Artificial intelligence system including three-dimensional labeling using frame of reference projections
A method includes receiving a plurality of images, each of the plurality of images being a two-dimensional view of a portion of a three-dimensional object; receiving a definition of a three-dimensional volume in a same frame of reference as the plurality of images; receiving a label for the three-dimensional volume; projecting the three-dimensional volume onto each of the plurality of images; determining, for each of the plurality of images an image metric; and determining whether to assign the label to respective ones of the plurality of images based on the image metric.
1 . A computer-implemented method, comprising:
receiving, by one or more processors, a plurality of images;
receiving, by the one or more processors, a definition of a three-dimensional volume in a same frame of reference as the plurality of images, wherein the three-dimensional volume is defined based on an intersection of a first two-dimensional bounding box in the same frame of reference and a second two-dimensional bounding box in the same frame of reference;
receiving, by the one or more processors, a label for the three-dimensional volume;
projecting, by the one or more processors, the three-dimensional volume onto each image of the plurality of images;
determining, by the one or more processors and for each image of the plurality of images, an image metric based on the projecting of the three-dimensional volume onto the image, the image metric including, for an image surface area metric defined by a ratio of a first amount of surface area of the image that is contained within the three-dimensional volume to a second amount of surface area of the image that is contained outside of the three-dimensional volume; and
labeling, by the one or more processors and for each image of the plurality of images, the image with the label for the three-dimensional volume when the image metric for the image satisfies an image surface area metric threshold.
2 . The computer-implemented method of claim 1 , wherein the image surface area metric threshold comprises a surface area percentage threshold.
3 . The computer-implemented method of claim 1 , further comprising:
training, by the one or more processors, a machine learning engine using images, of the plurality of images, that have been labeled with the label for the three-dimensional volume.
4 . The computer-implemented method of claim 3 , further comprising:
generating, by the one or more processors, an artificial intelligence engine based on the machine learning engine that has been trained.
5 . The computer-implemented method of claim 1 , wherein the plurality of images is associated with a regulatory constraint of a governmental administrative authority.
6 . The computer-implemented method of claim 5 , wherein:
the plurality of images comprises Protected Health Information (PHI); and
the regulatory constraint comprises a Health Insurance Portability and Accountability Act (HIPAA) constraint.
7 . A system, comprising:
one or more processors; and
at least one memory storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving a plurality of images;
receiving a definition of a three-dimensional volume in a same frame of reference as the plurality of images, wherein the three-dimensional volume is defined based on an intersection of a first two-dimensional bounding box in the same frame of reference and a second two-dimensional bounding box in the same frame of reference;
receiving a label for the three-dimensional volume;
projecting, by the one or more processors, the three-dimensional volume onto each image of the plurality of images;
determining, for each image of the plurality of images, an image metric based on the projecting of the three-dimensional volume onto the image, the image metric including an image surface area metric defined by a ratio of a first amount of surface area of the image that is contained within the three-dimensional volume to a second amount of surface area of the image that is contained outside of the three-dimensional volume; and
labeling, for each image of the plurality of images, the image with the label for the three-dimensional volume when the image metric for the image satisfies an image surface area metric threshold.
8 . The system of claim 7 , wherein the image surface area metric threshold comprises a surface area percentage threshold.
9 . The system of claim 7 , wherein the operations further comprise:
training a machine learning engine using images, of the plurality of images, that have been labeled with the label for the three-dimensional volume.
10 . The system of claim 9 , wherein the operations further comprise:
generating an artificial intelligence engine based on the machine learning engine that has been trained.
11 . The system of claim 7 , wherein the plurality of images is associated with a regulatory constraint of a governmental administrative authority.
12 . The system of claim 11 , wherein:
the plurality of images comprises Protected Health Information (PHI); and
the regulatory constraint comprises a Health Insurance Portability and Accountability Act (HIPAA) constraint.
13 . One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving, a plurality of images;
receiving, a definition of a three-dimensional volume in a same frame of reference as the plurality of images, wherein the three-dimensional volume is defined based on an intersection of a first two-dimensional bounding box in the same frame of reference and a second two-dimensional bounding box in the same frame of reference;
receiving a label for the three-dimensional volume;
projecting the three-dimensional volume onto each image of the plurality of images;
determining, for each image of the plurality of images, an image metric based on the projecting of the three-dimensional volume onto the image, the image metric including an image surface area metric defined by a ratio of a first amount of surface area of the image that is contained within the three-dimensional volume to a second amount of surface area of the image that is contained outside of the three-dimensional volume; and
labeling, for each image of the plurality of images, the image with the label for the three-dimensional volume when the image metric for the image satisfies an image surface area metric threshold.
14 . The one or more non-transitory computer-readable media of claim 13 , wherein the image surface area metric threshold comprises a surface area percentage threshold.
15 . The one or more non-transitory computer-readable media of claim 13 , wherein the operations further comprise:
training a machine learning engine using images, of the plurality of images, that have been labeled with the label for the three-dimensional volume.
16 . The one or more non-transitory computer-readable media of claim 15 , wherein the operations further comprise:
generating an artificial intelligence engine based on the machine learning engine that has been trained.
17 . The one or more non-transitory computer-readable media of claim 13 , wherein the plurality of images is associated with a regulatory constraint of a governmental administrative authority.
18 . The one or more non-transitory computer-readable media of claim 13 , wherein:
the plurality of images comprises Protected Health Information (PHI); and
the regulatory constraint comprises a Health Insurance Portability and Accountability Act (HIPAA) constraint.