Medical imaging device- and display-invariant segmentation and measurement
Medical imaging device- and display-invariant segmentation and measurement is provided. In various embodiments, a plurality of medical images is read from a data store. Metadata of each of the plurality of medical images is read. The metadata identifies an image acquisition device associated with each of the plurality of medical images. Based on the plurality of medical images and the metadata of each of the plurality of images, a learning system is trained to determine one or more image correction parameters. The one or more image correction parameters optimize segmentation of the plurality of medical images.
1. A method comprising:
reading a plurality of medical images from a data store;
reading metadata of each of the plurality of medical images, the metadata identifying an image acquisition device associated with each of the plurality of medical images;
based on the plurality of medical images and the metadata of each of the plurality of images, training a learning system to determine one or more image correction parameters, the one or more image correction parameters adapted to optimize the plurality of medical images for segmentation.
2. The method of claim 1 , further comprising:
after training, applying the learning system to determine one or more image correction parameters of an additional medical image.
3. The method of claim 2 , further comprising:
applying the determined one or more image correction parameters to the additional medical image to thereby generate a corrected medical image; and
segmenting the corrected medical image.
4. The method of claim 1 , wherein training the learning system comprises:
determining a segmentation of each of the plurality of medical images;
comparing the segmentation to ground truth.
5. The method of claim 1 , further comprising:
training the learning system to determine one or more segmentation parameters, the one or more segmentation parameters optimizing segmentation of the plurality of medical images.
6. The method of claim 5 , further comprising:
determining an expected error range of the segmentation.
7. The method of claim 1 , wherein the one or more image correction parameters includes window, level, noise, or smoothing.
8. The method of claim 1 , wherein the metadata further identifies one or more image acquisition parameter associated with each of the plurality of medical images.
9. The method of claim 1 , wherein the one or more image correction parameters includes exposure, intensity, image reconstruction kernels, acquisition pixel and slice spacing, contrast agent dose amount, light power, noise, or contrast level.
10. The method of claim 1 , wherein the learning system comprises a genetic algorithm.
11. The method of claim 1 , further comprising:
further training the learning system based on user-generated segmentation.
12. The method of claim 1 , wherein the metadata further comprises an indication of a subject anatomy of the plurality of medical images.
13. A system comprising:
a datastore;
a computing node comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor of the computing node to cause the processor to perform a method comprising:
reading a plurality of medical images from the data store;
reading metadata of each of the plurality of medical images, the metadata identifying an image acquisition device associated with each of the plurality of medical images;
based on the plurality of medical images and the metadata of each of the plurality of images, training a learning system to determine one or more image correction parameters, the one or more image correction parameters adapted to optimize the plurality of medical images for segmentation.
14. A computer program product for providing display-invariant segmentation, 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:
reading a plurality of medical images from a data store;
reading metadata of each of the plurality of medical images, the metadata identifying an image acquisition device associated with each of the plurality of medical images;
based on the plurality of medical images and the metadata of each of the plurality of images, training a learning system to determine one or more image correction parameters, the one or more image correction parameters adapted to optimize the plurality of medical images for segmentation.
15. The computer program product of claim 14 , the method further comprising:
after training, applying the learning system to determine one or more image correction parameters of an additional medical image.
16. The computer program product of claim 15 , the method further comprising:
applying the determined one or more image correction parameters to the additional medical image to thereby generate a corrected medical image; and
segmenting the corrected medical image.
17. The computer program product of claim 14 , wherein training the learning system comprises:
determining a segmentation of each of the plurality of medical images;
comparing the segmentation to ground truth.
18. The computer program product of claim 14 , the method further comprising:
training the learning system to determine one or more segmentation parameters, the one or more segmentation parameters optimizing segmentation of the plurality of medical images.
19. The computer program product of claim 18 , the method further comprising:
determining an expected error range of the segmentation.
20. The computer program product of claim 14 , the method further comprising:
further training the learning system based on user-generated segmentation.