A Skull-Adaptive Framework for AI-Based 3D Transcranial Focused Ultrasound Simulation

TL;DR

This paper introduces TFUScapes, a large-scale dataset of transcranial focused ultrasound simulations, and DeepTFUS, a deep learning model that predicts ultrasound pressure fields from skull images, aiming to improve non-invasive brain stimulation planning.

Contribution

The paper presents the first high-resolution, large-scale dataset of tFUS simulations and a novel deep learning model that estimates pressure fields directly from imaging data, reducing reliance on computationally intensive simulations.

Findings

TFUScapes dataset enables data-driven tFUS research.

DeepTFUS accurately predicts pressure fields from skull images.

The approach accelerates transcranial ultrasound planning.

Abstract

Transcranial focused ultrasound (tFUS) is an emerging modality for non-invasive brain stimulation and therapeutic intervention, offering millimeter-scale spatial precision and the ability to target deep brain structures. However, the heterogeneous and anisotropic nature of the human skull introduces significant distortions to the propagating ultrasound wavefront, which require time-consuming patient-specific planning and corrections using numerical solvers for accurate targeting. To enable data-driven approaches in this domain, we introduce TFUScapes, the first large-scale, high-resolution dataset of tFUS simulations through anatomically realistic human skulls derived from T1-weighted MRI images. We have developed a scalable simulation engine pipeline using the k-Wave pseudo-spectral solver, where each simulation returns a steady-state pressure field generated by a focused ultrasound transducer placed at realistic scalp locations. In addition to the dataset, we present DeepTFUS, a deep learning model that estimates normalized pressure fields directly from input 3D CT volumes and transducer position. The model extends a U-Net backbone with transducer-aware conditioning, incorporating Fourier-encoded position embeddings and MLP layers to create global transducer embeddings. These embeddings are fused with U-Net encoder features via feature-wise modulation, dynamic convolutions, and cross-attention mechanisms. The model is trained using a combination of spatially weighted and gradient-sensitive loss functions, enabling it to approximate high-fidelity wavefields. The TFUScapes dataset is publicly released to accelerate research at the intersection of computational acoustics, neurotechnology, and deep learning. The project page is available at https://github.com/CAMMA-public/TFUScapes.