Segmentating a tubular feature

Patent metadata

Field	Value
Publication number	US-12373953-B2
Application number	US-202017637492-A
Country	US
Kind code	B2
Filing date	Aug 26, 2020
Priority date	Aug 26, 2019
Publication date	Jul 29, 2025
Grant date	Jul 29, 2025

Abstract

In a method of segmenting a tubular feature in an image, a sequence of overlapping portions of the image are segmented using a trained model. The overlapping portions are positioned along the length of the tubular feature and combined to determine a segmentation of the tubular feature.

First claim

The invention claimed is:

1. A method of segmenting a tubular feature in an image, the method comprising:
segmenting a sequence of overlapping portions of the image using a trained model, the overlapping portions being positioned along the length of the tubular feature; and
combining the segmentations of the sequence of overlapping portions of the image to determine the segmentation of the tubular feature, wherein segmenting a sequence of overlapping portions of the image comprises:
segmenting a first portion of the image, the first portion of the image comprising a first portion of the tubular feature;
determining a first point comprised in the tubular feature based on the segmentation of the first portion of the image;
determining a first vector lying parallel to the length of the tubular feature at the first point; and
determining a second portion in the sequence of overlapping portions of the image based on the first point and the first vector, wherein the second portion of the image is determined such that the tubular feature is rotated in the second portion of the image based on the first vector, wherein the tubular feature is rotated such that the first vector lies in a predetermined orientation in the second portion of the image.

2. The method of claim 1 , wherein the center of the second portion of the image is determined according to the equation:
y i+1 =x i +a d i ;
wherein y i+1 comprises a coordinate at the center of the second portion of the image, x i comprises a coordinate of the first point, a represents the magnitude of a shift between the first point and the center of the second portion, and d i comprises the first vector.

3. The method of claim 1 , wherein the trained model has been trained on training data comprising i) example images comprising portions of tubular features wherein each example image is rotated based on the predetermined orientation, and ii) corresponding ground truth segmentations for each example image.

4. The method of claim 1 , further comprising:
determining a second point comprised in the tubular feature based on a segmentation of the second portion of the image;
determining a second vector lying parallel to the length of the tubular feature at the second point; and
determining a third portion in the sequence of overlapping portions of the image based on the second point and the second vector.

5. The method of claim 1 , wherein segmenting the first portion in the sequence of overlapping portions of the image comprises:
determining, for each image element in the first portion of the image, a probability value indicating the probability that the image element is comprised in the tubular feature; and
wherein determining a first point comprised in the tubular feature based on the segmentation of the first portion of the image comprises:
determining the first point based on image elements in the segmentation of the first portion of the image having a probability value above a predetermined threshold.

6. The method of claim 5 , further comprising:
determining a third point in the segmentation of the first portion of the image, the third point having a probability value above the predetermined threshold and lying more than a predetermined distance from the first point; and
determining a bifurcation in the tubular feature, based on the locations of the first point and the third point.

7. The method of claim 5 , further comprising:
ceasing to segment further portions of the image if a segmentation of a portion in the sequence of overlapping portions comprises probability values that are all below the predetermined threshold.

8. The method of claim 1 , wherein combining the segmentations of the sequence of overlapping portions of the image to determine the segmentation of the tubular feature comprises:
averaging image element values in the segmentations of the sequence of overlapping portions of the image in regions of the segmentations that are overlapping.

9. The method of claim 1 , wherein the image comprises a medical image and the tubular feature comprises either a blood vessel or a bronchial structure.

10. The method of claim 1 , wherein the trained model comprises a trained neural network model or a trained random forest model.

11. A system for segmenting a tubular feature in an image, the system comprising:
a memory comprising instruction data representing a set of instructions; and
a processor configured to communicate with the memory and to execute the set of instructions, wherein the set of instructions, when executed by the processor, cause the processor to:
segment a sequence of overlapping portions of the image using a trained model, the overlapping portions being positioned along the length of the tubular feature; and
combine the segmentations of the sequence of overlapping portions of the image to determine the segmentation of the tubular feature, wherein the step of segmenting a sequence of overlapping portions of the image using a trained model comprises:

segmenting a first portion of the image, the first portion of the image comprising a first portion of the tubular feature;
determining a first point comprised in the tubular feature based on the segmentation of the first portion of the image;
determining a first vector lying parallel to the length of the tubular feature at the first point; and
determining a second portion in the sequence of overlapping portions of the image based on the first point and the first vector, wherein the second portion of the image is determined such that the tubular feature is rotated in the second portion of the image based on the first vector, wherein the tubular feature is rotated such that the first vector lies in a predetermined orientation in the second portion of the image.

12. A non-transitory computer readable medium storing instructions that, on execution by a suitable computer or processor, cause the computer or processor to:
segment a sequence of overlapping portions of the image using a trained model, the overlapping portions being positioned along the length of the tubular feature; and
combine the segmentations of the sequence of overlapping portions of the image to determine the segmentation of the tubular feature, wherein segmenting a sequence of overlapping portions of the image comprises:
segmenting a first portion of the image, the first portion of the image comprising a first portion of the tubular feature;
determining a first point comprised in the tubular feature based on the segmentation of the first portion of the image;
determining a first vector lying parallel to the length of the tubular feature at the first point; and
determining a second portion in the sequence of overlapping portions of the image based on the first point and the first vector, wherein the second portion of the image is determined such that the tubular feature is rotated in the second portion of the image based on the first vector, wherein the tubular feature is rotated such that the first vector lies in a predetermined orientation in the second portion of the image.

Assignees

• Koninklijke Philips Nv

Inventors

• Weese Rolf Juergen
• Tio Dominique Siu Li
• Sital Cheryl Kimberley
• Brosch Tom

Classifications

• G06T2207/30172

  Centreline of tubular or elongated structure · CPC title

• G06T2207/30101

  Blood vessel; Artery; Vein; Vascular · CPC title

• G06T2207/20216

  Image averaging · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title