Systems and methods for generating head models
AssigneeMagnus Medical, Inc.
InventorsLuis Cuenca Montes, Armani Porter
Life of this patent
Estimating the term…
Abstract
Described herein are systems and methods for generating a head model, e.g., a morphable head model, that may include a 3D representation of the skull and face for neurostimulation therapy. The systems and methods may generally transform a 2D image of the head of a patient into a more accurate 3D representation of the face and skull using a cylindrical scanning, skin segmentation, and/or adaptive thresholding technique. In another variation, genetic techniques, such as facial genetic morphology, may be used in conjunction with the techniques described to increase aesthetic accuracy of the 3D representation of the face and skull. Benefits of these techniques may include preservation of all facial features, reduced noise, and avoidance of foreign objects.
Claims16
A method for creating a head model comprising:
- obtaining a magnetic resonance imaging (MRI) scan data of a head of a patient, where the MRI scan comprises two dimensional (2D) slices of the head of the patient, and where the head of the patient comprises a skull of the patient and a skin of the patient;
- identifying the skin of the patient in the MRI scan data;
- segmenting the MRI scan data based on the identified skin of the patient such that the 2D slices, when placed in order, define a 3D volume;
- generating a mesh of the head of the patient based on the segmented MRI scan data;
- generating a depth map of the head of the patient based on the segmented MRI scan data;
- extracting a plurality of facial features of the head of the patient using the depth map;
- providing the mesh of the head of the patient and the plurality of facial features of the head to a facial reconstruction mode;
- obtaining a reconstruction of the head of the patient from the facial reconstruction model.
A non-transitory computer-readable media storing instructions that, when executed by a computer, cause the computer to:
- obtain magnetic resonance imaging (MRI) scan data of a head of a patient, where the MRI scan comprises two dimensional (2D) slices of the head of the patient, and where the head of the patient comprises a skull of the patient and a skin of the patient;
- identify the skin of the patient in the MRI scan data;
- segment the MRI scan data based on the identified skin of the patient such that the 2D slices, when placed in order, define a 3D volume;
- generate a mesh of the head of the patient based on the segmented MRI scan data;
- generate a depth map of the head of the patient based on the segmented MRI scan data;
- extract a plurality of facial features of the head of the patient using the depth map;
- provide the mesh of the head of the patient and the plurality of facial features of the head to a facial reconstruction mode;
- obtain a reconstruction of the head of the patient from the facial reconstruction model.
Dependencies are inferred from the claim text.