Dataset Information

Technical note: Minimizing CIED artifacts on a 0.35 T MRI-Linac using deep learning.

ABSTRACT:

Background

Artifacts from implantable cardioverter defibrillators (ICDs) are a challenge to magnetic resonance imaging (MRI)-guided radiotherapy (MRgRT).

Purpose

This study tested an unsupervised generative adversarial network to mitigate ICD artifacts in balanced steady-state free precession (bSSFP) cine MRIs and improve image quality and tracking performance for MRgRT.

Methods

Fourteen healthy volunteers (Group A) were scanned on a 0.35 T MRI-Linac with and without an MR conditional ICD taped to their left pectoral to simulate an implanted ICD. bSSFP MRI data from 12 of the volunteers were used to train a CycleGAN model to reduce ICD artifacts. The data from the remaining two volunteers were used for testing. In addition, the dataset was reorganized three times using a Leave-One-Out scheme. Tracking metrics [Dice similarity coefficient (DSC), target registration error (TRE), and 95 percentile Hausdorff distance (95% HD)] were evaluated for whole-heart contours. Image quality metrics [normalized root mean square error (nRMSE), peak signal-to-noise ratio (PSNR), and multiscale structural similarity (MS-SSIM) scores] were evaluated. The technique was also tested qualitatively on three additional ICD datasets (Group B) including a patient with an implanted ICD.

Results

For the whole-heart contour with CycleGAN reconstruction: 1) Mean DSC rose from 0.910 to 0.935; 2) Mean TRE dropped from 4.488 to 2.877 mm; and 3) Mean 95% HD dropped from 10.236 to 7.700 mm. For the whole-body slice with CycleGAN reconstruction: 1) Mean nRMSE dropped from 0.644 to 0.420; 2) Mean MS-SSIM rose from 0.779 to 0.819; and 3) Mean PSNR rose from 18.744 to 22.368. The three Group B datasets evaluated qualitatively displayed a reduction in ICD artifacts in the heart.

Conclusion

CycleGAN-generated reconstructions significantly improved both tracking and image quality metrics when used to mitigate artifacts from ICDs.

SUBMITTER: Curcuru AN

PROVIDER: S-EPMC10929994 | biostudies-literature | 2024 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Technical note: Minimizing CIED artifacts on a 0.35 T MRI-Linac using deep learning.

Curcuru Austen N AN Yang Deshan D An Hongyu H Cuculich Phillip S PS Robinson Clifford G CG Gach H Michael HM

Journal of applied clinical medical physics 20240218 3

<h4>Background</h4>Artifacts from implantable cardioverter defibrillators (ICDs) are a challenge to magnetic resonance imaging (MRI)-guided radiotherapy (MRgRT).<h4>Purpose</h4>This study tested an unsupervised generative adversarial network to mitigate ICD artifacts in balanced steady-state free precession (bSSFP) cine MRIs and improve image quality and tracking performance for MRgRT.<h4>Methods</h4>Fourteen healthy volunteers (Group A) were scanned on a 0.35 T MRI-Linac with and without an MR ...[more]

PMID: 38368615

Similar Datasets

Project description:IntroductionLinear accelerator (linac) incorporating a magnetic resonance (MR) imaging device providing enhanced soft tissue contrast is particularly suited for abdominal radiation therapy. In particular, accurate segmentation for abdominal tumors and organs at risk (OARs) required for the treatment planning is becoming possible. Currently, this segmentation is performed manually by radiation oncologists. This process is very time consuming and subject to inter and intra operator variabilities. In this work, deep learning based automatic segmentation solutions were investigated for abdominal OARs on 0.35 T MR-images.MethodsOne hundred and twenty one sets of abdominal MR images and their corresponding ground truth segmentations were collected and used for this work. The OARs of interest included the liver, the kidneys, the spinal cord, the stomach and the duodenum. Several UNet based models have been trained in 2D (the Classical UNet, the ResAttention UNet, the EfficientNet UNet, and the nnUNet). The best model was then trained with a 3D strategy in order to investigate possible improvements. Geometrical metrics such as Dice Similarity Coefficient (DSC), Intersection over Union (IoU), Hausdorff Distance (HD) and analysis of the calculated volumes (thanks to Bland-Altman plot) were performed to evaluate the results.ResultsThe nnUNet trained in 3D mode achieved the best performance, with DSC scores for the liver, the kidneys, the spinal cord, the stomach, and the duodenum of 0.96 ± 0.01, 0.91 ± 0.02, 0.91 ± 0.01, 0.83 ± 0.10, and 0.69 ± 0.15, respectively. The matching IoU scores were 0.92 ± 0.01, 0.84 ± 0.04, 0.84 ± 0.02, 0.54 ± 0.16 and 0.72 ± 0.13. The corresponding HD scores were 13.0 ± 6.0 mm, 16.0 ± 6.6 mm, 3.3 ± 0.7 mm, 35.0 ± 33.0 mm, and 42.0 ± 24.0 mm. The analysis of the calculated volumes followed the same behavior.DiscussionAlthough the segmentation results for the duodenum were not optimal, these findings imply a potential clinical application of the 3D nnUNet model for the segmentation of abdominal OARs for images from 0.35 T MR-Linac.

Project description:PurposeThis study demonstrated a magnetic resonance (MR) signal multitask learning method for three-dimensional (3D) simultaneous segmentation and relaxometry of human brain tissues.Materials and methodsA 3D inversion-prepared balanced steady-state free precession sequence was used for acquiring in vivo multicontrast brain images. The deep neural network contained three residual blocks, and each block had 8 fully connected layers with sigmoid activation, layer norm, and 256 neurons in each layer. Online-synthesized MR signal evolutions and labels were used to train the neural network batch-by-batch. Empirically defined ranges of T1 and T2 values for the normal gray matter, white matter, and cerebrospinal fluid (CSF) were used as the prior knowledge. MRI brain experiments were performed on three healthy volunteers. The mean and standard deviation for the T1 and T2 values in vivo were reported and compared to literature values. Additional animal (N = 6) and prostate patient (N = 1) experiments were performed to compare the estimated T1 and T2 values with those from gold standard methods and to demonstrate clinical applications of the proposed method.ResultsIn animal validation experiment, the differences/errors (mean difference ± standard deviation of difference) between the T1 and T2 values estimated from the proposed method and the ground truth were 113 ± 486 and 154 ± 512 ms for T1, and 5 ± 33 and 7 ± 41 ms for T2, respectively. In healthy volunteer experiments (N = 3), whole brain segmentation and relaxometry were finished within ~ 5 s. The estimated apparent T1 and T2 maps were in accordance with known brain anatomy, and not affected by coil sensitivity variation. Gray matter, white matter, and CSF were successfully segmented. The deep neural network can also generate synthetic T1- and T2-weighted images.ConclusionThe proposed multitask learning method can directly generate brain apparent T1 and T2 maps, as well as synthetic T1- and T2-weighted images, in conjunction with segmentation of gray matter, white matter, and CSF.

Project description:PurposeThe purpose of this study was to identify the cause of severe image artifacts that occurred during gantry rotation in a 0.35 T MRI-Linac by comparing measurements of eddy currents, center frequency, and field inhomogeneities made with the gantry in motion and stationary.MethodsGradient and B0 eddy currents were calculated from the free induction decays (FIDs) resulting from selective excitation at a temporal resolution of 200 ms/measurement. B0 eddy currents were also calculated from FIDs acquired with nonselective excitation at a temporal resolution of 100 ms/measurement. Center frequencies and B0 inhomogeneities were measured by acquiring FIDs with a repetition time (TR) of 290 ms. Cartesian and radial 2D true fast imaging with steady-state precession (TrueFISP) pulse sequences used in real-time MRI-guided radiation therapy (MR-IGRT) were acquired. To assess artifact severity, the normalized root mean square error (nRMSE) was calculated between a reference MRI (static gantry) and MRIs acquired during gantry rotation for each serial acquisition. Image artifacts were qualitatively graded as nominal, minor, or severe. Measurements were conducted while the gantry was rotated through its entire range for both clockwise and counterclockwise. Measurements during gantry rotation were compared to measurements with a stationary gantry (every 30°).ResultsSevere image artifacts were observed 22-35% of the time while the gantry was rotating. Short time constant eddy currents were not affected by gantry rotation. The peak to peak center frequency and FWHM rose by factors of 13.2-14.5 and 1.1-1.6, respectively, for the rotating versus stationary gantry. The magnitude of the center frequency offset and field inhomogeneities depended on the direction of the gantry rotation.ConclusionsImage artifacts during gantry rotation were primarily caused by center frequency variations and field inhomogeneities. Therefore, dynamic B0 compensation techniques should be able to reduce artifacts during gantry rotation.

Project description:Secondary external dose calculations for a 0.35 T magnetic resonance image-guided radiation therapy (MRgRT) are needed within the radiation oncology community to follow safety standards set forth within the field. We evaluate the commercially available software, RadCalc, in its ability to accurately perform monitor unit dose calculations within a magnetic field. We also evaluate the potential effects of a 0.35 T magnetic field upon point dose calculations. Monitor unit calculations were evaluated with (wMag) and without (noMag) a magnetic field considerations in RadCalc for the ViewRay MRIdian. The magnetic field is indirectly accounted for by using asymmetric profiles for calculation. The introduction of double-stacked multi-leaf collimator leaves was also included in the monitor unit calculations and a single transmission value was determined. A suite of simple and complex geometries with a variety field arrangements were calculated for each method to demonstrate the effect of the 0.35 T magnetic field on monitor unit calculations. Finally, 25 patient-specific treatment plans were calculated using each method for comparison. All simple geometries calculated in RadCalc were within 2% of treatment planning system (TPS) values for both methods, except for a single noMag off-axis comparison. All complex muilt-leaf collimator (MLC) pattern calculations were within 5%. All complex phantom geometry calculations were within 5% except for a single field within a lung phantom at a distal point. For the patient calculations, the noMag method average percentage difference was 0.09 ± 2.5% and the wMag average percentage difference was 0.08 ± 2.5%. All results were within 5% for the wMag method. We performed monitor unit calculations for a 0.35 T MRgRT system using a commercially available secondary monitor unit dose calculation software and demonstrated minimal impact of the 0.35 T magnetic field on monitor unit dose calculations. This is the first investigation demonstrating successful calculations of dose using RadCalc in the low-field 0.35 T ViewRay MRIdian system.

Dataset Information

Technical note: Minimizing CIED artifacts on a 0.35 T MRI-Linac using deep learning.

Background

Purpose

Methods

Results

Conclusion

Publications

Technical note: Minimizing CIED artifacts on a 0.35 T MRI-Linac using deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets