Automated magnetic resonance image segmentation for ultrasound thermal therapy control

A system for delivering ultrasound thermal therapy comprising:

• a magnetic resonance (MR) imaging system;
• a high-intensity focused ultrasound (HIFU) system comprising an array of ultrasound transducer elements;
• a computer comprising a hardware-based processor, the computer operatively coupled to the MR imaging system and to the HIFU system;
• and
• a non-transitory storage medium comprising computer-readable instructions that, when executed by the processor, cause the processor to:
• send a first output signal to the MR system to acquire MR images of tissue proximal to a target treatment region in a patient, the tissue including a non-spatially uniform subcutaneous fat layer,
• automatically determine an actual thickness of the subcutaneous fat layer using a trained neural network, the neural network trained using manually-segmented MR images from previous patients,
• adjust a set of treatment parameters based on the actual thickness of the subcutaneous fat layer, and
• send a second output signal to the HIFU system to deliver thermal therapy to the target treatment region based on the adjusted treatment parameter.