Localization and classification of abnormalities in medical images
Systems and methods are provided for classifying an abnormality in a medical image. An input medical image depicting a lesion is received. The lesion is localized in the input medical image using a trained localization network to generate a localization map. The lesion is classified based on the input medical image and the localization map using a trained classification network. The classification of the lesion is output. The trained localization network and the trained classification network are jointly trained.
1. A method for detecting an abnormality in a medical image, comprising:
receiving an input medical image depicting an abnormality;
deleting different portions of the input medical image to generate a plurality of incomplete images, each of the plurality of incomplete images comprising a deleted portion of the input medical image and a remaining portion of the input medical image;
generating a plurality of synthesized images using a trained generative adversarial network, each of the plurality of synthesized images generated from a respective one of the plurality of incomplete images to comprise the remaining portion of the respective incomplete image and a synthesized portion replacing the deleted portion of the respective incomplete image;
determining a normal image from the plurality of synthesized images; and
detecting the abnormality in the input medical image based on the input medical image and the normal image.
2. The method of claim 1 , wherein deleting different portions of the input medical image to generate a plurality of incomplete images comprises:
randomly deleting the different portions of the input medical image to generate the plurality of incomplete images.
3. The method of claim 1 , wherein deleting different portions of the input medical image to generate a plurality of incomplete images comprises:
deleting the different portions of the input medical image based on a predetermined pattern to generate the plurality of incomplete images.
4. The method of claim 1 , wherein deleting different portions of the input medical image to generate a plurality of incomplete images comprises:
deleting a portion of the input medical image comprising a suspected abnormality.
5. The method of claim 1 , wherein deleting different portions of the input medical image to generate a plurality of incomplete images comprises:
applying stencils of different sizes or shapes to the input medical image.
6. The method of claim 1 , wherein determining a normal image from the plurality of synthesized images comprises:
determining the normal image as a particular synthesized image, of the plurality of synthesized images, that depicts a healthiest tissue.
7. The method of claim 6 , wherein determining the normal image as a particular synthesized image, of the plurality of synthesized images, that depicts a healthiest tissue comprises:
determining the particular synthesized image as one of the plurality of synthesized images that maximizes a distance metric between the plurality of synthesized images and the input medical image.
8. The method of claim 1 , further comprising training the trained generative adversarial network by:
receiving a multi-site dataset associated with different clinical sites and a deployment dataset associated with a deployment clinical site;
training a deep convolutional generative adversarial network based on the multi-site dataset; and
optimizing the trained deep convolutional generative adversarial network based on the deployment dataset to provide the trained generative adversarial network.
9. The method of claim 8 , wherein the multi-site dataset comprises a first dataset and a second dataset, and training a deep convolutional generative adversarial network based on the multi-site dataset comprises:
reordering the second dataset based on a similarity of the first dataset and the second dataset; and
determining the trained deep convolutional generative adversarial network based on a pretrained deep learning model and the reordered second dataset.
10. The method of claim 8 , wherein optimizing the trained deep convolutional generative adversarial network based on the deployment dataset to provide the trained generative adversarial network comprises:
reordering an annotated deployment dataset of the deployment dataset based on an uncertainty; and
determining the optimized deep convolutional generative adversarial network based on the trained deep convolutional generative adversarial network and the reordered annotated deployment dataset.
11. An apparatus for detecting an abnormality in a medical image, comprising:
means for receiving an input medical image depicting an abnormality;
means for deleting different portions of the input medical image to generate a plurality of incomplete images, each of the plurality of incomplete images comprising a deleted portion of the input medical image and a remaining portion of the input medical image;
means for generating a plurality of synthesized images using a trained generative adversarial network, each of the plurality of synthesized images generated from a respective one of the plurality of incomplete images to comprise the remaining portion of the respective incomplete image and a synthesized portion replacing the deleted portion of the respective incomplete image;
means for determining a normal image from the plurality of synthesized images; and
means for detecting the abnormality in the input medical image based on the input medical image and the normal image.
12. The apparatus of claim 11 , wherein the means for deleting different portions of the input medical image to generate a plurality of incomplete images comprises:
means for randomly deleting the different portions of the input medical image to generate the plurality of incomplete images.
13. The apparatus of claim 11 , wherein the means for deleting different portions of the input medical image to generate a plurality of incomplete images comprises:
means for deleting the different portions of the input medical image based on a predetermined pattern to generate the plurality of incomplete images.
14. The apparatus of claim 11 , wherein the means for deleting different portions of the input medical image to generate a plurality of incomplete images comprises:
means for deleting a portion of the input medical image comprising a suspected abnormality.
15. The apparatus of claim 11 , wherein the means for deleting different portions of the input medical image to generate a plurality of incomplete images comprises:
means for applying stencils of different sizes or shapes to the input medical image.
16. A non-transitory computer readable medium storing computer program instructions for detecting an abnormality in a medical image, the computer program instructions when executed by a processor cause the processor to perform operations comprising:
receiving an input medical image depicting an abnormality;
deleting different portions of the input medical image to generate a plurality of incomplete images, each of the plurality of incomplete images comprising a deleted portion of the input medical image and a remaining portion of the input medical image;
generating a plurality of synthesized images using a trained generative adversarial network, each of the plurality of synthesized images generated from a respective one of the plurality of incomplete images to comprise the remaining portion of the respective incomplete image and a synthesized portion replacing the deleted portion of the respective incomplete image;
determining a normal image from the plurality of synthesized images; and
detecting the abnormality in the input medical image based on the input medical image and the normal image.
17. The non-transitory computer readable medium of claim 16 , wherein determining a normal image from the plurality of synthesized images comprises:
determining the normal image as a particular synthesized image, of the plurality of synthesized images, that depicts a healthiest tissue.
18. The non-transitory computer readable medium of claim 17 , wherein determining the normal image as a particular synthesized image, of the plurality of synthesized images, that depicts a healthiest tissue comprises:
determining the particular synthesized image as one of the plurality of synthesized images that maximizes a distance metric between the plurality of synthesized images and the input medical image.
19. The non-transitory computer readable medium of claim 16 , the operations further comprising training the trained generative adversarial network by:
receiving a multi-site dataset associated with different clinical sites and a deployment dataset associated with a deployment clinical site;
training a deep convolutional generative adversarial network based on the multi-site dataset; and
optimizing the trained deep convolutional generative adversarial network based on the deployment dataset to provide the trained generative adversarial network.
20. The non-transitory computer readable medium of claim 19 , wherein the multi-site dataset comprises a first dataset and a second dataset, and training a deep convolutional generative adversarial network based on the multi-site dataset comprises:
reordering the second dataset based on a similarity of the first dataset and the second dataset; and
determining the trained deep convolutional generative adversarial network based on a pretrained deep learning model and the reordered second dataset.