IP Library Granted Patent US 12,433,688
Granted Patent B2
US 12,433,688 · App. 18/446,516 · Granted Oct 7, 2025

Method and system for vascular catheter tip detection in medical images

Inventors: Rui Liao (Princeton Junction, NJ); Venkatesh Narasimha Murthy (Hillsborough, NJ); Yue Zhang (Jersey City, NJ); Abdoul Aziz Amadou (London, GB)
Assignee: Siemens Healthineers AG
A61B34/20A61B6/12A61B6/481G06T7/248G06T7/277G06T7/73G16H30/40A61B2034/2065A61M2025/0166G06T2207/10016G06T2207/10116G06T2207/20132G06T2207/30021G06T2207/30101
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,433,688
App. No.
18/446,516
Filed
Aug 9, 2023
Granted
Oct 7, 2025
Kind
B2
Art Unit
3798
USPC
600/424
Abstract

A tip of a vascular catheter is detected in a sequence of vessel image frames obtained using x-rays. Within the vessel image frames, a proximal point corresponding to a vessel ostium is determined. The sequence of vessel image frames are cropped to an image area surrounding the proximal point to generate a cropped sequence of cropped vessel image frames. Within cropped vessel image frames not indicative of a contrast medium, the tip of the vascular catheter is detected, and the detected tip of the vascular catheter is tracked.

Claims (48)

1. A computer-implemented method for detecting a tip of a vascular catheter in a sequence of vessel image frames obtained using x-rays, the method comprising:

acquiring the sequence of vessel image frames;

determining, within the vessel image frames, a proximal point, the proximal point corresponding to a vessel ostium;

cropping the sequence of vessel image frames to an image area surrounding the proximal point, resulting in a cropped sequence of cropped vessel image frames;

detecting in real time with the acquisition, within cropped vessel image frames not indicative of a contrast medium, the tip of the vascular catheter;

tracking substantially concurrently with the detecting, within the sequence of vessel image frames, the detected tip of the vascular catheter; and

comparing a detected position of the tip of the vascular catheter, the detected position being output by the detecting of the tip of the vascular catheter with a tracked position of the tip of the vascular catheter, the tracked position being output by the tracking of the detected tip of the vascular catheter;

when the detected position and the tracked position differ by less than a position difference threshold, treating the detected position as a valid position of the tip of the vascular catheter; and

when the detected position and the tracked position differ by more than the position difference threshold, treating the tracked position as the valid position of the tip of the vascular catheter.

2. The method of claim 1 , wherein the determining the proximal point includes detecting the proximal point within vessel image frames indicative of the contrast medium.

3. The method of claim 2 , wherein the detecting the proximal point includes detecting the contrast medium within the vessel image frames and identifying the vessel image frames indicative of the contrast medium based on the detecting.

4. The method of claim 2 , wherein detecting the proximal point includes detecting a pattern of the contrast medium exiting the tip of the vascular catheter.

5. The method of claim 2 , wherein detecting the proximal point is performed using K-means clustering.

6. The method of claim 1 , wherein the determining the proximal point includes receiving information identifying the proximal point.

7. The method of claim 1 , wherein detecting the tip of the vascular catheter within the cropped vessel image frames not indicative of the contrast medium is based on classifying a position within each cropped vessel image frame as the tip.

8. The method of claim 1 , wherein:

detecting the tip of the vascular catheter outputs a detected position of the tip of the vascular catheter per cropped vessel image frame not indicative of a contrast medium; and

detecting the tip of the vascular catheter further includes Kalman filtering the detected positions.

9. The method of claim 1 , wherein tracking the detected tip of the vascular catheter is based on a correlation between temporally adjacent vessel image frames.

10. The method of claim 1 , wherein:

tracking of the detected catheter tip outputs a tracked position of the tip of the vascular catheter per vessel image frame; and

tracking of the detected catheter tip of the vascular catheter further includes Kalman filtering the tracked positions.

11. The method of claim 1 , wherein comparing the detected position of the tip with the tracked position of the tip further comprises:

when the detected position and the tracked position differ by more than the position difference threshold, resetting the detecting of the of the tip of the vascular catheter based on the tracked position.

12. In a non-transitory computer-readable medium comprising instructions configured to be executed by a computer including at least one processor, the instructions causing the processor to:

acquire a sequence of vessel image frames;

determine, within the sequence of vessel image frames, a proximal point, the proximal point corresponding to a vessel ostium;

crop each of the vessel image frames of the sequence of vessel image frames to an image area surrounding the proximal point, resulting in a cropped sequence of cropped vessel image frames;

detect, in real time with the acquisition of the sequence of vessel image frames, within each cropped vessel image frames not indicative of a contrast medium, the tip of the vascular catheter;

track, substantially concurrently with the detecting, within the sequence of vessel image frames, the detected tip of the vascular catheter;

compare a detected position of the tip of the vascular catheter, the detected position being output by the detecting of the tip of the vascular catheter with a tracked position of the tip of the vascular catheter, the tracked position being output by the tracking of the detected tip of the vascular catheter;

when the detected position and the tracked position differ by less than a position difference threshold, treating the detected position as a valid position of the tip of the vascular catheter; and

when the detected position and the tracked position differ by more than the position difference threshold, treating the tracked position as the valid position of the tip of the vascular catheter.

13. The non-transitory computer-readable medium of claim 12 , wherein the instructions cause the processor to determine the proximal point with detection of the proximal point within vessel image frames indicative of the contrast medium.

14. The non-transitory computer-readable medium of claim 12 , wherein the instructions cause the processor to determine the proximal point by reception of information identifying the proximal point.

15. The non-transitory computer-readable medium of claim 12 , wherein the instructions cause the processor to:

output a tracked position of the tip of the vascular catheter per vessel image frame;

and tracking Kalman filter the tracked positions.

16. A medical imaging device comprising:

an x-ray imager configured to record a sequence of vessel image frames; and

at least one processor configured to:

determine, in real time as x-ray imager records the sequence of vessel image frames, within each of vessel image frames of the sequence of the vessel image frames, a proximal point, the proximal point corresponding to a vessel ostium;

crop the sequence of vessel image frames to an image area surrounding the proximal point, resulting in a cropped sequence of cropped vessel image frames;

detect, within cropped vessel image frames not indicative of a contrast medium, the tip of the vascular catheter;

track, within the sequence of vessel image frames, the detected tip of the vascular catheter;

compare a detected position of the tip of the vascular catheter, the detected position being output by the detecting of the tip of the vascular catheter with a tracked position of the tip of the vascular catheter, the tracked position being output by the tracking of the detected tip of the vascular catheter;

when the detected position and the tracked position differ by less than a position difference threshold, treating the detected position as a valid position of the tip of the vascular catheter; and

when the detected position and the tracked position differ by more than the position difference threshold, treating the tracked position as the valid position of the tip of the vascular catheter.

Assignments (5)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 20, 2023
From: SIEMENS HEALTHCARE GMBH
To: SIEMENS HEALTHINEERS AG
Reel/Frame 066267/0346 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 28, 2023
From: SIEMENS MEDICAL SOLUTIONS USA, INC.
To: SIEMENS HEALTHCARE GMBH
Reel/Frame 064716/0106 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 23, 2023
From: AMADOU, ABDOUL AZIZ
To: SIEMENS HEALTHCARE LIMITED
Reel/Frame 064673/0124 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 23, 2023
From: SIEMENS HEALTHCARE LIMITED
To: SIEMENS MEDICAL SOLUTIONS USA, INC.
Reel/Frame 064678/0994 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 22, 2023
From: LIAO, RUI; NARASIMHA MURTHY, VENKATESH; ZHANG, YUE
To: SIEMENS MEDICAL SOLUTIONS USA, INC.
Reel/Frame 064661/0743 →
Priority Claims (1)
EP 22197534 · Sep 23, 2022 · regional
Continuity (1)
Related Publication 20240099784A1 · Mar 28, 2024
References Cited (17)
US 11058385B2 · Kunio · 2021 [cited by applicant]
US 20100177942A1 · Kolatt · 2010 [cited by examiner]
US 20160081760A1 · Verard · 2016 [cited by examiner]
US 20180042566A1 · Roffé · 2018 [cited by examiner]
US 20180353240A1 · Florent · 2018 [cited by examiner]
US 20200222018A1 · van Walsum · 2020 [cited by examiner]
US 20210346100A1 · Auvray et al. · 2021 [cited by applicant]
US 20220378514A1 · Kweon et al. · 2022 [cited by applicant]
US 20230143522A1 · Keast · 2023 [cited by examiner]
US 20240115230A1 · De Bruijn · 2024 [cited by examiner]
KR 102305965B1 · 2021 [cited by applicant]
Ambrosini, Pierre, et al. “Fully automatic and real-time catheter segmentation in X-ray fluoroscopy.” Medical Image Computing and Computer-Assisted Intervention—MICCAI 2017: 20th International Conference, Quebec City, Q… [cited by applicant]
Ma, Hua, et al. “Dynamic coronary roadmapping via catheter tip tracking in X-ray fluoroscopy with deep learning based Bayesian filtering.” Medical image analysis 61 (2020): 101634. [cited by applicant]
Piayda, Kerstin, et al. “Dynamic coronary roadmapping during percutaneous coronary intervention: a feasibility study.” European journal of medical research 23 (2018): 1-7. [cited by applicant]
Ullah, Ihsan, et al. “Synthesize and segment: Towards improved catheter segmentation via adversarial augmentation.” Applied Sciences 11.4 (2021): 1638. [cited by applicant]
Zhang, Liheng, et al. “Cascade attention machine for occluded landmark detection in 2D X-Ray angiography.” 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, 2019. [cited by applicant]
Extended European Search Report (EESR) mailed Feb. 27, 2023 in corresponding European Patent Application No. 22197534.5. [cited by applicant]