Computer-assisted data processing system and method incorporating automated learning
View Patent ↗A technique is provided for enhancing performance of computer-assisted data operating algorithms in a medical context. Datasets are compiled and accessed, which may include data from a wide range of resources, including controllable and prescribable resources, such as imaging systems. The datasets are analyzed by a human expert or medical professional, and the algorithms are modified based upon feedback from the human expert or professional. Modifications may be made to a wide range of algorithms and based upon a wide range of data, such as available from an integrated knowledge base. Modifications may be made in sub-modules of the algorithms providing enhanced functionality. Modifications may also be made on various bases, including patient-specific changes, population-specific changes, feature-specific changes, and so forth.
1. A computer implemented method for modifying a computer-assisted data operating algorithm, the method comprising:
analyzing a data set representative of an image via the computer-assisted data operating algorithm to generate a result data set identifying a feature of interest;
monitoring for changes in the result data set based upon input from a human expert;
modifying at least one submodule of the computer-assisted data operating algorithm without operator intervention based upon the changed result data set;
validating a modification of the computer-assisted data operating algorithm prior to modifying the at least one submodule; and
displaying a reconstructed image based upon the result data set.
2. The method of claim 1 , wherein the image is displayed for modification by the human expert.
3. The method of claim 1 , wherein the computer-assisted data operating algorithm is selected from a group consisting of computer-assisted detection algorithms, computer-assisted diagnosis algorithms, computer-assisted decision support algorithms, computer-assisted acquisition algorithms, computer-assisted analysis algorithms, computer-assisted processing algorithms, computer-assisted prognosis algorithms, computer-assisted treatment algorithms, computer-assisted prescription algorithms, and computer-assisted assessment algorithms.
4. The method of claim 1 , wherein the submodule affects feature detection performed by the computer-assisted data operating algorithm.
5. The method of claim 1 , wherein the submodule affects feature segmentation performed by the computer-assisted data operating algorithm.
6. The method of claim 1 , wherein the submodule affects feature classification performed by the computer-assisted data operating algorithm.
7. A computer implemented method for modifying a computer-assisted data operating algorithm, the method comprising:
accessing image data derived from a medical imaging system, and supplemental data from an integrated knowledge base including clinical and non-clinical data from a plurality of controllable and prescribable data resources;
analyzing the image data and the supplemental data via the computer-assisted data operating algorithm to generate a result data set identifying a feature of interest in the image data;
modifying the result data set based upon correction by a human medical professional;
modifying at least one submodule of the computer-assisted data operating algorithm based upon the changed result data set; and
displaying a reconstructed image based upon the result data set.
8. The method of claim 7 , wherein the modification to the at least one submodule is a patient-specific parameter.
9. The method of claim 8 , wherein the submodule is modified for a population of patients based upon a characteristic shared by members of the population.
10. The method of claim 7 , wherein the supplemental data is patient-specific.
11. The method of claim 7 , wherein the supplemental data includes data selected from a group consisting of electrical resource data, imaging resource data, laboratory data, histologic data, financial data, and demographic data.
12. The method of claim 7 , wherein the image data is displayed for modification by the human medical professional.
13. The method of claim 7 , further comprising validating that a modification of the computer-assisted data operating algorithm is desired prior to modifying the at least one parameter.
14. The method of claim 7 , wherein the computer-assisted data operating algorithm is a computer-assisted diagnosis algorithm.
15. The method of claim 7 , wherein the computer-assisted data operating algorithm is selected from a group consisting of computer-assisted detection algorithms, computer-assisted diagnosis algorithms, computer-assisted decision support algorithms, computer-assisted acquisition algorithms, computer-assisted analysis algorithms, computer-assisted processing algorithms, computer-assisted prognosis algorithms, computer-assisted treatment algorithms, computer-assisted prescription algorithms, and computer-assisted assessment algorithms.
16. The method of claim 7 , wherein the parameter affects feature detection performed by the computer-assisted data operating algorithm.
17. The method of claim 7 , wherein the parameter affects feature segmentation performed by the computer-assisted data operating algorithm.
18. The method of claim 7 , wherein the parameter affects feature classification performed by the computer-assisted data operating algorithm.
19. A computer-readable storage medium comprising:
computer code comprising instructions for analyzing a data set via a computer-assisted data operating algorithm to generate a result data set identifying a feature of interest, monitoring for changes in the result data set based upon input from a human expert, modifying at least one submodule of the computer-assisted data operating algorithm without operator intervention based upon the changed result data set, validating a modification of the computer-assisted data operating algorithm prior to modifying the at least one submodule.
20. A computer-readable storage medium comprising:
computer code comprising instructions for accessing image data derived from a medical imaging system, and supplemental data from an integrated knowledge base including clinical and non-clinical data from a plurality of controllable and prescribable data resources, analyzing the image data and the supplemental data via a computer-assisted data operating algorithm to generate a result data set identifying a feature of interest in the image data, modifying the result data set based upon correction by a human medical professional, and modifying at least one submodule of the computer-assisted data operating algorithm based upon the changed result data set.