System and method for synthesizing low-dimensional image data from high-dimensional image data using an object grid enhancement
A method for processing breast tissue image data includes processing image data of a patient's breast tissue to generate a high-dimensional grid depicting one or more high-dimensional objects in the patient's breast tissue; determining a probability or confidence of each of the one or more high-dimensional objects depicted in the high-dimensional grid; and modifying one or more aspects of at least one of the one or more high-dimensional objects based at least in part on its respective determined probability or confidence to thereby generate a lower-dimensional format version of the one or more high-dimensional objects. The method may further include displaying the lower-dimensional format version of the one or more high-dimensional objects in a synthesized image of the patient's breast tissue.
1. A method for processing breast tissue image data, comprising:
obtaining a set of image slices that collectively depict the patient's breast tissue;
identifying an image pattern in two or more slices of the set of image slices;
generating a high-dimensional object grid depicting the image pattern from the two or more slices of the set of image slices;
determining that the image pattern from the two or more slices of the set of image slices comprises one high-dimensional object having a high-dimensional feature; and
generating, based on the high-dimensional object grid and the determining that the image pattern from the two or more slices comprises one high-dimensional object, a lower-dimensional format image of the high-dimensional object depicting the high-dimensional feature.
2. The method of claim 1 , wherein generating the lower-dimensional format image of the high-dimensional object includes modifying one or more aspects of the high-dimensional object in order to depict the high-dimensional feature in the lower-dimensional format image.
3. The method of claim 2 , wherein modifying one or more aspects of the high-dimensional object comprises adjusting at least one of the one or more aspects to be more transparent.
4. The method of claim 2 , wherein modifying one or more aspects of the high-dimensional object comprises adjusting at least one of the one or more aspects to have higher contrast than one or more remaining aspects of the one or more aspects.
5. The method of claim 2 , wherein modifying one or more aspects of the high-dimensional object comprises adjusting at least one of the one or more aspects to be darker than one or more remaining aspects of the one or more aspects.
6. The method of claim 1 , wherein generating the lower-dimensional format image of the high-dimensional object comprises generating a synthesized two-dimensional image of the patient's breast tissue.
7. The method of claim 6 , further comprising displaying the synthesized two-dimensional image.
8. The method of claim 1 , further comprising determining that the image pattern from the two or more slices of the set of image slices comprises two or more objects.
9. The method of claim 8 , further comprising determining an x-coordinate and a y-coordinate for each of the two or more objects.
10. The method of claim 9 , further comprising determining, based on the x-coordinate and they-coordinate for each of the two or more objects, that a first object of the at least two objects is on a first slice of the set of image slices, that a second object of the at least two objects is on a second slice of the set of image slice, and that the first and second objects overlap.
11. The method of claim 10 , further comprising, modifying, based on determining that at least two of the two or more objects overlap, a first object of the at least two overlapping objects in the lower-dimensional format image.
12. The method of claim 11 , wherein the first object is modified such that the first object is more visible than a second object of the at least two overlapping objects in the lower-dimensional format image.
13. The method of claim 11 , wherein the first object is modified such that the first object is less visible than a second object of the at least two overlapping objects in the lower-dimensional format image.
14. The method of claim 13 , wherein the first object is modified such that the first object and a second object of the at least two overlapping objects are both visible in the lower-dimensional format image.
15. The method of claim 13 , wherein the first object and the second object are fused such that one or more aspects of each object is visible.
16. The method of claim 8 , wherein each of the two or more objects is associated with a respective set of aspects, wherein the set of aspects collectively represent one or more of a location, a size, a shape, and a morphology of the patient's breast tissue depicted by the object.
17. The method of claim 1 , wherein the high-dimensional object is at least one of a calcification, a spiculated lesion, a benign tumor, a regular mass, an irregular mass, or a dense object.
18. The method of claim 1 , wherein each of the two or more slices is a two-dimensional image and the image pattern from the two or more slices is a low-dimensional image pattern.
19. The method of claim 18 , wherein the high-dimensional object is an object with greater than two-dimensions and is defined by a combination of the low-dimensional image pattern across the two or more slices.
20. A system comprising:
a computer-readable memory storing executable instructions; and
one or more processors in communication with the computer-readable memory, wherein, when the one or more processors execute the executable instructions, the one or more processors perform:
obtaining a set of image slices that collectively depict the patient's breast tissue;
identifying an image pattern in two or more slices of the set of image slices;
generating a high-dimensional object grid depicting the image pattern from the two or more slices of the set of image slices;
determining that the image pattern from the two or more slices of the set of image slices comprises one high-dimensional object having a high-dimensional feature; and
generating, based on the high-dimensional object grid and the determining that the image pattern from the two or more slices comprises one high-dimensional object, a lower-dimensional format image of the high-dimensional object depicting the high-dimensional feature.
21. A non-transitory computer readable medium having stored theron one or more sequences of instructions for causing one or more processors to perform:
obtaining a set of image slices that collectively depict the patient's breast tissue;
identifying an image pattern in two or more slices of the set of image slices;
generating a high-dimensional object grid depicting the image pattern from the two or more slices of the set of image slices;
determining that the image pattern from the two or more slices of the set of image slices comprises one high-dimensional object having a high-dimensional feature; and generating, based on the high-dimensional object grid and the determining that the image pattern from the two or more slices comprises one high-dimensional object, a lower-dimensional format image of the high-dimensional object depicting the high-dimensional feature.