Determining appropriate medical image processing pipeline based on machine learning

1. A method, in a data processing system comprising at least one processor and at least one memory, wherein the at least one memory comprises instructions that are executed by the at least one processor to cause the at least one processor to implement an automated medical image processing pipeline selection system, and wherein the method comprises:

analyzing, by a medical image analytics subsystem of the automated medical processing pipeline, medical image data to extract first evidence data comprising characteristics of one or more medical images in the medical image data;

analyzing, by a text analytics subsystem of the automated medical processing pipeline, text data associated with the medical image data to extract second evidence data;

applying, by a machine learning model, a machine learning based analysis of both the first evidence data and the second evidence data to deduce at least one characteristic of the medical image data;

selecting, by the machine learning model, a medical image processing pipeline based on results of the machine learning based analysis of the first evidence data and second evidence data; and

processing, by the selected medical image processing pipeline, the medical image data to generate a results output.

2. The method of claim 1 , wherein the medical image analytics subsystem comprises a metadata parser and analytic subsystem that parses and analyzes metadata associated with the one or more medical images to determine characteristics of the one or more medical images specified in the metadata.

3. The method of claim 1 , wherein the medical image analytics subsystem comprises medical image analysis logic that analyzes graphical characteristics of the one or more medical images to determine characteristics of the one or more medical images.

4. The method of claim 1 , wherein the characteristics of the one or more medical images comprise at least one of image dimensionality, image modality, image modality mode, image modality view, imaging body part, imaging anatomical structure, targeted disease, or targeted abnormality.

5. The method of claim 1 , wherein the text data associated with the medical image data comprises a medical imaging report referencing the one or more medical images.

6. The method of claim 5 , wherein analyzing the text data associated with the medical image data comprises determining, by the text analytics subsystem, whether the second evidence comprises hint text indicating a medical image processing pipeline to select for processing the medical image data, wherein in response to the text data not comprising hint text indicating a medical image processing pipeline to select, the machine learning model selects the medical image processing pipeline based on machine learning based analysis of both the first evidence data and the second evidence data.

7. The method of claim 6 , wherein, in response to the second evidence data comprising hint text indicating a medical image processing pipeline to select for processing the medical image data, the indicated medical image processing pipeline is selected.

8. The method of claim 1 , wherein selecting, by the machine learning model, a medical image processing pipeline based on a machine learning based analysis of the first evidence data and second evidence data comprises automatically generating a new medical image processing pipeline based on the machine learning based analysis, wherein the new medical image processing pipeline comprises a plurality of medical image analysis algorithms selected from a collection of medical image analysis algorithms.

9. The method of claim 8 , wherein the plurality of medical image analysis algorithms comprise at least one of a segmentation analysis algorithm, a registration analysis algorithm, a classification analysis algorithm, an abnormality detection algorithm, or a disease detection algorithm.

10. The method of claim 1 , wherein the selected medical image processing pipeline is selected from a collection of medical image processing pipelines, and wherein each medical image processing pipeline comprises a differently configured plurality of medical image analysis algorithms, and wherein, for each of the medical image processing pipelines in the collection of medical image processing pipelines, a corresponding plurality of medical image analysis algorithms comprise at least one of a segmentation analysis algorithm, a registration analysis algorithm, a classification analysis algorithm, an abnormality detection algorithm, or a disease detection algorithm.

11. A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a data processing system, causes the data processing system to implement an automated medical image processing pipeline selection system, and wherein the computer readable program further causes the data processing system to:

analyze, by a medical image analytics subsystem of the automated medical processing pipeline, medical image data to extract first evidence data comprising characteristics of one or more medical images in the medical image data;

analyze, by a text analytics subsystem of the automated medical processing pipeline, text data associated with the medical image data to extract second evidence data;

apply, by a machine learning model, a machine learning based analysis of both the first evidence data and the second evidence data to deduce at least one characteristic of the medical image data;

select, by the machine learning model, a medical image processing pipeline based on results of the machine learning based analysis of the first evidence data and second evidence data; and

process, by the selected medical image processing pipeline, the medical image data to generate a results output.

12. The computer program product of claim 11 , wherein the medical image analytics subsystem comprises a metadata parser and analytic subsystem that parses and analyzes metadata associated with the one or more medical images to determine characteristics of the one or more medical images specified in the metadata.

13. The computer program product of claim 11 , wherein the medical image analytics subsystem comprises medical image analysis logic that analyzes graphical characteristics of the one or more medical images to determine characteristics of the one or more medical images.

14. The computer program product of claim 11 , wherein the characteristics of the one or more medical images comprise at least one of image dimensionality, image modality, image modality mode, image modality view, imaging body part, imaging anatomical structure, targeted disease, or targeted abnormality.

15. The computer program product of claim 11 , wherein the text data associated with the medical image data comprises a medical imaging report referencing the one or more medical images.

16. The computer program product of claim 15 , wherein analyzing the text data associated with the medical image data comprises determine, by the text analytics subsystem, whether the second evidence comprises hint text indicating a medical image processing pipeline to select for processing the medical image data, wherein in response to the text data not comprising hint text indicating a medical image processing pipeline to select, the machine learning model selects the medical image processing pipeline based on machine learning based analysis of both the first evidence data and the second evidence data.

17. The computer program product of claim 16 , wherein, in response to the second evidence data comprising hint text indicating a medical image processing pipeline to select for processing the medical image data, the indicated medical image processing pipeline is selected.

18. The computer program product of claim 11 , wherein the computer readable program further causes the data processing system to select, by the machine learning model, a medical image processing pipeline based on a machine learning based analysis of the first evidence data and second evidence data at least by automatically generating a new medical image processing pipeline based on the machine learning based analysis, wherein the new medical image processing pipeline comprises a plurality of medical image analysis algorithms selected from a collection of medical image analysis algorithms.

19. The computer program product of claim 18 , wherein the plurality of medical image analysis algorithms comprise at least one of a segmentation analysis algorithm, a registration analysis algorithm, a classification analysis algorithm, an abnormality detection algorithm, or a disease detection algorithm.

20. A data processing system comprising:

at least one processor; and

at least one memory coupled to the at least one processor, wherein the at least one memory comprises instructions which, when executed by the at least one processor, cause the at least one processor to implement an automated medical image processing pipeline selection system, and wherein the instructions further cause the at least one processor to:

analyze, by a medical image analytics subsystem of the automated medical processing pipeline, medical image data to extract first evidence data comprising characteristics of one or more medical images in the medical image data;

analyze, by a text analytics subsystem of the automated medical processing pipeline, text data associated with the medical image data to extract second evidence data;

apply, by a machine learning model, a machine learning based analysis of both the first evidence data and the second evidence data to deduce at least one characteristic of the medical image data;

select, by the machine learning model, a medical image processing pipeline based on results of the machine learning based analysis of the first evidence data and second evidence data; and

process, by the selected medical image processing pipeline, the medical image data to generate a results output.