PROVIDING REAL-TIME MARKER DETECTION FOR A STENT IN MEDICAL IMAGING

• US 20140241599A1
• Filed: 02/27/2013
• Published: 08/28/2014
• Est. Priority Date: 02/27/2013
• Status: Active Grant

• Current Assignee: Siemens Healthineers AG (Siemens AG)
• Original Assignee: Siemens AG, Siemens Corp. (Siemens AG)
• Inventors: Chen, Terrence, Durlak, Peter, Comaniciu, Dorin, Wang, Yu
• Granted Patent: US 9,084,531 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: A61B 2576/02 specially adapted for a particular organ or body part
• CPC Class Codes: A61B 5/0036 including treatment, e.g., using an implantable medical device, ablating, ventilating
• CPC Class Codes: A61B 6/12 Arrangements for detecting or locating foreign bodies
• CPC Class Codes: A61B 6/487 involving fluoroscopy
• CPC Class Codes: A61B 6/5217 extracting a diagnostic or physiological parameter from medical diagnostic data
• CPC Class Codes: G06F 18/24155 Bayesian classification
• CPC Class Codes: G06F 18/29 Graphical models, e.g. Bayesian networks
• CPC Class Codes: G06T 2207/30052 Implant; Prosthesis
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/84 using probabilistic graphical models from image or video features, e.g. Markov models or Bayesian networks
• CPC Class Codes: G06V 2201/034 of medical instruments
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing

Abstract

Real-time marker detection in medical imaging of a stent may be provided. A plurality of frames of image data may be obtained. A plurality of candidate markers for the stent may be determined in the plurality of frames of image data. One or more markers from the plurality of candidate markers may be detected. The detecting may be based on automatic initialization using a subset of frames of image data from the plurality of frames of image data. The detecting may be performed in real-time with the obtaining.

Claims

1. A method of providing real-time marker detection in medical imaging of a stent, the method comprising:

obtaining a plurality of frames of image data;

determining a plurality of candidate markers for the stent in the plurality of frames of image data; and

detecting, by a processor, one or more first markers for the stent from the plurality of candidate markers, the detecting being based on automatic initialization using a subset of frames of image data from the plurality of frames of image data, the detecting performed in real-time with the obtaining.

2. The method of claim 1, wherein obtaining the plurality of frames of image data comprises obtaining a plurality of frames of fluoroscopic image data.

3. The method of claim 1, wherein detecting the plurality of candidate markers for the stent comprises detecting a plurality of candidate marker pairs for the stent.

4. The method of claim 1, wherein the automatic initialization comprises applying an algorithm to the subset of frames of image data and finding one or more first markers from the plurality of candidate markers based on the applying.

5. The method of claim 1, wherein detecting comprises detecting the one or more first markers for the stent based, at least in part, on one or more models generated during the automatic initialization to model one or more of the plurality of candidate markers.

6. The method of claim 5, wherein the detecting comprises updating the one or more models generated during the automatic initialization, and detecting the one or more first markers based, at least in part, on the updating.

7. The method of claim 1, wherein determining the plurality of candidate markers comprises applying a machine learning-based detector to the plurality of frames of image data.

8. The method of claim 1, further comprising:

determining whether the detected one or more first markers are valid markers; and

selecting a final tracking marker based on the determining.

9. The method of claim 8, wherein the determining comprises determining that the detected one or more first markers are not valid for a frame of image data of the plurality of frames of image data, the method further comprising removing the respective frame of image data.

10. In a non-transitory computer-readable storage medium having stored therein data representing instructions executable by a programmed processor for providing real-time marker detection in medical imaging for a stent, the storage medium comprising instructions for:

obtaining a plurality of frames of image data;

determining a plurality of candidate marker pairs for the stent in the plurality of frames of image data; and

tracking one or more marker pairs from the plurality of candidate marker pairs for the stent, the tracking being automatically initialized using a subset of frames of image data from the plurality of frames of image data, and the tracking performed in real-time with the obtaining.

11. The computer-readable storage medium of claim 10, wherein obtaining the plurality of frames of image data comprises obtaining a plurality of frames of fluoroscopic image data.

12. The computer-readable storage medium of claim 10, wherein the automatic initializing comprises generating a plurality of Gaussian models to model one or more of the plurality of candidate marker pairs, and wherein the tracking of the one or more marker pairs is based, at least in part, on the plurality of Gaussian models.

13. The computer-readable storage medium of claim 10, wherein the automatic initializing comprises generating a joint template for each of the plurality of candidate marker pairs, and wherein the tracking of the one or more marker pairs is based, at least in part, on the joint templates.

14. The computer-readable storage medium of claim 10, further comprising validating the tracked marker pairs.

15. The computer-readable storage medium of claim 10, wherein the automatic initializing comprises applying a Viterbi algorithm to the subset of frames of image data.

16. A system for providing real-time marker detection in medical imaging, the system comprising:

a memory configured to store fluoroscopic image data;

a processor configured to determine a plurality of candidate marker pairs and to automatically initialize a detector for tracking one or more candidate marker pairs of the plurality of candidate marker pairs, the detector automatically initialized using a subset of the fluoroscopic image data, the processor configured to track, in real-time, the one or more candidate marker pairs for a stent in the fluoroscopic image data using the automatically initialized detector, and the processor configured to generate an image of the stent based on the tracking; and

a display configured to display the image of the stent.

17. The system of claim 16, wherein the processor is configured to generate a plurality of Gaussian models associated with the plurality of candidate marker pairs and a joint template for each of the plurality of candidate marker pairs, and wherein the processor is configured to track the one or more candidate marker pairs for the stent based, at least in part, on the plurality of Gaussian models and the joint templates.

18. The system of claim 16, wherein the processor is configured to determine whether one or more of the detected candidate marker pairs are valid.

19. The system of claim 18, wherein the processor is configured to determine that one or more of the detected candidate marker pairs is not valid when a length of the respective candidate marker pair is abnormal or a motion of the candidate marker pair is too large.

20. The system of claim 18, wherein, when the respective candidate marker pair is determined to be a valid marker pair, the processor is configured to select the respective candidate marker pair as a final tracking marker pair.