Pseudo-CTs from T1-weighted MRI for planning of low-intensity transcranial focused ultrasound neuromodulation: an open-source tool

TL;DR

This paper introduces an open-source tool that generates pseudo-CT images from T1-weighted MRI scans using a refined 3D CNN, enabling accurate skull modeling for transcranial ultrasound planning without the need for actual CT scans.

Contribution

We developed and validated a 3D CNN-based method to produce pseudo-CTs from MRI, facilitating safer and more accessible skull modeling for ultrasound applications.

Findings

Pseudo-CTs achieved a mean absolute error of 109.8 HU compared to real CTs.

Simulations based on pseudo-CTs produced focal pressures statistically equivalent to those based on real CTs.

Binary skull masks were less accurate in acoustic simulations than pseudo-CTs.

Abstract

Background: Individual skull models of bone density and geometry are important when planning the expected transcranial ultrasound acoustic field and estimating mechanical and thermal safety in low-intensity transcranial ultrasound stimulation (TUS) studies. Computed tomography (CT) images have typically been used to estimate skull acoustic properties. However, obtaining CT images in research participants may be prohibitive due to exposure to ionising radiation and limited access to CT scanners within research groups. Objective: We present a validated open-source tool for researchers to obtain individual skull estimates from T1-weighted MR images, for use in acoustic simulations. Methods: We refined a previously trained and validated 3D convolutional neural network (CNN) to generate 100 keV pseudo-CTs. The network was pretrained on 110 individuals and refined and tested on a database of 37 healthy control individuals. We compared simulations based on reference CTs to simulations based on our pseudo-CTs and binary skull masks, a common alternative in the absence of CT. Results: Compared with reference CTs, our CNN produced pseudo-CTs with a mean absolute error of 109.8 +/- 13.0 HU across the whole head and 319.3 +/- 31.9 HU in the skull. In acoustic simulations, the focal pressure was statistically equivalent for simulations based on reference CT and pseudo-CT (0.48 +/- 0.04 MPa and 0.50 +/- 0.04 MPa respectively) but not for binary skull masks (0.28 +/- 0.05 MPa). Conclusions: We show that our network can produce pseudo-CT comparable to reference CTs in healthy individuals, and that these can be used in acoustic simulations.