Automatic region-of-interest segmentation and registration of dynamic contrast-enhanced images of colorectal tumors

Patent metadata

Field	Value
Publication number	US-2017243349-A1
Application number	US-201415519145-A
Country	US
Kind code	A1
Filing date	Oct 13, 2014
Priority date	Oct 13, 2014
Publication date	Aug 24, 2017
Grant date	—

Abstract

A method for dynamic contrast enhanced (DCE) image processing and kinetic modeling of an organ's region-of-interest is provided. The method includes deriving at least a contour of an exterior of the organ's region-of-interest from one or more of a plurality of images; generating a spline function in response to the derived contour of the exterior of the organ's region-of-interest from the one or more of the plurality of images; registering the plurality of images wherein the organ's region-of-interest has been segmented; deriving a tracer curve for the organ's region-of-interest in the registered images, the tracer curve indicating a change in concentration of a contrast agent flowing through the organ's region-of-interest over a time period; and kinetic modeling by fitting a kinetic model to the tracer curve to generate one or more maps of tissue physiological parameters associated with the kinetic model.

First claim

1 . A method for dynamic contrast enhanced (DCE) image processing and kinetic modeling of an organ's region-of-interest, the method comprising:
deriving at least a contour of an exterior of the organ's region-of-interest from one or more of a plurality of images; generating a spline function in response to the derived contour of the exterior of the organ's region-of-interest from the one or more of the plurality of images; segmenting the organ's region-of-interest in accordance with the spline function; registering the plurality of images wherein the organ's region-of-interest has been segmented; deriving a tracer curve for the organ's region-of-interest in the registered images, the tracer curve indicating a change in concentration of a contrast agent flowing through the organ's region-of-interest over a time period; and kinetic modeling by fitting a kinetic model to the tracer curve to generate one or more maps of tissue physiological parameters associated with the kinetic model,

2 . The method according to claim 1 , wherein segmenting the organ's region-of-interest comprises generating segments for each of the plurality of images which include the organ's region-of-interest.

3 . The method according to claim 2 , wherein segmenting each of the plurality of images comprises:
identifying a plurality of voxels of the organ's region-of-interest in each of the plurality of images; dividing the organ's region-of-interest in each image into segments in response to the identified plurality of voxels.

4 . The method according to claim 3 , ‘wherein generating the spline function comprises encoding information on the derived contour of the exterior of the organ's region-of-interest for facilitating the segmentation of a successive image.

5 . The method according to claim 1 , wherein the organ's region-of-interest is a tumor.

6 . The method according to claim 5 , wherein the tumor is a colorectal tumor.

7 . The method according to claim 1 , wherein the kinetic model is based on a Tofts model.

8 . The method according to claim 1 , wherein the kinetic model is based on an adiabatic approximation to tissue homogeneity (AATH) model.

9 . The method according to claim 1 , wherein the spline function is a B-spline function.

10 . (canceled)

Assignees

• Agency Science Tech & Res

Inventors

• Hou Zujun
• Wang Yue

Classifications

• G06V10/40 Primary

  Extraction of image or video features · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06T2207/10096

  Dynamic contrast-enhanced magnetic resonance imaging [DCE-MRI] · CPC title

• G06T2207/30096

  Tumor; Lesion · CPC title

• G06T7/12

  Edge-based segmentation · CPC title