Systems and methods for processing images to prepare slides for processed images for digital pathology
Systems and methods are disclosed for processing an electronic image corresponding to a specimen. One method for processing the electronic image includes: receiving a target electronic image of a slide corresponding to a target specimen, the target specimen including a tissue sample from a patient, applying a machine learning system to the target electronic image to determine deficiencies associated with the target specimen, the machine learning system having been generated by processing a plurality of training images to predict stain deficiencies and/or predict a needed recut, the training images including images of human tissue and/or images that are algorithmically generated; and based on the deficiencies associated with the target specimen, determining to automatically order an additional slide to be prepared.
1. A computer-implemented method for processing an electronic image corresponding to a specimen, the method comprising:
receiving a target electronic image of a slide corresponding to a target specimen, the target specimen comprising a tissue sample from a patient;
applying a machine learning system to the target electronic image to predict a likelihood that a new stain is desired for the slide, the machine learning system having been generated by processing a plurality of training images and training data associated with the training images to predict a likelihood that a new stain is desired for the slide, each of the plurality of training images associated with a stain order; and
based on the predicted likelihood that a new stain is desired for the slide, determining to automatically order an additional slide to be prepared.
2. The computer-implemented method of claim 1 , further comprising:
receiving one or both of a tissue type from which the specimen was harvested or any diagnostic data associated with a selected patient or a selected case.
3. The computer-implemented method of claim 1 , further comprising:
generating a visual indicator of the predicted likelihood that a new stain is desired for the slide; and
outputting, to a graphical user interface associated with a user, the visual indicator.
4. The computer-implemented method of claim 1 , wherein the applying a machine learning system to the target electronic image to predict a likelihood that a new stain is desired for the slide further comprises determining at least one of low model information, predicted high risk lesions, a diagnosis that may automatically need additional tests, or suspicious morphology that automatically triggers genetic testing.
5. The computer-implemented method of claim 4 , further comprising:
predict the likelihood that the new stain is desired for the slide to within a threshold based on the determined diagnosis.
6. The computer-implemented method of claim 1 , further comprising:
detecting whether an image enhancement or an improved slide is desired; and
upon determining the image enhancement or the improved slide and the predicted likelihood that a new stain are desired for the slide, determining to automatically order an additional slide to be prepared.
7. The computer-implemented method of claim 1 , wherein each of the plurality of training images is associated with an indication of whether a pathologist ordered a new stain for that slide.
8. The computer-implemented method of claim 1 , wherein the slide comprising the sample of tissue is stained with hematoxylin and eosin.
9. The computer-implemented method of claim 1 , further comprising:
storing, via a data storage device configured to store patient data, one or both of the predicted likelihood that a new stain is desired for the slide or the determination to automatically order an additional slide to be prepared.
10. The computer-implemented method of claim 1 , wherein the training data further comprises additional information about the specimen of the slide.
11. A system for processing images, the system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform operations comprising:
receiving a target electronic image of a slide corresponding to a target specimen, the target specimen comprising a tissue sample from a patient;
applying a machine learning system to the target electronic image to predict a likelihood that a new stain is desired for the slide, the machine learning system having been generated by processing a plurality of training images and training data associated with the training images to predict a likelihood that a new stain is desired for the slide, each of the plurality of training images associated with a stain order; and
based on the predicted likelihood that a new stain is desired for the slide, determining to automatically order an additional slide to be prepared.
12. The system of claim 11 , further comprising:
receiving one or both of a tissue type from which the specimen was harvested or any diagnostic data associated with a selected patient or a selected case.
13. The system of claim 11 , further comprising:
generating a visual indicator of the predicted likelihood that a new stain is desired for the slide; and
outputting, to a graphical user interface associated with a user, the visual indicator.
14. The system of claim 11 , wherein the applying a machine learning system to the target electronic image to predict a likelihood that a new stain is desired for the slide further comprises determining at least one of low model information, predicted high risk lesions, a diagnosis that may automatically need additional tests, or suspicious morphology that automatically triggers genetic testing.
15. The system of claim 14 , further comprising:
predict the likelihood that the new stain is desired for the slide to within a threshold based on the determined diagnosis.
16. The system of claim 11 , further comprising:
detecting whether an image enhancement or an improved slide is desired; and
upon determining the image enhancement or the improved slide and the predicted likelihood that a new stain are desired for the slide, determining to automatically order an additional slide to be prepared.
17. The system of claim 11 , wherein each of the plurality of training images is associated with an indication of whether a pathologist ordered a new stain for that slide.
18. The system of claim 11 , further comprising:
storing, via a data storage device configured to store patient data, one or both of the predicted likelihood that a new stain is desired for the slide or the determination to automatically order an additional slide to be prepared.
19. The system of claim 11 , wherein the training data further comprises additional information about the specimen of the slide.
20. A non-transitory computer-readable medium storing instructions that, when executed by processor, cause the processor to perform operations for processing images, the operations comprising:
receiving a target electronic image of a slide corresponding to a target specimen, the target specimen comprising a tissue sample from a patient;
applying a machine learning system to the target electronic image to predict a likelihood that a new stain is desired for the slide, the machine learning system having been generated by processing a plurality of training images and training data associated with the training images to predict a likelihood that a new stain is desired for the slide, each of the plurality of training images associated with a stain order; and
based on the predicted likelihood that a new stain is desired for the slide, determining to automatically order an additional slide to be prepared.