Ultrasound system and method of vessel identification

Patent metadata

Field	Value
Publication number	US-10722209-B2
Application number	US-201615316535-A
Country	US
Kind code	B2
Filing date	Mar 31, 2016
Priority date	Apr 3, 2015
Publication date	Jul 28, 2020
Grant date	Jul 28, 2020

Abstract

An ultrasound system for identifying a vessel of a subject comprises: an ultrasound probe configured to simultaneously acquire a sequence of ultrasound blood flow data frames (such as a sequence of ultrasound Doppler data frames) and a sequence of ultrasound B-mode data frames of a region of interest including the vessel over a predetermined time period; a blood flow region selecting unit configured to select a blood flow region in the sequence of blood flow data frames; and a vessel segmenting unit configured to segment the vessel in at least one frame of the sequence of ultrasound B-mode data frames based on the selected blood flow region. Since there is no need to manually place any seed point for vessel segmentation any more, the user dependency is reduced and a fast measurement is made possible.

First claim

The invention claimed is:

1. An ultrasound system for identifying a vessel of a subject, comprising:
an ultrasound probe; and
a processor communicatively coupled to and configured to control the ultrasound probe to simultaneously acquire a sequence of ultrasound blood flow data frames and a sequence of ultrasound B-mode data frames of a region of interest including the vessel over a predetermined time period, wherein the region of interest comprises a longitudinal cross section of a length of the vessel and a landmark that is different than the vessel, and wherein the processor comprises:
a blood flow region selecting unit configured to detect a blood flow region indicating a blood flow along the length of the vessel in each frame of multiple frames in the sequence of ultrasound blood flow data frames, and to select a blood flow region among the detected blood flow regions based on a frame of the multiple frames in which the blood flow region is larger than a threshold;
a vessel segmenting unit configured to segment the vessel in at least one frame of the sequence of ultrasound B-mode data frames based on the selected blood flow region, the at least one frame comprising the ultrasound B-mode data frame temporally corresponding to the ultrasound blood flow data frame in which the selected blood flow region is detected, wherein the vessel segmenting unit is configured to identify an upper wall and a lower wall along the length of the vessel, and wherein the segmenting is based on seed points automatically derived from the selected blood flow region;
a landmark identifying unit configured to automatically identify the landmark in the at least one frame; and
a vessel feature deriving unit configured to derive, based on the identified landmark, a feature indicating a transverse size of the segmented vessel corresponding to a distance between the upper wall and the lower wall in each of the at least one frame,
wherein the landmark identifying unit is configured to identify a longitudinal portion along the length of the vessel at which the feature is derived, and
wherein the vessel feature deriving unit is configured to detect a collapse of the vessel at a location of the vessel based on at least one of:
the distance between the upper wall and lower wall falling below a predetermined threshold at that location; or
a change in the distance between the upper wall and lower wall exceeding a predetermined threshold at that location.

2. The ultrasound system of claim 1 , wherein the blood flow region selecting unit is further configured to determine a size for each of the detected blood flow regions, and to select the blood flow region based on the determined sizes.

3. The ultrasound system of claim 2 , wherein the size of the selected blood flow region is the largest size among the detected blood flow regions.

4. The ultrasound system of claim 1 , wherein the vessel segmenting unit is further configured to segment the vessel in at least one other frame of the sequence of B-mode data frames by means of tracking the vessel based on the segmented vessel in the at least one frame.

5. The ultrasound system of claim 1 , wherein the processor further comprises a respiration identifying unit, wherein
the respiration identifying unit is configured to identify a respiration cycle of the subject; and
the vessel feature deriving unit is configured to derive the feature based on the identified respiration cycle.

6. The ultrasound system of claim 5 , wherein
the vessel segmenting unit is configured to segment the vessel in each of a plurality of data frames of the sequence of ultrasound B-mode data frames; and
the respiration identifying unit is configured to identify the respiration cycle of the subject based on the segmented vessels in the plurality of data frames.

7. The ultrasound system of claim 1 , the ultrasound blood flow data frame is an ultrasound Doppler data frame.

8. The ultrasound system of claim 1 , wherein the vessel is an inferior vena cava.

9. The ultrasound system of claim 1 , wherein the region of interest is two-dimensional.

10. The system of claim 1 , wherein the vessel feature deriving unit is configured to derive the feature at a first location in the vessel based on a second location of the identified landmark.

11. The system of claim 10 , wherein the identified landmark is a hepatic vein.

12. The system of claim 1 , wherein the at least one frame comprising the ultrasound B-mode data frame is acquired at a same time as the ultrasound blood flow data frame in which the selected blood flow region is detected.

13. A method of identifying a vessel of a subject, comprising steps of:
controlling, by a processor, an ultrasound probe to simultaneously acquire a sequence of ultrasound blood flow data frames and a sequence of ultrasound B-mode data frames of a region of interest including the vessel over a predetermined time period, wherein the region of interest comprises a longitudinal cross section of a length of the vessel and a landmark that is different than the vessel;
detecting, by the processor, a blood flow region indicating a blood flow along the length of the vessel in each frame of multiple frames in the sequence of ultrasound blood flow data frames and selecting a blood flow region among the detected blood flow regions based on a frame of the multiple frames in which the blood flow region is larger than a threshold;
segmenting, by the processor, the vessel in at least one frame of the sequence of ultrasound B-mode data frames based on the selected blood flow region, the at least one frame comprising the ultrasound B-mode data frame temporally corresponding to the ultrasound blood flow data frame in which the selected blood flow region is detected, wherein the segmenting comprises identifying an upper wall and a lower wall along the length of the vessel, and wherein the segmenting is based on seed points automatically derived from the selected blood flow region;
identifying, by the processor, the landmark in the at least one frame;
identifying, by the processor and based on the identified landmark, a longitudinal portion along the length of the vessel for deriving a feature;
deriving, by the processor at the identified longitudinal portion, a feature indicating a transverse size of the segmented vessel corresponding to a distance between the upper wall and the lower wall in each of the at least one frame; and
detecting a collapse of the vessel at a location of the vessel based on at least one of:
the distance between the upper wall and lower wall falling below a predetermined threshold at that location; or
a change in the distance between the upper wall and lower wall exceeding a predetermined threshold at that location.

14. The method of claim 13 , wherein deriving the feature comprises deriving the feature at a first location in the vessel based on a second location of the identified landmark.

15. The method of claim 14 , wherein the landmark comprises a hepatic vein, and identifying the landmark includes identifying the hepatic vein.

16. The method of claim 13 , wherein controlling the ultrasound probe to simultaneously acquire the sequence of ultrasound blood flow frames and the sequence of ultrasound B-mode data frames comprises acquiring the at least one frame comprising the ultrasound B-mode data frame at a same time as the ultrasound blood flow data frame in which the selected blood flow region is detected.

17. A non-transitory computer-readable medium comprising computer program instructions which, when being executed, performs the method of

Assignees

• Koninklijke Philips Nv

Inventors

• Chen Jiangang
• Raju Balasundar Iyyavu
• Leyvi Evgeniy

Classifications

• A61B8/5284

  involving retrospective matching to a physiological signal · CPC title

• A61B8/469

  for selection of a region of interest · CPC title

• A61B8/481

  involving the use of contrast agents, e.g. microbubbles introduced into the bloodstream · CPC title

• A61B8/14

  Echo-tomography · CPC title

• A61B8/5223

  for extracting a diagnostic or physiological parameter from medical diagnostic data (for algorithms to analyse biomedical images G06T7/0012) · CPC title