Computer-implemented method for providing a de-identified medical image
A computer-implemented method, comprising: receiving input data including a medical image and an in-image annotation; applying a first function to the input data to determine a relevance value of pixels in the image and a relevance map; applying a second function to the medical image to generate a de-identified medical image; applying a trained function to the medical image and the de-identified medical image to determine a first property in the medical image and a second property in the de-identified medical image; applying a comparison function to the first property and the second property to determine a similarity value, wherein in response to the similarity value being below a similarity threshold, the relevance map is adjusted and the applying of the second function, the applying of the trained function and the applying of the comparison function are repeated; and providing the de-identified medical image and the in-image annotation.
1 . A computer-implemented method for providing a de-identified medical image, the computer-implemented method comprising:
receiving input data, wherein the input data includes a medical image and an in-image annotation based on the medical image;
applying a first function to the input data, wherein a relevance value of pixels in the medical image is determined based on the in-image annotation, and a relevance map is generated;
applying a second function to the medical image to generate a de-identified medical image based on the relevance map;
applying a trained function to the medical image and the de-identified medical image to determine a first property in the medical image and to determine a second property in the de-identified medical image;
applying a comparison function to the first property and the second property, wherein the first property and the second property are compared to each other and a similarity value is determined, wherein
in response to the similarity value being below a similarity threshold, the relevance map is adjusted and the applying of the second function, the applying of the trained function and the applying of the comparison function are repeated; and
providing the de-identified medical image and the in-image annotation.
2 . The computer-implemented method according to claim 1 , wherein the applying of the second function comprises:
modifying, blurring, adding noise or adding geometrical distortions in regions with pixels of lower relevance.
3 . The computer-implemented method according to claim 2 , wherein a strength of the modifying, blurring, adding noise or adding geometrical distortions depends on relevance values of the pixels.
4 . The computer-implemented method according to claim 3 , wherein the relevance map comprises relevance values ranging from 0 to 1.
5 . The computer-implemented method according to claim 3 , wherein the relevance value is determined based on a distance map, the distance map being based on the in-image annotation and pixels inside the in-image annotation.
6 . The computer-implemented method according to claim 5 , wherein another trained function is applied to the medical image, wherein additional non-relevant pixels are determined based on information in the medical image.
7 . The computer-implemented method according to claim 3 , wherein at least one of the first property or the second property is determined by an object segmentation task, an object detection task, an image classification task, or a regression task.
8 . The computer-implemented method according to claim 1 , wherein the relevance map comprises relevance values ranging from 0 to 1.
9 . The computer-implemented method according to claim 1 , wherein the relevance value is determined based on a distance map, the distance map being based on the in-image annotation and pixels inside the in-image annotation.
10 . The computer-implemented method according to claim 1 , wherein another trained function is applied to the medical image, wherein additional non-relevant pixels are determined based on information in the medical image.
11 . The computer-implemented method according to claim 1 , wherein at least one of the first property or the second property is determined by an object segmentation task, an object detection task, an image classification task, or a regression task.
12 . The computer-implemented method according to claim 1 , wherein the similarity value is a Hausdorff distance, a difference of normalized probabilities or a difference of prediction results.
13 . The computer-implemented method according to claim 1 , wherein the medical image is an X-ray image.
14 . A non-transitory computer program product comprising instructions which, when executed by a providing system, cause the providing system to perform the method of claim 1 .
15 . A non-transitory computer-readable medium comprising instructions which, when executed by a providing system, cause the providing system to perform the method of claim 1 .
16 . A providing system comprising:
a memory storing computer-executable instructions; and
at least one processor configured to execute the computer-executable instructions to cause the providing system to perform the method of claim 1 .
17 . A providing system comprising:
a first interface configured to receive input data, wherein the input data includes a medical image and an in-image annotation based on the medical image;
a first computation unit configured to apply a first function to the input data, wherein a relevance value of pixels in the medical image is determined based on the in-image annotation, and a relevance map is generated;
a second computation unit configured to apply a second function to the medical image to generate a de-identified medical image based on the relevance map;
a third computation unit configured to apply a trained function to the medical image and the de-identified medical image to determine a first property in the medical image and a second property in the de-identified medical image;
a fourth computation unit configured to apply a comparison function to the first property and the second property, wherein the first property and the second property are compared to each other and a similarity value is determined, wherein
in response to the similarity value being below a similarity threshold, the relevance map is adjusted, and the second function, the trained function and the comparison function are reapplied; and
a second interface configured to provide the de-identified medical image and the in-image annotation.
18 . A medical imaging system comprising the providing system according to claim 17 .