Automated calibration and quality assurance of medical images
AssigneeInternational Business Machines Corporation
InventorMark Bronkalla
Life of this patent
Estimating the term…
Abstract
Self-describing calibration targets for inclusion in medical imagery and automated quality control and calibration are provided. In various embodiments, a medical image is received. The medical image includes a calibration target in its field of view. A description of the calibration target is read from the calibration target. The description includes size and at least one color reference. Based on the description of the calibration target, correction parameters are determined for the medical image. The correction parameters include pixel shape correction parameters, scale correction parameters, contrast correction parameters, or color correction parameters.
Claims20
A method comprising:
- receiving a medical image including a calibration target, the calibration target having a size and at least one color, the calibration target comprising a self-descriptor and swatches of a plurality of different percentages of a single color, the self-descriptor comprising encoded information defining the size and the plurality of different percentages;
- reading from the calibration target the self-descriptor of the calibration target;
- based on the self-descriptor of the calibration target, determining correction parameters for the medical image, the correction parameters comprising pixel shape correction parameters, scale correction parameters, contrast correction parameters, or color correction parameters.
A computer program product for automated calibration of medical imagery, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:
- receiving a medical image including a calibration target, the calibration target having a size and at least one color, the calibration target comprising a self-descriptor and swatches of a plurality of different percentages of a single color, the self-descriptor comprising encoded information defining the size and the plurality of different percentages;
- reading from the calibration target the self-descriptor of the calibration target;
- based on the self-descriptor of the calibration target, determining correction parameters for the medical image, the correction parameters comprising pixel shape correction parameters, scale correction parameters, contrast correction parameters, or color correction parameters.
Dependencies are inferred from the claim text.