System and method for monitoring multiple lesions

Patent metadata

Field	Value
Publication number	US-12150776-B2
Application number	US-202117240222-A
Country	US
Kind code	B2
Filing date	Apr 26, 2021
Priority date	Apr 26, 2021
Publication date	Nov 26, 2024
Grant date	Nov 26, 2024

Abstract

A method and apparatus for tracking disease progression as revealed by multiple lesions perform a global optimization to identify corresponding lesions by overlap, for example, after outlines of the lesions have been morphologically dilated. A clustering algorithm addresses the problem of lesions separating into parts or joining together to provide a clear picture of disease progression.

First claim

What we claim is:

1. An apparatus for assessing treatment of a patient comprising:
an electronic computer executing a stored program to:
(a) receive a first and a subsequent, second scan of tissue of the patient revealing diseased tissue at different times with respect to treatment of the patient, the first and subsequent second scan including at least one lesion that merges or splits between the first and second subsequent scan;
(b) perform a registration of the first and second scans;
(c) identify first lesions in the first scan and second lesions in the second scan;
(d) measure an overlapping of first regions around the first lesions with second regions around the second lesions;
(e) globally assign first lesions to corresponding second lesions based on a global optimization of assignment according to overlap between the first and second regions to identify lesions of the first and second scans that have split or merged; and
(f) compare changes in corresponding first and second lesions as identified to provide a report indicating disease progression.

2. The apparatus of claim 1 wherein the assignment performs a linear optimization.

3. The apparatus of claim 2 wherein the assignment employs a Munkres assignment algorithm.

4. The apparatus of claim 1 wherein the report identifies categories of lesions as appearing or disappearing or corresponding wherein corresponding lesions include a representation of a same lesion in the first and second scans, appearing lesions are lesions in the second scan that have no corresponding lesion in the first scan, and disappearing lesions are lesions in the first scan that have no corresponding lesions in the second scan.

5. The apparatus of claim 1 wherein the report identifies changes in lesion volume and different lesions between the first and second scans.

6. The apparatus of claim 1 wherein the region is larger than the lesion and conformal to the lesion.

7. The apparatus of claim 6 wherein the region is dilated by at least a margin of 15 mm.

8. The apparatus of claim 6 wherein the region is dilated by a margin that is functionally related to a density of lesions in a predetermined area about the region.

9. The apparatus of claim 1 wherein scans are molecular imaging scans.

10. The apparatus of claim 1 wherein registration provides a nonrigid registration three-dimensional registration.

11. An apparatus for assessing treatment of a patient comprising:
an electronic computer executing a stored program to:
(a) receive a first and a subsequent, second scan of tissue of the patient revealing diseased tissue;
(b) perform a registration of the first and second scans;
(c) identify first lesions in the first scan and second lesions in the second scan;
(d) measure an overlapping of first regions around the first lesions with second regions around the second lesions;
(e) globally assign first lesions to corresponding second lesions based on a global optimization of overlap between the first and second regions; and
(f) compare changes in corresponding first and second lesions to provide a report indicating disease progression;
further including the step of clustering lesions after step (c) to combine at least two lesions in one of the first and second scans that overlap with a single lesion in another of the first and second scans into a single lesion in one of the first and second scans.

12. The apparatus of claim 11 wherein the combining evaluates a separation of the at least two lesions compared to a dimension of the single lesion.

13. The apparatus of claim 12 wherein the dimension of the single lesion is measured in relationship to an axis between centers of the at least two lesions.

14. The apparatus of claim 13 wherein the dimension is a longest chord of the single lesion having no more than a predetermined angular separation from the axis.

15. The apparatus of claim 14 wherein the predetermined angular separation is less than 10 degrees.

16. A method for assessing cancer treatment of a patient comprising:
(a) receiving a first and subsequent second scan of tissue of the patient identifying diseased tissue and revealing the diseased tissue at different times with respect to treatment of the patient, the images including lesions that have split or merged;
(b) performing a global registration of the first and second scans
(c) identifying first lesions in the first scan and second lesions in the second scan;
(d) measuring an overlapping of regions around the first lesions with regions around the second lesions;
(e) globally assigning first lesions to corresponding second lesions based on a global optimization of assignment according to overlap between corresponding first and second lesions to identify lesions of the first and second scans that have split or merged; and
(f) comparing the changes in corresponding first and second lesions as identified to provide a report indicating disease progression.

Assignees

• Wisconsin Alumni Res Found
• Aiq Solutions Inc
• Wisconsin Alumni Res Foundation & Aiq Solutions Inc

Inventors

• Jeraj Robert
• Fernandes Victor
• Perk Timothy
• Ferjancic Peter
• Huff Daniel

Classifications

• G06T2207/10104

  Positron emission tomography [PET] · CPC title

• G06T7/0016 Primary

  involving temporal comparison · CPC title

• G06T2207/30096

  Tumor; Lesion · CPC title

• G06T2207/20212

  Image combination · CPC title

• G06T7/38

  Registration of image sequences · CPC title