Learning-Based Efficient Phase- Amplitude Modulation and Hybrid Control for MRI-Guided Focused Ultrasound Treatment

Magnetic resonance-guided focused ultrasound (MRg-FUS) has become attractive, accredited to its non-invasive nature. However, ultrasound beams focusing and steering is still challenging owing to aberrations induced by soft tissue heterogeneity. In particular for beam motion control to ensure real-time and precise tracking in the deep-seated region over abdominal organs, while considering full-wave propagation. To this end, we proposed a closed-loop hybrid control scheme and a learning-based modulation model for robot-assisted MRg-FUS treatments. By introducing a rapid phase estimator to provide an efficient (<3 ms) solution, the robust H_∞ controller enables real-time and accurate tracking (0.30 mm) without prior knowledge of heterogeneous media, even under unknown disturbances. Our model enables rapid (2.65 ms) phase-amplitude modulation and precise targeting (mean 0.35 mm, max. 0.65 mm), meeting clinical standard. Focal obliquity is significantly “aligned” to only 2.7°. Results from sensitivity analysis and transducer design also support the model's clinical feasibility and potential in widespread MRg-FUS treatments.

I. Introduction

Focused ultrasound (FUS), owing to its advantages of being completely non-invasive and non-ionizing, has been established as promising interventions [1], e.g., treatments of uterine fibroids [2] and essential tremors [3]. Ultrasound imaging [4], [5], [6] and magnetic resonance imaging (MRI) [7], [8] have been introduced to this procedure to provide intraoperative guidance. MRI plays an increasingly important role in guidance and safety monitoring, accredited to its superior soft-tissue imaging contrast and detailed visualization of physiological changes. Magnetic resonance (MR) thermometry can offer real-time thermal maps to monitor temperature in high-intensity FUS (HIFU). MR elastography [9] can assess thermal damage by measuring tissue elasticity changes. As another elastography method, MR-acoustic radiation force imaging (MR-ARFI) [10] could detect micro-scale tissue displacements resulting from millisecond-short (1–20 ms) ultrasound pulses (Fig. 1(a)), so as to visualize focal spot without causing thermal damage [11]. It would induce negligible temperature rise, making MR-ARFI advantageous in low-intensity FUS (LIFU). Previous studies [12], [13] have reported that few MR-ARFI sequences enable rapid (∼3 s) acquisition on two-dimensional (2D) displacement image, showing the potential in closed-loop feedback control. Therefore, advances in MRI are quite readily available in clinical practice for both HIFU and LIFU. Fig. 1.

(a) MR-ARFI tissue displacement map (in μm) in a sheep liver (Image source: [13]). (b) MRI-guided 5-DoF robotic platform providing sufficient workspace for focal spot steering. (c) Phase field showing phase aberration effect, where the wavefronts are out of phase due to tissue heterogeneity. (d) Distorted focal spot with grating lobes.