SYSTEMS AND METHODS FOR CORRELATING OBJECTS OF INTEREST
A method of correlating regions in an image pair including a cranial-caudal image and a medial-lateral-oblique image. Data from a similarity matching model is received by an ensemble model, the data including at least a matched pair of regions and a first confidence level indicator associated with the matched pair of regions. Data from a geo-matching model is received by the ensemble model, the data from the geo-matching model including at least the matched pair of regions and a second confidence level indicator. A joint probability of correlation is determined by the ensemble model based on evaluation of each of the first and second confidence level by the ensemble matching model, wherein the joint probability of correlation provides a probability that the region in each image correlates to the corresponding region in the other image. The joint probability of correlation is provided to an output device.
1 . (canceled)
2 . A method of correlating regions of interest (ROIs) in an image pair including a cranial-caudal (CC) image and a medial-lateral-oblique (MLO) image, the method comprising:
performing a similarity matching process comprising:
receiving, by a similarity matching model, the image pair;
locating a CC similarity ROI in the CC image of the image pair;
locating an MLO similarity ROI in the MLO image of the image pair;
matching the CC similarity ROI and the MLO similarity ROI using similarity characteristics to yield similarity output data;
performing a geo-matching process comprising:
receiving, by a geo-matching model, the image pair;
locating a CC geo-matching ROI in the CC image of the image pair;
locating an MLO geo-matching ROI in the MLO image of the image pair;
matching the CC geo-matching ROI and the MLO geo-matching ROI using location characteristics to yield geo-matching output data;
performing an ensemble matching process comprising:
receiving, by an ensemble matching model, the similarity output data and the geo-matching output data;
matching the CC similarity ROI and the MLO similarity ROI with each of the CC geo-matching ROI and the MLO geo-matching ROI to yield a joint probability of correlation; and
providing the joint probability of correlation to an output device.
3 . The method of claim 2 , further comprising receiving, by the ensemble matching model, the image pair.
4 . The method of claim 3 , wherein the joint probability of correlation is further based on the image pair.
5 . The method of claim 2 , wherein the similarity output data comprises a first confidence level and the geo-matching output data comprises a second confidence level.
6 . The method of claim 5 , wherein the first confidence level indicates a reliability of the match of the CC similarity ROI and the MLO similarity ROI and the second confidence level indicates a reliability of the match of the CC geo-matching ROI and the MLO geo-matching ROI.
7 . The method of claim 5 , further comprising determining, by the ensemble matching ML model, a third confidence level based on evaluation of each of the first and second confidence level and the joint probability of correlation, wherein the third confidence level indicates a reliability of the joint probability of correlation.
8 . The method of claim 2 , wherein the joint probability of correlation comprises a reliability of the CC similarity ROI and the CC geo-matching ROI relating to a common CC ROI and the MLO similarity ROI and the MLO geo-matching ROI relating to a common MLO ROI.
9 . The method of claim 8 , wherein the joint probability of correlation further comprises a reliability of a match between the common CC ROI and the common MLO ROI.
10 . The method of claim 8 , wherein providing the joint probability of correlation to the output device comprises displaying the image pair with a pair of symbols, wherein each of the pair of symbols marks one of the common CC ROI and the common MLO ROI.
11 . The method of claim 2 , wherein providing the joint probability of correlation to the output device comprises a numerical value associated with the joint probability of correlation.
12 . The method of claim 2 , wherein providing the joint probability of correlation to an output device comprises:
receiving a selection of one of the common CC ROI and the common MLO ROI; and
presenting, in response to receiving the selection, the other of the common CC ROI and the common MLO ROI.
13 . The method of claim 2 , wherein each image of the image pair is a whole breast image.
14 . The method of claim 2 , wherein each image of the image pair is acquired using a plurality of projection images.
15 . The method of claim 14 , wherein each image of the image pair comprises a reconstructed image based on the plurality of projection images.
16 . The method of claim 14 , further comprising synthesizing a synthesized image using the joint probability of correlation and displaying the synthesized image on the output device.
17 . The method of claim 16 , wherein each of the pixels in the synthesized image is mapped to a projection image of the plurality of projection images.
18 . A system for correlating regions of interest (ROIs) in an image pair including a cranial-caudal (CC) image and a medial-lateral-oblique (MLO) image, the system comprising:
at least one processor in communication with at least one memory;
a similarity matching module that executes on the at least one processor and during operation is configured to perform a similarity matching process comprising:
receiving, by a similarity matching model, the image pair;
locating a CC similarity ROI in the CC image of the image pair;
locating an MLO similarity ROI in the MLO image of the image pair;
matching the CC similarity ROI and the MLO similarity ROI using similarity characteristics to yield similarity output data;
a geo-matching matching module that executes on the at least one processor and during operation is configured to perform a geo-matching process comprising:
receiving, by a geo-matching model, the image pair;
locating a CC geo-matching ROI in the CC image of the image pair;
locating an MLO geo-matching ROI in the MLO image of the image pair;
matching the CC geo-matching ROI and the MLO geo-matching ROI using location characteristics to yield geo-matching output data;
an ensemble matching module that executes on the at least one processor and during operation is configured to perform an ensemble matching process comprising:
receiving, by an ensemble matching model, the similarity output data and the geo-matching output data;
matching the CC similarity ROI and the MLO similarity ROI with each of the CC geo-matching ROI and the MLO geo-matching ROI to yield a joint probability of correlation; and
an output device which receives the joint probability of correlation from the ensemble matching module.
19 . The system of claim 18 , wherein the similarity output data includes one or more of margin data and shape data.
20 . The system of claim 18 , wherein the geo-matching output data includes location data.
21 . The system of claim 18 , further comprising an input device configured to receive user input, wherein the ensemble matching model further receives user input via the input device.