System and method for automatic detection and registration of medical images
A system and method for automatic registration of medical images includes accessing image data of a subject and plurality of elongated fiducial markers arranged in an asymmetrical orientation and analyzing the image data to detect the elongated fiducial markers by applying a line filter to treat the elongated fiducial markers as lines within the image data. The system and method also includes matching the elongated fiducial markers within the image data to a model of the elongated fiducial markers, registering the image data with a coordinate system based on the matching, and generating a report indicating at least the registered image data.
1. A system comprising:
a computer system including a non-transitive, computer-readable storage medium having stored thereon a program that causes the computer system to:
access image data illustrating a subject and plurality of elongated fiducial markers arranged in a rotationally asymmetric orientation;
analyze the image data to detect the elongated fiducial markers by applying a line filter to treat the elongated fiducial markers as lines within the image data;
enhance a contrast of the elongated fiducial markers within the image data;
match the enhanced contrast of the elongated fiducial markers within the image data to a model of the elongated fiducial markers;
register the image data with a coordinate system based on the matching of the enhanced contrast of the elongated fiducial markers to the model of the elongated fiducial markers; and
generate a report indicating at least the registered image data.
2. The system of claim 1 wherein the line filter includes a multi-scale line filter.
3. The system of claim 1 wherein the image data includes data from at least three asymmetrically oriented elongated fiducial markers.
4. The system of claim 1 wherein the image data includes three-dimensional (3D) image data.
5. The system of claim 1 wherein the computer system is further caused to iteratively determine a correspondence of the elongated fiducial markers to the model to perform the matching.
6. The system of claim 1 wherein the image data includes at least one of magnetic resonance image data and computed tomography image data.
7. The system of claim 1 wherein the report includes a plan for a therapeutic treatment of the subject.
8. A method for automatically registering medical images with an image coordinate system, the method comprising steps of:
a) positioning a fiducial frame having a plurality of elongated fiducial markers arranged rotationally asymmetric and proximate to a subject;
b) acquiring, with a medical imaging system, image data of the subject and fiducial frame;
c) applying a line filter that treats the elongated fiducial markers as lines within the image data;
d) distinguishing the elongated fiducial markers within the image data;
e) matching the elongated fiducial markers within the image data to a model of the elongated fiducial markers;
f) registering the image data with a coordinate system based on the matching of the elongated fiducial markers to the model of the elongated fiducial markers; and
g) generating a report indicating at least the registered image data.
9. The method of claim 8 further comprising registering the registered image with at least one of a surgical and a therapeutic plan using the report.
10. The method of claim 8 further comprising apply a multi-scale line filter in step c).
11. The method of claim 8 wherein step a) includes arranging at least three asymmetrically oriented elongated fiducial markers proximate to the subject.
12. The method of claim 8 wherein step b) includes acquiring three-dimensional (3D) image data.
13. The method of claim 8 wherein step e) includes iteratively determining a correspondence of the elongated fiducial markers to the model.
14. The method of claim 8 wherein the medical imaging system includes at least one of magnetic resonance system and a computed tomography system.
15. The method of claim 8 wherein steps c) through g) are performed automatically by a computer system that includes a non-transitive, computer-readable storage medium having stored thereon a program that causes the computer system to carry out steps c) through g) automatically.
16. The method of claim 8 wherein the fiducial frame is a free-standing system and the elongated fiducial markers are arranged to form opposing z-shapes connected by an elongated fiducial marker.
17. A system for automatically registering medical images with an image coordinate system, the system comprising:
a fiducial frame having a plurality of elongated fiducial markers arranged rotationally asymmetric within the fiducial frame;
an imaging system configured to acquire image data from the fiducial frame and a subject located proximate to the fiducial frame;
a computer system including a non-transitive, computer-readable storage medium having stored thereon a program that causes the computer system to:
access the image data of the subject and the fiducial frame;
analyze the image data to detect the elongated fiducial markers by applying a line filter to treat the elongated fiducial markers as lines within the image data;
match the elongated fiducial markers detected within the image data to a model of the elongated fiducial markers;
register the image data with a coordinate system based on the matching of the enhanced contrast of the elongated fiducial markers to the model of the elongated fiducial markers; and
generate a report indicating at least the registered image data.
18. The system of claim 17 wherein the line filter includes a multi-scale line filter.
19. The system of claim 17 wherein the medical imaging data includes three-dimensional (3D) image data.
20. The system of claim 17 wherein the computer system is further caused to iteratively determine a correspondence of the elongated fiducial markers to the model to perform the match.