Searching a medical reference image
A method and system are for identification of at least one medical reference image. An embodiment of the method includes providing a medical representation image based on a current examination image depicting a body part of a first patient; defining a region of interest in the medical representation image; generating a feature signature, at least for the region of interest; comparing the medical representation image with a plurality of medical images of at least one second patient stored in a medical image database, based on the feature signature generated; and identifying at least one medical image in the medical image database as the at least one medical reference image, the at least one medical reference image providing a similarity degree to the medical representation image above a threshold. In an embodiment, the generating is performed using a trained machine-learning algorithm.
1. A method for identification of at least one medical reference image, the method comprising:
obtaining a medical representation image based on a current examination image depicting a body part of a first patient, the medical representation image having a lower quality relative to the current examination image;
defining a region of interest in the medical representation image;
generating a feature signature at least for the region of interest defined in the medical representation image;
comparing, based on the feature signature, the medical representation image with a plurality of medical images of at least one second patient, the plurality of medical images stored in a medical image database; and
identifying at least one of the plurality of medical images as the at least one medical reference image, the at least one medical reference image providing a similarity degree to the medical representation image that is above a threshold, wherein
the generating a feature signature is performed using a trained machine-learning algorithm.
2. The method of claim 1 , wherein the obtaining a medical representation image comprises:
acquiring a digital photograph of the current examination image.
3. The method of claim 2 , wherein the defining a region of interest comprises:
defining the region of interest based on an identified anatomical feature in the medical representation image, and wherein
the identified anatomical feature is indicative of a pathological condition of the first patient.
4. The method of claim 2 , further comprising:
correcting at least one artefact in the medical representation image before generating the feature signature.
5. The method of claim 4 , wherein the at least one artefact includes at least one of an image element grid artefact, a dust artefact, a LCD refreshing artefact, an illumination artefact or an artefact due to limited grey scale dynamic range.
6. The method of claim 4 , wherein the correcting at least one artefact in the medical representation image is carried out by a trained machine-learning algorithm.
7. The method of claim 1 , wherein the defining a region of interest comprises:
defining the region of interest based on an identified anatomical feature in the medical representation image, and wherein
the identified anatomical feature is indicative of a pathological condition of the first patient.
8. The method of claim 7 , wherein the defining a region of interest is carried out manually by a user.
9. The method of claim 1 , wherein the defining a region of interest is carried out manually by a user.
10. The method of claim 1 , further comprising:
correcting at least one artefact in the medical representation image before generating the feature signature.
11. The method of claim 10 , wherein the at least one artefact includes at least one of an image element grid artefact, a dust artefact, a LCD refreshing artefact, an illumination artefact or an artefact due to limited grey scale dynamic range.
12. The method of claim 11 , wherein the correcting at least one artefact in the medical representation image is carried out by a trained machine-learning algorithm.
13. The method of claim 10 , wherein the correcting at least one artefact in the medical representation image is carried out by a trained machine-learning algorithm.
14. The method of claim 13 , wherein the comparing and the identifying are performed considering residual artefacts remaining after the correcting at least one artefact in the medical representation image.
15. The method of claim 10 , wherein the comparing and the identifying are performed considering residual artefacts remaining after correcting the at least one artefact in the medical representation image.
16. The method of claim 1 , further comprising
acquiring a first imaging parameter for the current examination image and acquiring a second imaging parameter for each of the plurality of medical images, the first imaging parameter and the second imaging parameter being indicative of an imaging modality used for image acquisition, and wherein
the identifying identifies the at least one medical reference image based on at least one of the first imaging parameter or the second imaging parameter.
17. A non-transitory computer program product storing program elements to configure a processor of a system to identify at least one medical reference image by performing the method of claim 1 , when the program elements are loaded into a memory of the processor and executed by the processor.
18. A non-transitory computer-readable medium storing program elements, readable and executable by a processor of a system for identification of at least one medical reference image, to perform the method of claim 1 when the program elements are executed by the processor.
19. A system for identification of at least one medical reference image, the system comprising:
an interface adapted to obtain a medical representation image based on a current examination image representing a body part of a first patient, the medical representation image having a lower quality relative to the current examination image; and
at least one processor adapted to
define a region of interest in the medical representation image,
generate a feature signature at least for the region of interest in the medical representation image,
compare, based on the feature signature, the medical representation image with a plurality of medical images of at least one second patient, the plurality of medical images stored in a medical image database,
identify at least one of the plurality of medical images as the at least one medical reference image, the at least one medical reference image providing a similarity degree to the medical representation image that is above a threshold,
wherein the at least one processor is adapted to run a trained machine-learning algorithm to generate the feature signature.
20. The system of claim 19 , wherein the at least one processor is adapted to correct at least one artefact in the medical representation image.
21. The system of claim 19 , wherein the medical representation image is a digital photograph of the current examination image.
22. A system for identification of at least one medical reference image, the system comprising:
an interface adapted to obtain a medical representation image based on a current examination image representing a body part of a first patient, the medical representation image having a lower quality relative to the current examination image and
processing circuitry adapted to
define a region of interest in the medical representation image,
generate a feature signature at least for the region of interest in the medical representation image,
compare, based on the feature signature, the medical representation image with a plurality of medical images stored in a medical image database,
identify at least one of the plurality of medical images as the at least one medical reference image, the at least one medical reference image providing a similarity degree to the medical representation image that is above a threshold,
wherein the processing circuitry is adapted to run a trained machine-learning algorithm to generate the feature signature.
23. The system of claim 22 , wherein the processing circuitry includes a field programmable gate array.
24. The system of claim 22 , wherein the processing circuitry is adapted to correct at least one artefact in the medical representation image.
25. The system of claim 22 , wherein the medical representation image is a digital photograph of the current examination image.