Systems and methods for adjusting appearance of objects in medical images

1. A method for adjusting appearance of objects in medical images, the method comprising:

receiving, by a computer, a raw image of a subject, the raw image containing one or more objects of interest;

rectifying and resealing the raw image into a plurality of different image resolutions;

detecting edges in the raw image by generating a strength image and an index image, each pixel of the strength image representing strength of an edge centered at a corresponding pixel in the raw image and each pixel of the index image representing (i) an angle of the edge centered at the corresponding pixel of the raw image; (ii) a length of the edge centered at the corresponding pixel of the raw image, or both (i) and (ii);

aggregating offset in the raw image by calculating a first offset image and a directional correlation image,

wherein each pixel of the first offset image represents an offset at the corresponding pixel in the raw image, the offset determined by one or more parameters associated with a plurality of neighboring pixels to the corresponding pixel in the raw image, wherein the one or more parameters include: (iii) strength of an edge centered at one of the plurality of neighboring pixels, (iv) an angle of the edge centered at one of the plurality of neighboring pixels, (v) length of the edge centered at each of the plurality of neighboring pixels, or a combination of (iii), (iv) and/or (v), and

wherein each pixel of the directional correlation image represents an eccentricity value associated with plurality of edges, wherein each of the plurality of edges is centered at one of the plurality of neighboring pixels;

calculating an additional offset image for the raw image at each of the plurality of different image resolutions and combining the offsets of the first offset image and the offsets of the additional offset images into a weighted sum, wherein the weighted sum is added to the raw image at a selected resolution thereby generating an enhanced image; and

generating a corrected enhanced image from the enhanced image by correcting one or more pixel values of one or more regions of the enhanced image to be within a predetermined intensity range.

2. The method of claim 1 , wherein the one or more objects comprise a radio-dense object.

3. The method of claim 1 , wherein the one or more objects comprise a metal object.

4. The method of claim 1 , wherein the one or more objects comprise a needle-like object.

5. The method of claim 1 , wherein the raw image of the subject is an X-ray image or CT image.

6. A method for adjusting appearance of objects in medical images, the method comprising:

receiving, by a computer, a raw image of a subject, the raw image containing one or more objects of interest;

rectify and rescale the raw image into a plurality of different image resolutions;

detecting edges in the raw image by generating a strength image and an index image, each pixel of the strength image representing strength of an edge centered at a corresponding pixel in the raw image and each pixel of the index image representing: (i) an angle of the edge centered at the corresponding pixel of the raw image; (ii) a length of the edge centered at the corresponding pixel of the raw image, or both (i) and (ii);

adjusting the strength image based on spatial gradient and standard deviation of the raw image;

aggregating offset in the raw image by calculating a first offset image and a directional correlation image,

wherein each pixel of the first offset image represents an offset at the corresponding pixel in the raw image, the offset determined by one or more parameters associated with a plurality of neighboring pixels to the corresponding pixel in the raw image, wherein the one or more parameters include: (iii) strength of an edge centered at one of the plurality of neighboring pixels, (iv) an angle of the edge centered at each of the plurality of neighboring pixels, (v) a length of the edge centered at one of the plurality of neighboring pixels , or a combination of (iii), (iv) and/or (v), and

wherein each pixel of the directional correlation image represents an eccentricity value associated with a plurality of edges;

calculating an additional offset image for the raw image at each of the plurality of different image resolutions and combining the offsets of the first offset image and the offsets of the additional offset images into a weighted sum, wherein the weighted sum is added to the raw image at a selected resolution thereby generating an enhanced image;

applying a local histogram correction to a plurality of regions of the enhanced image;

calculating a weighting image, the weighting image based on difference between the enhanced image and the raw image;

generating a corrected enhanced image by correcting one or more pixel values of one or more regions of the enhanced image to be within a predetermined intensity range; and

merging the enhanced image or the corrected enhanced image with a baseline image or the raw image based on the weighting image thereby generating a merged enhanced image.

7. The method of claim 6 further comprising generating a mask using the enhanced image, the corrected enhanced image, or the weighting image.

8. The method of claim 7 , further comprising superimposing the mask on the raw image or the baseline image thereby generating a masked image.

9. A method for adjusting appearance of objects in medical images, the method comprising:

receiving, by a computer, a raw image of a subject, the raw image containing one or more objects of interest;

detecting edges in the raw image by generating (i) a strength image, (ii) an index image, or (iii) both (i) and (ii), wherein the strength image is a first image output of a long edge detection process performed on the raw image, and the index image is a second image output of the long edge detection process performed on the raw image;

rectifying and resealing the raw image into a plurality of different image resolutions;

aggregating offset in the raw image by calculating a first offset image,

wherein each pixel of the first offset image represents an offset at a corresponding pixel in the raw image, and

wherein each pixel of a directional correlation image represents an eccentricity of each edge of a plurality of edges, wherein each of the plurality of edges is centered at one of a plurality of neighboring pixels to the corresponding pixel in the raw image;

calculating an additional offset image for the raw image at each of the plurality of different image resolutions and combining the offsets of the first offset image and the offsets of the additional offset images into a weighted sum, wherein the weighted sum is added to the raw image at a selected resolution thereby generating an enhanced image; and

applying a histogram correction to the enhanced image to bring the enhanced image within a predetermined intensity range, thereby generating a corrected enhanced image.

10. The method of claim 9 , further comprising rectifying and resealing the raw image.

11. The method of claim 9 , wherein each pixel of the strength image represents strength of an edge centered at the corresponding pixel in the raw image and each pixel of the index image represents (iv) an angle of the edge centered at the corresponding pixel of the raw image, (v) a length of the edge centered at the corresponding pixel of the raw image, or both (iv) and (v).

12. The method of claim 11 , further comprising adjusting the strength image based on a spatial gradient and a standard deviation of the raw image.

13. The method of claim 11 , wherein the offset is determined by one or more parameters associated with the plurality of neighboring pixels to the corresponding pixel in the raw image, the one or more parameters including: (vi) strength of an edge centered at each neighboring pixel, (vii) angle of the edge centered at each neighboring pixel, (viii) length of the edge centered at each neighboring pixel, or a combination of (vi), (vii) and/or (viii).

14. The method of claim 13 further comprising correcting a plurality of local histograms of the enhanced image, each local histogram generated from a portion of the enhanced image.

15. The method of claim 9 further comprising correcting a plurality of local histograms of the enhanced image, each local histogram generated from a portion of the enhanced image.