Object-correspondence identification without full volume registration

• US 20030146913A1
• Filed: 02/07/2002
• Published: 08/07/2003
• Est. Priority Date: 02/07/2002
• Status: Active Grant

• Current Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Original Assignee: Siemens Corporate Research Incorporated (Siemens AG)
• Inventors: Fan, Li, Shen, Hong, Qian, Jianzhong
• Granted Patent: US 6,738,063 B2
• Time in Patent Office: Days
• US Class Current: 345/419
• CPC Class Codes: G06T 2200/04 involving 3D image data
• CPC Class Codes: G06T 2207/30064 Lung nodule
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/32 using correlation-based methods
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06T 7/38 Registration of image sequences

Abstract

Disclosed is a method for object correspondence identification between two image sets, said method steps comprising roughly aligning the two image sets, receiving a selected point in said one image set, locating a rough matching point in said another image, defining a first volume-of-interest around said selected point, defining a search window around said matching point comprising a plurality of neighboring points, for every point in said search window, defining a second volume-of-interest, computing the similarity between each said second volume-of-interest with said first volume-of-interest, and selecting that second volume-of-interest that is most similar to said first volume-of-interest.

Claims

1. A method for object correspondence identification between two image sets, comprising:

receiving a selected point in said one image set;

locating a rough matching point in said another image;

defining a first volume-of-interest around said selected point;

defining a search window around said matching point comprising a plurality of neighboring points;

for every point in said search window, defining a second volume-of-interest;

computing the similarity/dissimilarity between each said second volume-of-interest with said first volume-of-interest; and

selecting that second volume-of-interest that is most similar to said first volume-of-interest.

2. The method of claim 1 wherein said receiving of a selected point is effected through a graphical user interface.

3. The method of claim 1 further comprising the step of roughly aligning the two image sets.

4. The method of claim 3 wherein said rough alignment is effected through area and boundary matching.

5. The method of claim 1 wherein said step of computing the similarity between said first and second volumes of interest comprises a grayscale cross correlation computation according to the equation

6. The method of claim 1 wherein said step of computing the similarity between said first and second volumes of interest comprises computing the sum of absolute differences over all the voxels in said volumes-of-interest in accordance with the equation

S(V_A,V_B)=Σ

|V_A(x,y,z)−

V_B(x,y,z)|

7. The method of claim 1 wherein said step of computing the similarity between said first and second volumes of interest comprises thresholding followed by summation of inclusive OR:

$I<br><br>\left(x,y,z\right)=\{\begin{array}{ccc}1,& V_A<br><br>\left(x,y,z\right)\ge <br><br>T,& V_B<br><br>\left(x,y,z\right)\ge <br><br>T\\ 1,& V_A<br><br>\left(x,y,z\right)<<br><br>T,& V_B<br><br>\left(x,y,z\right)<<br><br>T,\mathrm{and}\\ 0,& \text{\hspace{1em}<br><br>}& \mathrm{else}\end{array}$S(V_A,V_B)=Σ

|I(x,y,z)|

where T is the threshold, and the summation is over all the voxels in both said volumes-of-interest.

8. The method of claim 1 wherein said step of computing the similarity between said first and second volumes of interest comprises surface matching wherein the surface points of all objects within each volume-of-interest are defined as those points inside said volume-of-interest that have at least one immediate neighbor whose intensity is above a given threshold T and at least one immediate neighbor whose intensity is below T, and performing the steps of:

constructing a three-dimensional distance map for a first said volume-of-interest, V_A, D_A(x,y,z) such that its value is the distance of the given point to the closest surface point within V_A; and

calculating the dissimilarity between said volumes-of-interest according to the equation

$\mathrm{ds}=\underset{\left(x,y,z\right)\in <br><br>s_B}{\sum <br><br>}<br><br>D_A<br><br>\left(x,y,z\right).$

 

where s_B represents the complete set of surface points in said second volume-of-interest V_B.

9. The method of claim 8 further comprising the step of normalizing the coordinates of V_A and VB so as to correct any difference in resolution between said image sets.

10. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform the method steps for object correspondence identification between two image sets, said method steps comprising:

receiving a selected point in said one image set;

locating a rough matching point in said another image;

defining a first volume-of-interest around said selected point;

defining a search window around said matching point, comprising a plurality of neighboring points;

for every point in said search window, defining a second volume-of-interest;

computing the similarity/dissimilarity between each said second volume-of-interest with said first volume-of-interest; and

selecting that second volume-of-interest that is most similar to said first volume-of-interest.

11. The invention of claim 10 wherein said receiving of a selected point is effected through a graphical user interface.

12. The invention of claim 10 further comprising the step of roughly aligning the two image sets.

13. The invention of claim 12 wherein said rough alignment is effected through area and boundary matching.

14. The invention of claim 10 wherein said step of computing the similarity between said first and second volumes of interest comprises a grayscale cross correlation computation according to the equation

15. The invention of claim 10 wherein said step of computing the similarity between said first and second volumes of interest comprises computing the sum of absolute differences over all the voxels in said volumes-of-interest in accordance with the equation

S(V_A,V_B)=Σ

|V_A(x,y,z)−

V_B(x,y,z)|

16. The invention of claim 10 wherein said step of computing the similarity between said first and second volumes of interest comprises thresholding followed by summation of inclusive OR:

$I<br><br>\left(x,y,z\right)=\{\begin{array}{ccc}1,& V_A<br><br>\left(x,y,z\right)\ge <br><br>T,& V_B<br><br>\left(x,y,z\right)\ge <br><br>T\\ 1,& V_A<br><br>\left(x,y,z\right)<<br><br>T,& V_B<br><br>\left(x,y,z\right)<<br><br>T,\mathrm{and}\\ 0,& \text{\hspace{1em}<br><br>}& \mathrm{else}\end{array}$S(V_A,V_B)=Σ

|I(x,y,z)|

where T is the threshold, and the summation is over all the voxels in both said volumes-of-interest.

17. The invention of claim 10 wherein said step of computing the similarity between said first and second volumes of interest comprises surface matching wherein the surface points of all objects within each volume-of-interest are defined as those points inside said volume-of-interest that have at least one immediate neighbor whose intensity is above a given threshold T and at least one immediate neighbor whose intensity is below T, and performing the steps of:

constructing a three-dimensional distance map for a first said volume-of-interest, V_A, D_A(x,y,z) such that its value is the distance of the given point to the closest surface point within V_A; and

calculating the dissimilarity between said volumes-of-interest according to the equation

$d<br><br>\text{\hspace{1em}<br><br>}<br><br>s=\underset{\left(x,y,z\right)\in <br><br>\text{\hspace{1em}<br><br>}<br><br>s_B}{\sum <br><br>}<br><br>D_A<br><br>\left(x,y,z\right).$

 

where s_B represents the complete set of surface points in said second volume-of-interest V_B.

18. The method of claim 17 further comprising the step of normalizing the coordinates of V_A and VB so as to correct any difference in resolution between said image sets.