2 = 0.91). Our results indicate great potential for the application of ML in combination with fast MR thermometry techniques for rapid prediction of RF heating for implants in various MR environments.

show abstract

Genetic algorithm search for the worst‐case MRI RF exposure for a multiconfiguration implantable fixation system modeled using artificial neural networks

Cited by 9 publications

References 15 publications

Computational Investigation of the Factors That Affect Tangential Electric Fields along Cardiac Lead Paths inside MRI Birdcage Coils

Computational Investigation of the Factors That Affect Tangential Electric Fields along Cardiac Lead Paths inside MRI Birdcage Coils

Predicting RF Heating of Conductive Leads During Magnetic Resonance Imaging at 1.5 T: A Machine Learning Approach

Rapid prediction of MRI-induced RF heating of active implantable medical devices using machine learning

Contact Info

Product

Resources

About