Systems and methods for processing images to classify the processed images for digital pathology
Systems and methods are disclosed for receiving a target image corresponding to a target specimen, the target specimen comprising a tissue sample of a patient, applying a machine learning model, which may also be known as a machine learning system, to the target image to determine at least one characteristic of the target specimen and/or at least one characteristic of the target image, the machine learning model having been generated by processing a plurality of training images to predict at least one characteristic, the training images comprising images of human tissue and/or images that are algorithmically generated, and outputting the at least one characteristic of the target specimen and/or the at least one characteristic of the target image.
1. A computer-implemented method for analyzing an image corresponding to a specimen, the method comprising:
receiving a target image corresponding to a target specimen, the target specimen comprising a tissue sample of a patient;
applying a machine learning model to the target image to determine at least one characteristic of the target specimen and/or at least one characteristic of the target image, the machine learning model having been generated by processing a plurality of training images to identify a quality assessment and predict at least one characteristic, the training images comprising images of human tissue and/or images that are algorithmically generated;
predicting a presence of a quality control issue based on the quality assessment;
in response to the quality assessment for the target image indicating the presence of the quality control issue, outputting a recommendation for increasing a quality of the target image based on a type of the quality control issue; and
outputting the at least one characteristic of the target specimen and/or the at least one characteristic of the target image.
2. The computer-implemented method of claim 1 , further comprising:
determining a prediction of a specimen type of the target specimen based on the at least one characteristic of the target specimen; and
outputting the prediction of the specimen type of the target specimen.
3. The computer-implemented method of claim 1 , further comprising:
determining a prediction of a specimen type of the target specimen based on the at least one characteristic of the target specimen;
determining whether a confidence value of the prediction exceeds a predetermined threshold; and
in response to determining that the confidence value of the prediction does not exceed the predetermined threshold, outputting an alert indicating that the specimen type of the target specimen is not identifiable.
4. The computer-implemented method of claim 1 , further comprising:
determining a confidence value of a prediction of a specimen type of the target specimen based on the at least one characteristic of the target specimen; and
outputting the confidence value.
5. The computer-implemented method of claim 4 , further comprising:
identifying a prior treatment associated with the patient; and
determining the confidence value of the prediction of the specimen type based at least in part on the prior treatment associated with the patient.
6. The computer-implemented method of claim 1 , wherein the recommendation comprises any one or any combination of a specimen cut, a scanning parameter, a slide reconstruction, and/or a slide marking.
7. The computer-implemented method of claim 1 , further comprising:
determining, using the target image and the machine learning model, whether the target specimen is post-treatment or pre-treatment.
8. The computer-implemented method of claim 1 , further comprising:
determining, using the target image and the machine learning model, whether the target specimen is post-treatment or pre-treatment;
upon determining that the target specimen is post-treatment, determining a predicted degree to which the target specimen has been treated based on the target image; and
outputting the predicted degree to which the target specimen has been treated.
9. The computer-implemented method of claim 1 , further comprising:
identifying, after predicting the presence of the quality control issue, the type of the quality control issue based on the quality assessment.
10. A system for analyzing an image corresponding to a specimen, the system comprising:
at least one memory storing instructions; and
at least one processor executing the instructions to perform operations comprising a process including:
receiving a target image corresponding to a target specimen, the target specimen comprising a tissue sample of a patient;
applying a machine learning system to the target image to determine at least one characteristic of the target specimen and/or at least one characteristic of the target image, the machine learning system having been generated by processing a plurality of training images to identify a quality assessment and predict at least one characteristic, the training images comprising images of human tissue and/or images that are algorithmically generated;
predicting a presence of a quality control issue based on the quality assessment;
in response to the quality assessment for the target image indicating the presence of the quality control issue, outputting a recommendation for increasing a quality of the target image based on a type of the quality control issue; and
outputting the at least one characteristic of the target specimen and/or the at least one characteristic of the target image.
11. The system of claim 10 , further comprising:
determining a prediction of a specimen type of the target specimen based on the at least one characteristic of the target specimen; and
outputting the prediction of the specimen type of the target specimen.
12. The system of claim 10 , further comprising:
determining a prediction of a specimen type of the target specimen based on the at least one characteristic of the target specimen;
determining whether a confidence value of the prediction exceeds a predetermined threshold; and
in response to determining that the confidence value of the prediction does not exceed the predetermined threshold, outputting an alert indicating that the specimen type of the target specimen is not identifiable.
13. The system of claim 10 , the operations further comprising:
determining a confidence value of a prediction of a specimen type of the target specimen based on the at least one characteristic of the target specimen; and
outputting the confidence value.
14. The system of claim 13 , the operations further comprising:
identifying a prior treatment associated with the patient; and
determining the confidence value of the prediction of the specimen type based at least in part on the prior treatment associated with the patient.
15. The system of claim 10 , wherein the recommendation comprises a specimen cut, a scanning parameter, a slide reconstruction, and/or a slide marking.
16. The system of claim 10 , the operations further comprising:
determining, using the target image and the machine learning system, whether the target specimen is post-treatment or pre-treatment.
17. The system of claim 10 , the operations further comprising:
determining, using the target image and the machine learning system, whether the target specimen is post-treatment or pre-treatment;
upon determining that the target specimen is post-treatment, determining a predicted degree to which the target specimen has been treated based on the target image; and
outputting the predicted degree to which the target specimen has been treated.
18. The system of claim 10 , the operations further comprising:
identifying, after predicting the presence of the quality control issue, the type of the quality control issue based on the quality assessment.
19. A non-transitory computer-readable medium storing instructions that, when executed by processor, cause the processor to perform a method for analyzing an image corresponding to a specimen, the method comprising:
receiving a target image corresponding to a target specimen, the target specimen comprising a tissue sample of a patient;
applying a machine learning model to the target image to determine at least one characteristic of the target specimen and/or at least one characteristic of the target image, the machine learning model having been generated by processing a plurality of training images to identify a quality assessment and predict at least one characteristic, the training images comprising images of human tissue and/or images that are algorithmically generated;
predicting a presence of a quality control issue based on the quality assessment;
in response to the quality assessment for the target image indicating the quality control issue, outputting a recommendation for increasing a quality of the target image based on a type of the quality control issue; and
outputting the at least one characteristic of the target specimen and/or the at least one characteristic of the target image.
20. The non-transitory computer-readable medium of claim 19 , further comprising:
determining a prediction of a specimen type of the target specimen based on the at least one characteristic of the target specimen; and
outputting the prediction of the specimen type of the target specimen.