Method and system for needle tracking in fluoroscopic image sequences
View Patent ↗A method and system for tracking a needle in a fluoroscopic image sequence is disclosed. In order to track a needle in a fluoroscopic image sequence, the needle is initialized in a first frame of the fluoroscopic image sequence. Needle segments are detected in each subsequent frame of the fluoroscopic image sequence, and the needle is detected in each frame of the fluoroscopic image by tracking the needle from a previous frame of the fluoroscopic image sequence based on the detected needle segments in the current frame.
1. A method for tracking a needle in a fluoroscopic image sequence of at least at least a portion of a body of a patient, comprising:
independently detecting needle segments in each of a plurality of frames of the fluoroscopic image sequence; and
detecting the needle in a current frame of the fluoroscopic image sequence by tracking the detected needle from a previous frame of the fluoroscopic image sequence based on a position of the needle in the previous frame and the detected needle segments in the current frame, wherein the detected needle segments are used as primitive features to detect motion between the needle in the previous frame and the needle in the current frame due to breathing motion in the body of the patient.
2. The method of claim 1 , further comprising:
initializing the needle in a first frame of the fluoroscopic image sequence, wherein the plurality of frames are subsequent to the first frame in the fluoroscopic image sequence.
3. The method of claim 2 , wherein said step of initializing a needle in a first frame of the fluoroscopic image sequence comprises:
receiving at least two user inputs corresponding to locations of two end points of the needle in the first frame; and
detecting the needled in the first frame based on the at least two user inputs.
4. The method of claim 1 , wherein said step of independently detecting needle segments in each of a plurality of frames of the fluoroscopic image sequence comprises:
detecting needle segments in each of the plurality of frames using a learning-based needle segment detector.
5. The method of claim 4 , wherein said learning based needle segment detector is trained using a probabilistic boosting tree (PBT) and Haar features.
6. The method of claim 1 , wherein said step of detecting the needle in a current frame of the fluoroscopic image sequence by tracking the detected needle from a previous frame of the fluoroscopic image sequence comprises:
determining motion parameters corresponding to the motion between the needle in the previous frame and the needle in the current frame due to the breathing motion in the body of the patient.
7. The method of claim 6 , wherein said step of determining motion parameters corresponding to the motion between the needle in the previous frame and the needle in the current frame due to the breathing motion in the body of the patient comprises:
calculating the motion parameters using multi-resolution affine tracking of the needle from the previous frame to the current frame.
8. The method of claim 7 , wherein the multi-resolution affine tracking uses kernel-based estimation based on the detected needle segments in the current frame.
9. The method of claim 6 , further comprising:
compensating for the breathing motion in an abdominal intervention based on the determined motion parameters.
10. The method of claim 1 , further comprising:
repeating said step of detecting the needle in a current frame of the fluoroscopic image sequence for each of the plurality of frames of the fluoroscopic image sequence.
11. An apparatus for tracking a needle in a fluoroscopic image sequence of at least at least a portion of a body of a patient, comprising:
means for independently detecting needle segments in each of a plurality of frames of the fluoroscopic image sequence; and
means for detecting the needle in a current frame of the fluoroscopic image sequence by tracking the detected needle from a previous frame of the fluoroscopic image sequence based on a position of the needle in the previous frame and the detected needle segments in the current frame, wherein the detected needle segments are used as primitive features to detect motion between the needle in the previous frame and the needle in the current frame due to breathing motion in the body of the patient.
12. The apparatus of claim 11 , further comprising:
means for initializing the needle in a first frame of the fluoroscopic image sequence, wherein the plurality of frames are subsequent to the first frame in the fluoroscopic image sequence.
13. The apparatus of claim 12 , wherein said means for initializing a needle in a first frame of the fluoroscopic image sequence comprises:
means for receiving at least two user inputs corresponding to locations of two end points of the needle in the first frame; and
means for detecting the needled in the first frame based on the at least two user inputs.
14. The apparatus of claim 11 , wherein said means for independently detecting needle segments in each of a plurality of frames of the fluoroscopic image sequence comprises:
means for detecting needle segments in each of the plurality of frames using a learning-based needle segment detector.
15. The apparatus of claim 11 , wherein said means for detecting the needle in a current frame of the fluoroscopic image sequence by tracking the detected needle from a previous frame of the fluoroscopic image sequence comprises:
means for determining motion parameters corresponding to the motion between the needle in the previous frame and the needle in the current frame due to the breathing motion in the body of the patient.
16. The apparatus of claim 15 , wherein said means for determining motion parameters corresponding to the motion between the needle in the previous frame and the needle in the current frame due to the breathing motion in the body of the patient comprises:
means for calculating the motion parameters using multi-resolution affine tracking of the needle from the previous frame to the current frame.
17. The apparatus of claim 16 , wherein the multi-resolution affine tracking uses kernel-based estimation based on the detected needle segments in the current frame.
18. A non-transitory computer readable medium encoded with computer executable instructions for tracking a needle in a fluoroscopic image sequence of at least at least a portion of a body of a patient, the computer executable instructions defining steps comprising:
independently detecting needle segments in each of a plurality of frames of the fluoroscopic image sequence; and
detecting the needle in a current frame of the fluoroscopic image sequence by tracking the detected needle from a previous frame of the fluoroscopic image sequence based on a position of the needle in the previous frame and the detected needle segments in the current frame, wherein the detected needle segments are used as primitive features to detect motion between the needle in the previous frame and the needle in the current frame due to breathing motion in the body of the patient.
19. The computer readable medium of claim 18 , further comprising computer executable instructions defining the step of:
initializing the needle in a first frame of the fluoroscopic image sequence, wherein the plurality of frames are subsequent to the first frame in the fluoroscopic image sequence.
20. The computer readable medium of claim 19 , wherein the computer executable instructions defining the step of initializing a needle in a first frame of the fluoroscopic image sequence comprise computer executable instructions defining the steps of:
receiving at least two user inputs corresponding to locations of two end points of the needle in the first frame; and
detecting the needled in the first frame based on the at least two user inputs.
21. The computer readable medium of claim 18 , wherein the computer executable instructions defining the step of independently detecting needle segments in each of a plurality of frames of the fluoroscopic image sequence comprise computer executable instructions defining the step of:
detecting needle segments in each of the plurality of frames using a learning-based needle segment detector.
22. The computer readable medium of claim 18 , wherein the computer executable instructions defining the step of detecting the needle in a current frame of the fluoroscopic image sequence by tracking the detected needle from a previous frame of the fluoroscopic image sequence comprise computer executable instructions defining the step of:
determining motion parameters corresponding to the motion between the needle in the previous frame and the needle in the current frame due to the breathing motion in the body of the patient.
23. The computer readable medium of claim 22 , wherein the computer executable instructions defining the step of determining motion parameters corresponding to the motion between the needle in the previous frame and the needle in the current frame due to the breathing motion in the body of the patient comprise computer executable instructions defining the step of:
calculating the motion parameters using multi-resolution affine tracking of the needle from the previous frame to the current frame.
24. The computer readable medium of claim 23 , wherein the multi-resolution affine tracking uses kernel-based estimation based on the detected needle segments in the current frame.
25. The computer readable medium of claim 18 , further comprising computer executable instructions defining the step of:
repeating said step of detecting the needle in a current frame of the fluoroscopic image sequence for each of the plurality of frames of the fluoroscopic image sequence.