Back to results
US 10,593,051 B2Granted
Medical image registration guided by target lesion
AssigneeInternational Business Machines Corporation
InventorsSun Young Park, Dustin M. Sargent
Life of this patent
Estimating the term…
Abstract
Machine logic (for example, software) for registering multiple medical images, each showing a common lesion, with each other. In performing this registration, registration points are chosen to be both: (i) outside of image portion that is potentially compromised by the lesion (in any of the multiple images); and (ii) as close to the lesion as possible. However, in at least one of the images the extent of the lesion is not known—so, in order to accommodate this uncertainty about the lesion boundaries, lesion predicting machine logic rules are used to predict the size, shape and/or location of the lesion. Machine learning is used to intermittently adjust and improve the lesion predicting machine logic rules.
Claims18
A method comprising:
- receiving, by machine logic, a first medical image including a portion of a subject's body, and a lesion having a first size/shape/location with respect to the subject's body;
- receiving, by machine logic, a second medical image(s) that shows at least a portion of the subject's body, and the lesion having a second size/shape/location with respect to the subject's body;
- choosing, by machine logic, a plurality of candidate registration points, with each candidate registration point corresponding to a machine logic identifiable location in the subject's body, and with each candidate registration point being shown in both of the first medical image and the second medical image;
- receiving, by machine logic, a subject medical data set including at least one diagnostic report and at least one structured report based on examination of the subject;
- applying, by machine logic, a set of lesion-development-related machine logic based rules to determine, based at least in part on the subject medical data set, a potentially compromised area in the second medical image, with the potentially compromised area being an area that is potentially affected by the lesion as shown in the second medical image at the second size/shape/location;
- selecting, by machine logic, a plurality of selected registration points from the plurality of candidate registration points such that the selected registration points are shown in the second medical image:
- (i) outside of the potentially compromised area, and (ii) relatively close to the potentially compromised area;
- and
- registering, by machine logic, at least the first and second medical images with each other using the set of selected registration points.
6 more elements
A computer program product (CPP) comprising:
- a computer readable storage medium configured to store computer code executable by a processor(s) set;
- and
- computer code stored on the computer readable storage medium, with the computer code including data and instructions for causing the processor(s) set to perform at least the following operations:
- receiving, by machine logic, a first medical image including a portion of a subject's body, and a lesion having a first size/shape/location with respect to the subject's body,
- receiving, by machine logic, a second medical image(s) that shows at least a portion of the subject's body, and the lesion having a second size/shape/location with respect to the subject's body,
- choosing, by machine logic, a plurality of candidate registration points, with each candidate registration point corresponding to a machine logic identifiable location in the subject's body, and with each candidate registration point being shown in both of the first medical image and the second medical image,
- receiving, by machine logic, a subject medical data set including at least one diagnostic report and at least one structured report based on examination of the subject,
- applying, by machine logic, a set of lesion-development-related machine logic based rules to determine, based at least in part on the subject medical data set, a potentially compromised area in the second medical image, with the potentially compromised area being an area that is potentially affected by the lesion as shown in the second medical image at the second size/shape/location,
- selecting, by machine logic, a plurality of selected registration points from the plurality of candidate registration points such that the selected registration points are shown in the second medical image:
- (i) outside of the potentially compromised area, and (ii) relatively close to the potentially compromised area, and
- registering, by machine logic, at least the first and second medical images with each other using the set of selected registration points.
8 more elements
A computer system (CS) comprising:
- a processor(s) set;
- a computer readable storage medium configured to store computer code executable by a processor(s) set;
- and
- computer code stored on the computer readable storage medium, with the computer code including data and instructions for causing the processor(s) set to perform at least the following operations:
- receiving, by machine logic, a first medical image including a portion of a subject's body, and a lesion having a first size/shape/location with respect to the subject's body,
- receiving, by machine logic, a second medical image(s) that shows at least a portion of the subject's body, and the lesion having a second size/shape/location with respect to the subject's body,
- choosing, by machine logic, a plurality of candidate registration points, with each candidate registration point corresponding to a machine logic identifiable location in the subject's body, and with each candidate registration point being shown in both of the first medical image and the second medical image,
- receiving, by machine logic, a subject medical data set including at least one diagnostic report and at least one structured report based on examination of the subject,
- applying, by machine logic, a set of lesion-development-related machine logic based rules to determine, based at least in part on the subject medical data set, a potentially compromised area in the second medical image, with the potentially compromised area being an area that is potentially affected by the lesion as shown in the second medical image at the second size/shape/location,
- selecting, by machine logic, a plurality of selected registration points from the plurality of candidate registration points such that the selected registration points are shown in the second medical image:
- (i) outside of the potentially compromised area, and (ii) relatively close to the potentially compromised area, and
- registering, by machine logic, at least the first and second medical images with each other using the set of selected registration points.
9 more elements
Dependencies are inferred from the claim text.