Differential prediction of aberration corrections for ultrasound therapy
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12582386-B2
Publication Date
2026-03-24
Expiration Date
Abstract
Various approaches for delivering ultrasound energy to a target region during a therapeutic or diagnostic procedure includes implementing an adjustment mechanism having a machine-learning model that has been trained, based on input vectors corresponding to a difference and/or a ratio of parameter values between multiple transducer elements, to generate, for each of the transducer elements, one or more parameter value to compensate for expected beam aberration resulting for an intervening tissue; and activating the transducer elements in accordance with the corresponding parameter values so as to generate an optimized focal zone at the target region during the therapeutic or diagnostic procedure.
Core Innovation
An ultrasound system delivers ultrasound energy to a target region during a therapeutic or diagnostic procedure. A machine-learning adjustment mechanism is trained on input vectors constructed from at least one of a difference or a ratio of parameter values between transducer elements. It receives numeric quantities characterizing tissue intervening between active transducer elements and the target region, and generates parameter values for the active elements to compensate for expected beam aberration and form an optimized focal zone.
The corresponding method provides the adjustment mechanism, receives the tissue-characterizing numeric quantities, generates parameter values for each active transducer element, and activates the elements in accordance with those values. Disclosed implementations include neural networks, Siamese networks, lookup tables, measurement-based updates, and predictions for additional target regions. Transducer parameter values include corrections to amplitude, phase, frequency, duty cycle, sonication pattern, or time delay.
Claims Coverage
The patent claims identify two inventive features across independent claims directed to an ultrasound system and an ultrasound delivery method.
Machine-learning aberration compensation system
Claim 1 recites an ultrasound transducer with active transducer elements and an adjustment mechanism comprising a machine-learning model trained on input vectors constructed from at least one of a difference or a ratio of parameter values between transducer elements. The mechanism receives numeric quantities characterizing intervening tissue and generates, for each active element, at least one parameter value to compensate for expected beam aberration. A controller activates the elements according to the corresponding values to generate an optimized focal zone.
Machine-learning aberration compensation method
Claim 18 recites providing an adjustment mechanism comprising a machine-learning model trained on input vectors constructed from at least one of a difference or a ratio of parameter values between transducer elements; receiving numeric quantities characterizing intervening tissue; generating, for each active element, at least one parameter value to compensate for expected beam aberration; and activating the elements according to the corresponding values to generate an optimized focal zone.
The independent claims cover system and method embodiments of using machine learning trained on transducer parameter differences or ratios to generate aberration-compensating settings and produce an optimized focal zone.
Stated Advantages
The described use of differences or ratios of parameter values between transducer elements reduces shared measurement bias.
The generated parameter values compensate for expected beam aberration and are used to generate an optimized focal zone at the target region.
Documented Applications
Delivery of ultrasound energy to a target region during a therapeutic or diagnostic procedure.
The method may use updated parameter values to compensate for expected beam aberration at a secondary target region different from the target region.
Interested in licensing this patent?