Acoustic Simulation for Transcranial Focused Ultrasound Using GAN-Based Synthetic CT

Koh, Heekyung; Park, Tae Young; Chung, Yong An; Lee, Jong‐Hwan; Kim, Hyung-Min

doi:10.1109/jbhi.2021.3103387

Cited by 24 publications

(12 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar work using a 3D cGAN from Koh et al 16 observed a larger MAE than ours (190 ± 22 vs. 280 ± 24) but a larger correlation coefficient between the real and synthesized SDRs (0.92 vs. 0.95). It was observed MAE was greater at the inferior of the skull than the superior of the skull.…”

Section: Discussionsupporting

confidence: 82%

“…During training, G aimed to generate synthetic CT skull image G(x) from x to fool D, while D learned to classify y and G(x). Our loss function was composed of an adversarial loss L cGAN and a L1 loss L L1 which encouraged less blurring (in Koh et al, 16 an additional gradient loss was incorporated to generate sCT for the whole head):…”

Section: Methodsmentioning

confidence: 99%

“…The irregular skull geometry of sCT may lead to significant differences in TcMRgFUS planning. In very recent work done in parallel to ours 16 a 3D cGAN was proposed to synthesize the whole head CT from MR images. Here we focus on the skull, which is the critical structure for TcMRgFUS.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Synthetic CT Skull Generation for Transcranial MR Imaging-Guided Focused Ultrasound Interventions with Conditional Adversarial Networks

Liu¹,

Sigona²,

Manuel³

et al. 2022

Preprint

View full text Add to dashboard Cite

Transcranial MRI-guided focused ultrasound (TcMRgFUS) is a therapeutic ultrasound method that focuses sound through the skull to a small region noninvasively under MRI guidance. It is clinically approved to thermally ablate regions of the thalamus and is being explored for other therapies, such as blood brain barrier opening and neuromodulation. To accurately target ultrasound through the skull, the transmitted waves must constructively interfere at the target region. However, heterogeneity of the sound speed, density, and ultrasound attenuation in different individuals' skulls requires patient-specific estimates of these parameters for optimal treatment planning. CT imaging is currently the gold standard for estimating acoustic properties of an individual skull during clinical procedures, but CT imaging exposes patients to radiation and increases the overall number of imaging procedures required for therapy. A method to estimate acoustic parameters in the skull without the need for CT would be desirable. Here, we synthesized CT images from routinely acquired T1-weighted MRI by using a 3D patch-based conditional generative adversarial network (cGAN) and evaluated the performance of synthesized CT images for treatment planning with transcranial focused ultrasound. A dataset of 86 paired CT and T1-weighted MR images were randomly split so that 66 images were used for training, 10 for validation and parameter tuning, and 10 for acoustic testing. We compared the performance of synthetic CT (sCT) to real CT (rCT) images using an open-source treatment planning software, Kranion, and found that the number of active elements, skull density ratio, and skull thickness between rCT and sCT had Pearson's Correlation Coefficients of 0.989, 0.915, and 0.941, respectively, suggesting strong positive linear correlation. Of a total of 990 elements 95.7 ± 1.4% of active and inactive elements overlapped between rCTs and sCTs. Simulations using the acoustic toolbox, k-Wave, resulted in 23.5 ± 6.51% less maximum root-mean-squared (RMS) pressure simulated with sCTs than the corresponding rCT pressure. An average focal shift of 0.96 ± 0.56 mm and 1.07 ± 0.58 mm was observed between the thalamus target and the maximum RMS pressure location in rCTs and sCTs, respectively. Our work demonstrates the feasibility of replacing real CT with the MR-synthesized CT for TcMRgFUS planning.

show abstract

Section: Discussionsupporting

confidence: 82%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Synthetic CT Skull Generation for Transcranial MR Imaging-Guided Focused Ultrasound Interventions with Conditional Adversarial Networks

Liu¹,

Sigona²,

Manuel³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Third, using CT images increases treatment workflow overhead, requiring separate imaging sessions to acquire all pre-operative images.An alternative to CT is MR imaging, a safe, non-ionizing imaging modality. In recent years, developments in MR imaging of bone have been able to produce images with CT-like bone contrast [38][39][40][41][42][43] . These MR imaging techniques use ultrashort echo time (UTE), zero echo time (ZTE), or T1-weighted magnetization preparation rapid acquisition gradient echo (T1w MPRAGE) sequences to acquire bone signal before it decays rapidly due to T2* effects.…”

mentioning

confidence: 99%

Comparison between MR and CT imaging used to correct for skull-induced phase aberrations during transcranial focused ultrasound

Leung

Moore

Gilbo

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Transcranial focused ultrasound with the InSightec Exablate system uses thermal ablation for the treatment of movement and mood disorders and blood brain barrier disruption for tumor therapy. The system uses computed tomography (CT) images to calculate phase corrections that account for aberrations caused by the human skull. This work investigates whether magnetic resonance (MR) images can be used as an alternative to CT images to calculate phase corrections. Phase corrections were calculated using the gold standard hydrophone method and the standard of care InSightec ray tracing method. MR binary image mask, MR-simulated-CT (MRsimCT), and CT images of three ex vivo human skulls were supplied as inputs to the InSightec ray tracing method. The degassed ex vivo human skulls were sonicated with a 670 kHz hemispherical phased array transducer (InSightec Exablate 4000). 3D raster scans of the beam profiles were acquired using a hydrophone mounted on a 3-axis positioner system. Focal spots were evaluated using six metrics: pressure at the target, peak pressure, intensity at the target, peak intensity, positioning error, and focal spot volume. Targets at the geometric focus and 5 mm lateral to the geometric focus were investigated. There was no statistical difference between any of the metrics at either target using either MRsimCT or CT for phase aberration correction. As opposed to the MRsimCT, the use of CT images for aberration correction requires registration to the treatment day MR images; CT misregistration within a range of ± 2 degrees of rotation error along three dimensions was shown to reduce focal spot intensity by up to 9.4%. MRsimCT images used for phase aberration correction for the skull produce similar results as CT-based correction, while avoiding both CT to MR registration errors and unnecessary patient exposure to ionizing radiation.

show abstract

“…Interestingly, pre-treatment transcranial model could be employed as a turnkey solution for optimizing the parameters for treatment targets and, meanwhile, examining the biophysical mechanisms of TUS at individual level. Previous studies focused on investigating the spatial distribution of TUS effect are based on the magnetic resonance imaging (MRI) or computed tomography scans of young adults with an average head size (Koh et al, 2021 ; Zhang et al, 2021 ). However, this standard model has limited power to represent the distribution of TUS-induced effects in the individuals with various skull and brain morphology.…”

Section: Why Age-specific Transcranial Models Important?mentioning

confidence: 99%

Radiomics-Informed Modeling for Transcranial Ultrasound Stimulation: Age Matters

2022

Front. Neurosci.

View full text Add to dashboard Cite

Acoustic Simulation for Transcranial Focused Ultrasound Using GAN-Based Synthetic CT

Cited by 24 publications

References 52 publications

Synthetic CT Skull Generation for Transcranial MR Imaging-Guided Focused Ultrasound Interventions with Conditional Adversarial Networks

Synthetic CT Skull Generation for Transcranial MR Imaging-Guided Focused Ultrasound Interventions with Conditional Adversarial Networks

Comparison between MR and CT imaging used to correct for skull-induced phase aberrations during transcranial focused ultrasound

Radiomics-Informed Modeling for Transcranial Ultrasound Stimulation: Age Matters

Contact Info

Product

Resources

About