JPWO2021136971A5

JPWO2021136971A5 -

Info

Publication number: JPWO2021136971A5
Application number: JP2022540520A
Authority: JP
Publication date: 2023-12-27

Claims

determining a plurality of sets of image data associated with a plurality of patients, each patient being associated with a set of image data derived from imaging a portion of said patient; Each set includes a plurality of voxels, each voxel of the plurality of voxels labeled with a tissue type, and each voxel of the plurality of voxels labeled with a transducer array to the portion of the patient. a step labeled with a field strength distribution value (Vcm ^-1 ) derived from the simulated application of an alternating electric field from the pair;
determining a plurality of features for a predictive model based on a first portion of the plurality of sets of image data;
training the predictive model based on the plurality of features and the first portion of the plurality of sets of image data, the predictive model configured to estimate electric field strength distribution values; step and
testing the predictive model based on a second portion of the plurality of sets of image data;
outputting the predictive model based on test results.

Said step of determining a plurality of sets of image data comprises:
determining RAW image data for each patient, the RAW image data including a plurality of voxels;
assigning a tissue type to each voxel of the plurality of voxels;
simulating the application of alternating electric fields from a pair of transducer arrays at a plurality of locations within the RAW image data based on the tissue type of each voxel;
labeling each voxel of the plurality of voxels of the RAW image data with the tissue type, the simulated electric field, and the location associated with the simulated electric field;
and generating the plurality of sets of image data based on the labeled RAW image data.

The step of determining a plurality of features for a predictive model based on a first portion of the plurality of sets of image data includes a feature selection technique including one or more of a filter method, a wrapper method, or an embedding method. 2. The method of claim 1, comprising:

2. The method of claim 1, wherein the plurality of features include two or more of a conductivity value, a dielectric constant value, a distance to the nearest transducer array, or a distance to the nearest conductive material.

The step of training the predictive model based on the plurality of features and the first portion of the plurality of sets of image data includes one or more of discriminant analysis, decision trees, statistical algorithms, or neural networks. 2. The method of claim 1, comprising machine learning techniques comprising:

determining a new set of image data for a new patient, the new set of image data including a plurality of voxels;
presenting the new set of image data to the predictive model;
and estimating, with the predictive model, one or more electric field distribution strength values for the pair of transducer arrays at each of a plurality of locations for each voxel of the plurality of voxels. Method described.

7. The method of claim 6, further comprising: selecting one of the plurality of locations based on the estimated one or more electric field distribution strength values.

determining a tissue type for each voxel of the plurality of voxels of the new set of image data;
and determining, for each voxel of the plurality of voxels of the new set of image data, a conductivity value, a permittivity value, a distance to the nearest transducer array, and a distance to the nearest conductive material. 7. The method of claim 6, comprising:

A device,
one or more processors;
a memory for storing processor-executable instructions;
9. An apparatus, wherein the instructions, when executed by the one or more processors, cause the apparatus to perform a method according to any one of claims 1 to 8 .

One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 8 .

determining a set of image data for one patient, the set of image data including a plurality of voxels;
presenting the set of image data to a predictive model, the predictive model generating field strength distribution values based on one or more simulated alternating electric fields from a pair of transducer arrays at a plurality of locations; a step configured to estimate
estimating, for each voxel of the plurality of voxels, one or more electric field distribution strength values for the pair of transducer arrays at each of a plurality of locations with the predictive model;
of the plurality of locations based on the estimated one or more electric field distribution strength values for the pair of transducer arrays at each of the plurality of locations, a region of interest, and anatomical constraints associated with the patient. and determining a transducer array map including one or more locations of the transducer array.

12. The method of claim 11 , further comprising: selecting one of the plurality of locations based on the estimated one or more electric field distribution strength values.

determining a tissue type for each voxel of the plurality of voxels of the set of image data;
and determining, for each voxel of the plurality of voxels of the set of image data, a conductivity value, a permittivity value, a distance to the nearest transducer array, and a distance to the nearest conductive material. , the method of claim 11 .

A device,
one or more processors;
memory that stores processor-executable instructions;
Equipped with
14. An apparatus, wherein the instructions, when executed by the one or more processors, cause the apparatus to perform a method according to any one of claims 11 to 13.

One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by a processor, cause the processor to perform the method of any one of claims 11-13 .