Systems and methods for processing electronic images for computational detection methods
Systems and methods are disclosed for receiving one or more electronic slide images associated with a tissue specimen, the tissue specimen being associated with a patient and/or medical case, partitioning a first slide image of the one or more electronic slide images into a plurality of tiles, detecting a plurality of tissue regions of the first slide image and/or plurality of tiles to generate a tissue mask, determining whether any of the plurality of tiles corresponds to non-tissue, removing any of the plurality of tiles that are determined to be non-tissue, determining a prediction, using a machine learning prediction model, for at least one label for the one or more electronic slide images, the machine learning prediction model having been generated by processing a plurality of training images, and outputting the prediction of the trained machine learning prediction model.
1. A computer-implemented method for processing electronic slide images, the method comprising:
receiving one or more electronic slide images associated with a tissue specimen, the tissue specimen being associated with a patient and/or medical case;
determining a prediction, using a machine learning prediction model, for at least one label for the one or more electronic slide images, the machine learning prediction model having been generated by
partitioning one of a plurality of training images into a plurality of training tiles for the plurality of training images;
creating a training tissue mask by detecting at least one tissue region from a background of the one or more electronic slide images;
removing at least one of the plurality of tiles detected to be non-tissue; and
using the machine learning prediction model under weak supervision to infer at least one tile-level prediction using at least one label of a plurality of synoptic annotations of the plurality of training images.
2. The computer-implemented method of claim 1 , wherein the plurality of tiles that are determined to be non-tissue are further determined to be a background of the tissue specimen.
3. The computer-implemented method of claim 1 , further comprising: detecting a plurality of tissue regions of the one or more electronic slide images and/or plurality of tiles by segmenting the tissue regions from the background.
4. The computer-implemented method of claim 3 , wherein the segmenting comprises using thresholding based on color, color intensity, and/or texture features.
5. The computer-implemented method of claim 1 , wherein the plurality of training images comprise a plurality of electronic slide images and a plurality of target labels.
6. The computer-implemented method of claim 1 , wherein using the machine learning prediction model under weak supervision comprises using multiple-instance learning (MIL), Multiple Instance Multiple Label Learning (MIMLL), self-supervised learning, and unsupervised clustering.
7. The computer-implemented method of claim 1 , wherein using the machine learning prediction model under weak supervision comprises using at least one of Multiple Instance Multiple Label Learning (MIMLL), self-supervised learning, and unsupervised clustering.
8. The computer-implemented method of claim 1 , further comprising:
receiving a plurality of predictions of at least one feature from a weakly-supervised tile-level learning module for the plurality of training tiles;
applying the machine learning model to take, as an input, the plurality of predictions of the at least one feature from the weakly-supervised tile-level learning module for the plurality of training tiles; and
predicting a plurality of labels for a slide or a patient specimen, using the plurality of training tiles.
9. The computer-implemented method of claim 8 , wherein at least one of the plurality of labels is binary, categorical, ordinal or real-valued.
10. The computer-implemented method of claim 8 , wherein applying the machine learning model to take, as the input, the plurality of predictions of the at least one feature from the weakly-supervised tile-level learning module for the plurality of training tiles comprises a plurality of image features.
11. The computer-implemented method of claim 1 , wherein the machine learning prediction model predicts at least one label using at least one unseen slide.
12. A system for processing electronic slide images corresponding to a tissue specimen, the system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform operations comprising:
receiving one or more electronic slide images associated with the tissue specimen;
determining a prediction, using a machine learning prediction model, for at least one label for the one or more electronic slide images, the machine learning prediction model having been generated by
partitioning one of a plurality of training images into a plurality of training tiles for the plurality of training images;
creating a training tissue mask by detecting at least one tissue region from a background of the one or more electronic slide images;
removing at least one of the plurality of tiles detected to be non-tissue; and
using the machine learning prediction model under weak supervision to infer at least one tile-level prediction using at least one label of a plurality of synoptic annotations of the plurality of training images.
13. The system of claim 12 , wherein the plurality of training tiles that are determined to be non-tissue are further determined to be a background of the tissue specimen.
14. The system of claim 12 , further comprising: detecting a plurality of tissue regions of the one or more electronic slide images and/or plurality of tiles by segmenting the tissue regions from the background.
15. The system of claim 14 , wherein the segmenting comprises using thresholding based on color, color intensity, and/or texture features.
16. The system of claim 12 , wherein the plurality of training electronic slide images comprise a plurality of electronic slide images and a plurality of target labels.
17. The system of claim 12 , wherein using the machine learning prediction model under weak supervision comprises using multiple-instance learning (MIL), Multiple Instance Multiple Label Learning (MIMLL), self-supervised learning, and unsupervised clustering.
18. The system of claim 12 , further comprising:
receiving a plurality of predictions of at least one feature from a weakly-supervised tile-level learning module for the plurality of training tiles;
applying the machine learning model to take, as an input, the plurality of predictions of the at least one feature from the weakly-supervised tile-level learning module for the plurality of training tiles; and
predicting a plurality of labels for a slide or a patient specimen, using the plurality of training tiles.
19. The system of claim 18 , wherein at least one of the plurality of labels is binary, categorical, ordinal or real-valued.
20. A non-transitory computer readable medium storing instructions that, when executed by a processor, cause the processor to perform a method for processing electronic slide images corresponding to a tissue specimen, the method comprising:
receiving one or more electronic slide images associated with a tissue specimen, the tissue specimen being associated with a patient and/or medical case;
determining a prediction, using a machine learning prediction model, for at least one label for the one or more electronic slide images, the machine learning prediction model having been generated by
partitioning one of a plurality of training images into a plurality of training tiles for the plurality of training images;
creating a training tissue mask by detecting at least one tissue region from a background of the one or more electronic slide images;
removing at least one of the plurality of tiles detected to be non-tissue; and
using the machine learning prediction model under weak supervision to infer at least one tile-level prediction using at least one label of a plurality of synoptic annotations of the plurality of training images.