Reducing structural redundancy in automatic image segmentation
View Patent ↗A method for automatically training and applying automatic segmentation in digital image processing is provided. The method may include, in response to receiving a plurality of digital images wherein each digital image associated with the plurality of digital images comprises only one annotated structure out of a plurality of structures included in each digital image, applying a predictive algorithm to each digital image that determines a predicted probability of each annotation in each digital image, determines a predicted background for each digital image, and merges the predicted probability of each annotation with the predicted background in each digital image. The method may further include, in response to applying the predictive algorithm, using the received plurality of digital images to train and apply an application for automatically segmenting unlabeled digital images.
1. A method for automatically training and applying automatic segmentation in digital image processing, the method comprising:
in response to receiving a plurality of digital images wherein each digital image associated with the plurality of digital images comprises only one annotated structure out of a plurality of different structures included in each digital image, applying a predictive algorithm to each digital image that determines a predicted probability of annotations for each structure other than the one annotated structure in each digital image based on a spatial and structural correlation of the one annotated structure relative to the plurality of different structures, determines a predicted background for each digital image, and merges the predicted probability of the annotations with the predicted background in each digital image; and
in response to applying the predictive algorithm, using the received plurality of digital images to train and apply an application for automatically segmenting unlabeled digital images.
2. The method of claim 1 , further comprising:
presenting a user interface and prompting a user to annotate a digital image associated with the plurality of digital images using the user interface.
3. The method of claim 2 , wherein presenting the user interface and prompting the user further comprises:
for a digital image with a number of structures of interest for annotating, presenting the same number of different digital images to the user on the user interface and prompting the user to annotate one different structure in each of the different digital images.
4. The method of claim 1 , wherein applying the application for automatically segmenting the unlabeled digital images further comprises:
applying a machine learning computer vision algorithm and the received plurality of digital images to the unlabeled digital images to segment the unlabeled digital images.
5. The method of claim 1 , wherein the plurality of digital images comprises digital X-ray images.
6. The method of claim 1 , wherein automatically segmenting the unlabeled digital images further comprises:
automatically identifying anatomical structures within an unlabeled digital X-ray image.
7. The method of claim 1 , wherein the application for automatically segmenting unlabeled digital images includes one or more image segmentation techniques selected from a group comprising at least one of atlas-based segmentation, shape-based segmentation, image-based segmentation, interactive segmentation, and subjective surface segmentation.
8. A computer system for automatically training and applying automatic segmentation in digital image processing, comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:
in response to receiving a plurality of digital images wherein each digital image associated with the plurality of digital images comprises only one annotated structure out of a plurality of different structures included in each digital image, applying a predictive algorithm to each digital image that determines a predicted probability of annotations for each structure other than the one annotated structure in each digital image based on a spatial and structural correlation of the one annotated structure relative to the plurality of different structures, determines a predicted background for each digital image, and merges the predicted probability of the annotations with the predicted background in each digital image; and
in response to applying the predictive algorithm, using the received plurality of digital images to train and apply an application for automatically segmenting unlabeled digital images.
9. The computer system of claim 8 , further comprising:
presenting a user interface and prompting a user to annotate a digital image associated with the plurality of digital images using the user interface.
10. The computer system of claim 9 , wherein presenting the user interface and prompting the user further comprises:
for a digital image with a number of structures of interest for annotating, presenting the same number of different digital images to the user on the user interface and prompting the user to annotate one different structure in each of the different digital images.
11. The computer system of claim 8 , wherein applying the application for automatically segmenting the unlabeled digital images further comprises:
applying a machine learning computer vision algorithm and the received plurality of digital images to the unlabeled digital images to segment the unlabeled digital images.
12. The computer system of claim 8 , wherein the plurality of digital images comprises digital X-ray images.
13. The computer system of claim 8 , wherein automatically segmenting the unlabeled digital images further comprises:
automatically identifying anatomical structures within an unlabeled digital X-ray image.
14. The computer system of claim 8 , wherein the application for automatically segmenting unlabeled digital images includes one or more image segmentation techniques selected from a group comprising at least one of atlas-based segmentation, shape-based segmentation, image-based segmentation, interactive segmentation, and subjective surface segmentation.
15. A computer program product for automatically training and applying automatic segmentation in digital image processing, comprising:
one or more tangible computer-readable storage devices and program instructions stored on at least one of the one or more tangible computer-readable storage devices, the program instructions executable by a processor, the program instructions comprising:
in response to receiving a plurality of digital images wherein each digital image associated with the plurality of digital images comprises only one annotated structure out of a plurality of different structures included in each digital image, program instructions to apply a predictive algorithm to each digital image that determines a predicted probability of annotations for each structure other than the one annotated structure in each digital image based on a spatial and structural correlation of the one annotated structure relative to the plurality of different structures, determines a predicted background for each digital image, and merges the predicted probability of the annotations with the predicted background in each digital image; and
in response to applying the predictive algorithm, program instructions to use the received plurality of digital images to train and apply an application for automatically segmenting unlabeled digital images.
16. The computer program product of claim 15 , further comprising:
program instructions to present a user interface and prompt a user to annotate a digital image associated with the plurality of digital images using the user interface.
17. The computer program product of claim 16 , wherein the program instructions to present the user interface and prompt the user further comprises:
program instructions to, for a digital image with a number of structures of interest for annotating, presenting the same number of different digital images to the user on the user interface and prompting the user to annotate one different structure in each of the different digital images.
18. The computer program product of claim 15 , wherein the program instructions to apply the application for automatically segmenting the unlabeled digital images further comprises:
program instructions to apply a machine learning computer vision algorithm and the received plurality of digital images to the unlabeled digital images to segment the unlabeled digital images.
19. The computer program product of claim 15 , wherein the program instructions to automatically segment the unlabeled digital images further comprises:
automatically identifying anatomical structures within an unlabeled digital X-ray image.
20. The computer program product of claim 15 , wherein the application for automatically segmenting unlabeled digital images includes one or more image segmentation techniques selected from a group comprising at least one of atlas-based segmentation, shape-based segmentation, image-based segmentation, interactive segmentation, and subjective surface segmentation.