Abstract: Methods and systems for automatic segmentation of structures of interest of an organ in an MR image. The method includes creating a weighted active shape model (wASM); registering model points of the structures in an MR atlas image to a target image that is the MR image to be segmented, as initial model points of the structures in the target image; and iteratively fitting the wASM to the target image, starting from the initial model points, until the shape converges, wherein the final shape is the segmentation of the structures of interest.

Abstract: A patient-customized electrode array (EA) includes a plurality of electrodes, {Ei}, assembled in a pre-curved form, wherein the curvature of the EA at the i-th electrode Ei is characterized with a curvature that matches the curvature of the i-th point Pi of a structure curve in the cochlea of a patient where the i-th electrode Ei is to be placed, wherein i=1, 2, 3, . . . N, N is an integer greater than zero.

Abstract: A patient-customized electrode array (EA) includes a plurality of electrodes, {Ei}, assembled in a pre-curved form, wherein the curvature of the EA at the i-th electrode Ei is characterized with a curvature that matches the curvature of the i-th point Pi of a structure curve in the cochlea of a patient where the i-th electrode Ei is to be placed, wherein i=1, 2, 3, . . . N, N is an integer greater than zero.

Abstract: Methods and systems for segmentation of structures of interest (SOI) in a CT image post-operatively acquired with an implant user in a region of interest in which an implant is implanted. The method includes inputting the post-operatively acquired CT (Post-CT) image to trained networks to generate a dense deformation field (DDF) from the input Post-CT image to an atlas image; and warping a segmentation mesh of the SOI in the atlas image to the input Post-CT image using the DDF so as to generate the segmentation mesh of the SOI in the input Post-CT image, wherein the segmentation mesh of the SOI in the atlas image is generated by applying an active shape model-based method to the atlas image.

Abstract: Systems and methods are provided for performing model-based cochlear implant programming (MOCIP) on a living subject with a cochlear implant (CI) to determine stimulation settings of a patient-customized electro-neural interface (ENI) model. The method includes: localizing an electrode array of the CI and intracochlear structures of the living subject to determine patient-specific electrode positions of the CI and a patient-specific anatomy shape; generating a CI electric field model based on the patient-specific electrodes positions of the CI and the patient-specific anatomy shape; and establishing an auditory nerve fiber (ANF) bundle model using the CI electric field model, and estimating neural health of the living subject using the ANF bundle model applications of the same.

Abstract: A method for designing a patient-customized EA or selecting an existing EA that fits the patient best includes segmenting shapes of SOIs of the cochlea in a pre-operative CT image using a shape model; defining a 3D curve of interest within the shape model of the SOIs as a sequence of points-; automatically transforming the defined 3D curve to the pre-operative CT image so as to obtain a structure curve in the cochlea; determining a length and curvatures of the structure curve at the sequence of points; and designing a patient-customized EA or selecting an existing EA based on the determined length and curvatures of the structure curve such that after the EA shape model, which estimates the resting state shape of the EA, is rigidly registered to the structure curve in the cochlea, the EA shape model has a registration error smaller than a preset value.

Abstract: A workflow has been developed that enables initially mapping of a focused ultrasound (FUS) beam using magnetic resonance (MR) thermometry or MR-acoustic radiation force imaging (MR-ARFI) while working within the MRI device. During this procedure, key measurements will be taken including the precise location of the transducer relative to the skull and the transducer parameters (such as amplitudes and phases) required to place the ultrasound focus at the desired focal size and location in the skull. The anatomical measurements will be used to build a patient-specific, device-specific stereotactic frame to hold the transducer in the position relative to the skull and the aberration corrects will be applied. FUS therapy can then be delivered to the patient outside of the MR environment.

Abstract: A deep-learning-based method for metal artifact reduction in CT images includes providing a dataset and a cGAN. The dataset includes CT image pairs, randomly partitioned into a training set, a validation set, and a testing set. Each Pre-CT and Post-CT image pairs is respectively acquired in a region before and after an implant is implanted. The Pre-CT and Post-CT images of each pair are artifact-free CT and artifact-affected CT images, respectively. The cGAN is conditioned on the Post-CT images, includes a generator and a discriminator that operably compete with each other, and is characterized with a training objective that is a sum of an adversarial loss and a reconstruction loss. The method also includes training the cGAN with the dataset; inputting the post-operatively acquired CT image to the trained cGAN; and generating an artifact-corrected image by the trained cGAN, where metal artifacts are removed in the artifact-corrected image.

Abstract: A method for active electrode selection in a cochlear implant having an electrode array with a plurality of electrodes implanted in a cochlea of a living subject. The method includes estimating an activation region (AR) of each electrode based on its distance to nerve sites; presenting the AR in a visualization representation, wherein each electrode is represented by a bar having a width or length representing the AR; identifying electrodes having substantial AR overlap if the AR of one electrode overlaps substantially with the AR bar of another electrode; and selecting and deactivating at least one of the identified electrodes with substantial AR overlap.

Abstract: Systems and methods are provided for performing model-based cochlear implant programming (MOCIP) on a living subject with a cochlear implant (CI) to determine stimulation settings of a patient-customized electro-neural interface (ENI) model. The method includes: localizing an electrode array of the CI and intracochlear structures of the living subject to determine patient-specific electrode positions of the CI and a patient-specific anatomy shape; generating a CI electric field model based on the patient-specific electrodes positions of the CI and the patient-specific anatomy shape; and establishing an auditory nerve fiber (ANF) bundle model using the CI electric field model, and estimating neural health of the living subject using the ANF bundle model applications of the same.

Abstract: A method for using information of patient-specific cochlea size and/or shape to determine a patient-customized cochlear implant electrode insertion and placement plan includes segmenting shapes of structures of interest (SOIs) of the cochlea in a pre-operative CT image of the cochlea using a shape model; defining a 3D modiolar hugging curve within the shape model of the SOIs as a sequence of points; automatically transforming the defined 3D modiolar hugging curve to the pre-operative CT image so as to obtain a modiolar curve in the cochlea; rigidly registering an EA shape model of the EA to the modiolar curve in the cochlea, thereby placing a resting state shape of the EA within the patient's SOIs such that the EA matches the modiolar curve in the cochlea; and determining a patient-customized insertion plan for electrode placement using the registered EA shape model.

Abstract: A deep-learning-based method for metal artifact reduction in CT images includes providing a dataset and a cGAN. The dataset includes CT image pairs, randomly partitioned into a training set, a validation set, and a testing set. Each Pre-CT and Post-CT image pairs is respectively acquired in a region before and after an implant is implanted. The Pre-CT and Post-CT images of each pair are artifact-free CT and artifact-affected CT images, respectively. The cGAN is conditioned on the Post-CT images, includes a generator and a discriminator that operably compete with each other, and is characterized with a training objective that is a sum of an adversarial loss and a reconstruction loss. The method also includes training the cGAN with the dataset; inputting the post-operatively acquired CT image to the trained cGAN; and generating an artifact-corrected image by the trained cGAN, where metal artifacts are removed in the artifact-corrected image.

Abstract: A method for designing a patient-customized EA or selecting an existing EA that fits the patient best includes segmenting shapes of SOIs of the cochlea in a pre-operative CT image using a shape model; defining a 3D curve of interest within the shape model of the SOIs as a sequence of points-; automatically transforming the defined 3D curve to the pre-operative CT image so as to obtain a structure curve in the cochlea; determining a length and curvatures of the structure curve at the sequence of points; and designing a patient-customized EA or selecting an existing EA based on the determined length and curvatures of the structure curve such that after the EA shape model, which estimates the resting state shape of the EA, is rigidly registered to the structure curve in the cochlea, the EA shape model has a registration error smaller than a preset value.

Abstract: A method for designing a patient-customized EA or selecting an existing EA that fits the patient best includes segmenting shapes of SOIs of the cochlea in a pre-operative CT image using a shape model; defining a 3D curve of interest within the shape model of the SOIs as a sequence of points-; automatically transforming the defined 3D curve to the pre-operative CT image so as to obtain a structure curve in the cochlea; determining a length and curvatures of the structure curve at the sequence of points; and designing a patient-customized EA or selecting an existing EA based on the determined length and curvatures of the structure curve such that after the EA shape model, which estimates the resting state shape of the EA, is rigidly registered to the structure curve in the cochlea, the EA shape model has a registration error smaller than a preset value.

Abstract: Systems and methods for performing current steering compatible image-guided cochlear implant (CI) electrode deactivation. The cochlear implant includes an electrode array having a plurality of electrodes implanted in a cochlea of a living subject. For each electrode, a corresponding distance-vs-frequency (DVF) curve is obtained. An analysis is performed on the DVF curves to identify the interfering electrodes, each having an interference with at least one other electrode. Then, rules may apply to the interfering electrodes in order to select one or more interfering electrodes to be deactivated. The rules may include: keeping the electrode having a corresponding DVF curve located at a left-most location on the plot to avoid a resulting sound frequency upshift; avoiding leaving any electrode stranded without a neighboring electrode; and deactivating a minimal number of the interfering electrodes to ensure that high interference is allowed only for each electrode with one neighboring electrode.

Abstract: A method for using information of patient-specific cochlea size and/or shape to determine a patient-customized cochlear implant electrode insertion and placement plan includes segmenting shapes of structures of interest (SOIs) of the cochlea in a pre-operative CT image of the cochlea using a shape model; defining a 3D modiolar hugging curve within the shape model of the SOIs as a sequence of points; automatically transforming the defined 3D modiolar hugging curve to the pre-operative CT image so as to obtain a modiolar curve in the cochlea; rigidly registering an EA shape model of the EA to the modiolar curve in the cochlea, thereby placing a resting state shape of the EA within the patient's SOIs such that the EA matches the modiolar curve in the cochlea; and determining a patient-customized insertion plan for electrode placement using the registered EA shape model.

Abstract: A method for designing a patient-customized EA or selecting an existing EA that fits the patient best includes segmenting shapes of SOIs of the cochlea in a pre-operative CT image using a shape model; defining a 3D curve of interest within the shape model of the SOIs as a sequence of points-; automatically transforming the defined 3D curve to the pre-operative CT image so as to obtain a structure curve in the cochlea; determining a length and curvatures of the structure curve at the sequence of points; and designing a patient-customized EA or selecting an existing EA based on the determined length and curvatures of the structure curve such that after the EA shape model, which estimates the resting state shape of the EA, is rigidly registered to the structure curve in the cochlea, the EA shape model has a registration error smaller than a preset value.

Abstract: One aspect of the invention provides a method for customizing cochlear implant stimulation of a living subject. The cochlear implant includes an electrode array having a plurality of electrodes implanted in a cochlea of the living subject. The method includes determining a position for each of the plurality of electrodes and spiral ganglion nerves that the electrode array stimulates, determining a geometric relationship between neural pathways within the cochlea and the electrode array implanted therein, and using one or more electrodes of the electrode array to stimulate a group of SG neural pathways of the cochlea based on the location of the one or more electrodes and their geometric relationship with the neural pathways.

Abstract: Systems and methods for performing current steering compatible image-guided cochlear implant (CI) electrode deactivation. The cochlear implant includes an electrode array having a plurality of electrodes implanted in a cochlea of a living subject. For each electrode, a corresponding distance-vs-frequency (DVF) curve is obtained. An analysis is performed on the DVF curves to identify the interfering electrodes, each having an interference with at least one other electrode. Then, rules may apply to the interfering electrodes in order to select one or more interfering electrodes to be deactivated. The rules may include: keeping the electrode having a corresponding DVF curve located at a left-most location on the plot to avoid a resulting sound frequency upshift; avoiding leaving any electrode stranded without a neighboring electrode; and deactivating a minimal number of the interfering electrodes to ensure that high interference is allowed only for each electrode with one neighboring electrode.

Abstract: One aspect of the invention provides a method for customizing cochlear implant stimulation of a living subject. The cochlear implant includes an electrode array having a plurality of electrodes implanted in a cochlea of the living subject. The method includes determining a position for each of the plurality of electrodes and spiral ganglion nerves that the electrode array stimulates, determining a geometric relationship between neural pathways within the cochlea and the electrode array implanted therein, and using one or more electrodes of the electrode array to stimulate a group of SG neural pathways of the cochlea based on the location of the one or more electrodes and their geometric relationship with the neural pathways.