Integrated deep learning and clinical image viewing and reporting
View Patent ↗Integrated deep learning and clinical image viewing and reporting are provided. In some embodiments, a clinical image is received. An annotated image is generated from the clinical image by application of a deep learning system. At least one clinical finding is generated from the clinical image by application of the deep learning system. The annotated image and the at least one clinical finding are provided to a user. A structured report is generated based on the annotated image and the at least one clinical finding.
1. A method comprising:
receiving a clinical image;
generating an annotated image from the clinical image by application of a deep learning system;
generating at least one clinical finding based on the clinical image by application of the deep learning system;
providing the annotated image and the at least one clinical finding to a user;
generating a structured report based on the annotated image and the at least one clinical finding.
2. The method of claim 1 , further comprising:
receiving from the user a plurality of updated annotations to the annotated image;
training the deep learning system based on the plurality of updated annotations.
3. The method of claim 1 , further comprising:
receiving clinical data associated with the clinical image, and wherein the at least one clinical finding is based on the clinical data associated with the clinical image.
4. The method of claim 1 , wherein the clinical image comprises computed tomography, magnetic resonance imagery, ultrasound imagery, white light imaging, positron emission tomography imagery, angiography, single-photon emission computed tomography, or X-ray imagery.
5. The method of claim 1 , further comprising acquiring the clinical image from a medical imaging modality.
6. The method of claim 1 , wherein the deep learning system comprises an artificial neural network.
7. The method of claim 1 , wherein providing the annotated image to the user comprises:
providing an annotation layer reflecting features of interest.
8. The method of claim 7 , wherein the annotation layer comprises grey scale presentation states objects, structured report objects, or secondary capture objects.
9. The method of claim 1 , wherein providing the annotated image comprises displaying the annotated image through a viewer.
10. The method of claim 1 , wherein providing the annotated image and the at least one clinical finding to the user comprises routing through a gateway.
11. The method of claim 1 , further comprising:
receiving from the user a plurality of updates to the at least one clinical finding;
updating the structured report based on the plurality of updates to the at least one clinical finding.
12. The method of claim 11 , further comprising:
training the deep learning system based on the plurality of updates to the at least one clinical finding.
13. The method of claim 11 , further comprising:
storing the updated structured report in a data store.
14. A computer program product for clinical reporting, 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 clinical image;
generating an annotated image from the clinical image by application of a deep learning system;
generating at least one clinical finding based on the clinical image by application of the deep learning system;
providing the annotated image and the at least one clinical finding to a user;
generating a structured report based on the annotated image and the at least one clinical finding.
15. The computer program product of claim 14 , the method further comprising:
receiving from the user a plurality of updated annotations to the annotated image;
updating the structured report based on the plurality of updated annotations;
training the deep learning system based on the plurality of updated annotations.
16. The computer program product of claim 14 , the method further comprising:
receiving clinical data associated with the clinical image, and wherein the at least one clinical finding is based on the clinical data associated with the clinical image.
17. The computer program product of claim 14 , the method further comprising acquiring the clinical image from a medical imaging modality.
18. The computer program product of claim 14 , wherein providing the annotated image to the user comprises:
providing an annotation layer reflecting features of interest.
19. The computer program product of claim 14 , the method further comprising:
receiving from the user a plurality of updates to the at least one clinical finding;
updating the structured report based on the plurality of updates to the at least one clinical finding.
20. The computer program product of claim 19 , the method further comprising:
training the deep learning system based on the plurality of updates to the at least one clinical finding.