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.

Abstract: Approaches for focusing an ultrasound transducer having multiple transducer elements include generating the first sonication to one or more target regions and measuring the first set of reflection signals resulting from the first sonication; based on the first set of reflection signals, determining whether a target number or a target occurrence rate of focusing events has been reached; if not, generating the second sonication at an adjusted acoustic power to the target region(s) and measuring the second set of reflection signals resulting from the second sonication; and based at least in part on the second set of reflection signals, adjusting a parameter value associated with one or more transducer elements so as to improve an ultrasound focus at the target region(s).

Abstract: Various approaches for operating an ultrasound transducer having multiple transducer elements include acquiring one or more measurements of anatomical regions through which ultrasound waves emitted from the transducer elements travel; for each of the anatomical regions, determining values of characteristics based at least in part on the measurement(s); computationally predicting aberrations of the ultrasound waves traveling through the anatomical regions by using the first values as input to a predictor that has been computationally trained to predict ultrasound aberrations based on values of the characteristics; and driving the transducer elements to compensate for the predicted aberrations.

Abstract: Various approaches for operating an ultrasound transducer having multiple transducer elements include acquiring one or more measurements of anatomical regions through which ultrasound waves emitted from the transducer elements travel; for each of the anatomical regions, determining values of characteristics based at least in part on the measurement(s); computationally predicting aberrations of the ultrasound waves traveling through the anatomical regions by using the first values as input to a predictor that has been computationally trained to predict ultrasound aberrations based on values of the characteristics; and driving the transducer elements to compensate for the predicted aberrations.