Conformal treatment planning using three-dimensional ultrasound
OwnerJames DOMINE, Sneha SHIVKUMAR +2inventors
InventorsJames DOMINE, Sneha SHIVKUMAR, Qingxiang KE, James Luis BADIA
Life of this patent
Estimating the term…
Abstract
Three dimensional (3D) image data is generated from an imaging device. A 3D model of the tissue is generated in response to identification one or more tissue structures of the 3D image data. A conformal 3D treatment profile is generated in response to the 3D model, and a user interface is configured to allow the user to view corresponding portions of the 3D model and the 3D treatment profile on corresponding 2D tissue sections and the real time image.
Claims22
A method of planning medical treatment of a prostate, the method comprising:
- obtaining a three-dimensional (3D) image data of the prostate of a patient with an imaging device;
- with a first machine learning model trained with 3D image data:
- identifying a plurality of tissue structures in the 3D image data;
- and
- generating a 3D model of the prostate using the plurality of tissue structures, the generating comprising determining a 3D boundary of the prostate;
- with a second machine learning model trained with 3D image data, generating a treatment profile for a medical procedure to treat the prostate using the 3D model;
- and
- displaying the treatment profile to enable the medical procedure to be performed on the prostate,
- wherein the method is performed under control of at least one processor.
A non-transitory computer readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to:
- obtain a three-dimensional (3D) image data of a prostate of a patient with an imaging device;
- with a first machine learning model trained with 3D image data:
- identify a plurality of tissue structures in the 3D image data;
- and
- generate a 3D model of the prostate using the plurality of tissue structures, the generating comprising determining a 3D boundary of the prostate;
- with a second machine learning model trained with 3D image data, generate a treatment profile for a medical procedure to treat the prostate using the 3D model;
- and
- display the treatment profile to enable the medical procedure to be performed on the prostate.
Dependencies are inferred from the claim text.