Automated peer review of medical imagery

1. A method comprising:

determining, at a remote server, at least one finding for a present study by applying computer-aided diagnosis comprising at least one of: image cognition to at least one image in the present study, natural language processing of at least one note in the present study, or extraction of image annotation in the present study, the present study comprising a pathology report or surgical report, the present study having a subject anatomy;

determining, at the remote server, based on the at least one finding and the subject anatomy of the present study, at least one prior study that does not include the at least one finding of the present study from a plurality of prior studies by applying natural language processing to text from each of the plurality of prior studies, each prior study comprising a prior radiology report, each prior radiology report including the subject anatomy and having occurred before the present study;

determining, at the remote server, at least one additional finding from the at least one prior study by applying computer-aided diagnosis comprising image cognition to each prior radiology report in the at least one prior study;

determining, at the remote server, whether the at least one finding of the present study is associated with the at least one additional finding of the at least one prior study by cross-correlating the at least one finding of the present study with the at least one additional finding of the at least one prior study;

when the at least one finding of the present study is associated with the at least one additional finding, flagging the at least one prior study for review; and

loading the flagged at least one prior study into a Picture Archiving and Communication System (PACS) workstation for review.

2. The method of claim 1 , further comprising:

computing an accuracy score based on whether the at least one finding is associated with the at least one previous finding of the at least one prior study.

3. The method of claim 1 , further comprising:

providing, over a network, the at least one prior study to a user for review with respect to the at least one finding.

4. The method of claim 1 , wherein the at least one prior study is selected such that it can support or refute the at least one finding upon review.

5. The method of claim 1 , wherein the at least one prior study are providing to the user for review as a time series.

6. The method of claim 1 , wherein the at least one finding is determined from the pathology report or the surgical note by natural language processing.

7. The method of claim 1 , wherein the at least one finding is determined from image annotation.

8. The method of claim 1 , wherein the at least one prior study having an original reviewer, and wherein the user for review is selected to be other than the original reviewer.

9. A computer program product for analyzing medical images, 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:

determining, at a remote server, at least one finding for a present study by applying computer-aided diagnosis comprising at least one of: image cognition to at least one image in the present study, natural language processing of at least one note in the present study, or extraction of image annotation in the present study, the present study comprising a pathology report or surgical report, the present study having a subject anatomy;

determining, at the remote server, based on the at least one finding and the subject anatomy of the present study, at least one prior study that does not include the at least one finding of the present study from a plurality of prior studies by applying natural language processing to text from each of the plurality of prior studies, each prior study comprising a prior radiology report, each prior radiology report including the subject anatomy and having occurred before the present study;

determining, at the remote server, at least one additional finding from the at least one prior study by applying computer-aided diagnosis comprising image cognition to each prior radiology report in the at least one prior study;

determining, at the remote server, whether the at least one finding of the present study is associated with the at least one additional finding of the at least one prior study by cross-correlating the at least one finding of the present study with the at least one additional finding of the at least one prior study;

when the at least one finding of the present study associated with the at least one additional finding, flagging the at least one prior study for review; and

loading the flagged at least one prior study into a Picture Archiving and Communication System (PACS) workstation for review.

10. The computer program product of claim 9 , the method further comprising:

computing an accuracy score based on whether the at least one finding is associated with the at least one previous finding of the at least one prior study.

11. The computer program product of claim 9 , the method further comprising:

providing, over a network, the at least one prior study to a user for review with respect to the at least one finding.

12. The computer program product of claim 9 , wherein the at least one prior study is selected such that it can support or refute the at least one finding upon review.

13. The computer program product of claim 9 , wherein the at least one prior study are providing to the user for review as a time series.