Determining an anatomical atlas

Patent metadata

Field	Value
Publication number	US-9508144-B2
Application number	US-201314437788-A
Country	US
Kind code	B2
Filing date	Oct 22, 2013
Priority date	Oct 26, 2012
Publication date	Nov 29, 2016
Grant date	Nov 29, 2016

Abstract

A data processing method for determining data which are referred to as atlas data and comprise information on a description of an image of a general anatomical structure, wherein this image is referred to as the atlas image, the method comprising the following steps performed by a computer: acquiring patient data which comprise a description of a set of images of an anatomical structure of a set of patients, wherein the images are referred to as patient images and each patient image is associated with a parameter set which comprises one or more parameters which obtain when the patient images are generated, wherein the parameters influence representations of anatomical elements as expressed by image values in the patient images; acquiring model data which comprise information on a description of an image of a model of an anatomical structure of a (single or average or generic) patient which is referred to as the model image and is associated with the parameter set; determining matching transformations which are referred to as PM transformations and which are constituted to respectively match the set of patient images of the set of patients to the model image by matching images associated with the same parameter set; determining an inverse average transformation by applying an inverting and averaging operation to the determined PM transformations; and a) determining the atlas data by applying the determined inverse average transformation to the model data; or b) respectively applying the determined PM transformations to the respective patient images in order to determine matched patient images, averaging the matched patient images in order to determine an average matched patient image, and determining the atlas data by applying the determined inverse average transformation to the average matched patient image.

First claim

The invention claimed is:

1. A medical image processing system, comprising:
analytical devices for generating patient images of a patient; and
a computer for determining data which are referred to as atlas data and comprise information on a description of an image of a general anatomical structure,
wherein this image is referred to as an atlas image,
the computer being constituted to perform following steps:
acquiring patient data which comprise a description of a set of one or more of the patient images of an anatomical structure of a set of one or more patients, wherein the set of one or more of the patient images being referred to as patient image set and each patient image is associated with a parameter set which comprises one or more parameters which are obtained when the patient images are generated, wherein the one or more parameters influence representations of anatomical elements as expressed by image values in the patient images, the patient data comprising the patient image set and the parameter sets associated with the patient image set;
acquiring model data which comprise information on a description of an image of a model of an anatomical structure of a patient which is referred to as the model image and is associated with the parameter set;
wherein the model of an anatomical structure is referred to as the model structure and comprises a model of at least one anatomical element which is referred to as model element;
wherein the model data comprise:
model spatial information on a description of the spatial information on the model structure; and
model element representation information on a description of a plurality of representation data sets which contain information on representations of the at least one model element in the model images to be determined and are referred to as model representation data sets, wherein the model element representation information also describes a determination rule for determining respective model representation data sets for one or more respective model elements in accordance with respective parameter sets;

wherein acquiring the model data involves determining, on the basis of the model data and the patient data, a set of one or more of the model images which respectively represent at least a part of the model structure by using the spatial information on the model structure and particular model representation data sets which are determined by applying the determination rule in accordance with the one or more associated parameter sets and at least one particular model element referred to as corresponding model element, which is to be matched to at least one corresponding anatomical element represented in the patient image and referred to as patient element, the set of one or more of the model images being referred to as model image set;
determining matching transformations which are referred to as PM transformations and which are constituted to respectively match the patient image set to the model image set by matching images associated with the same parameter set;
determining an inverse average transformation by applying an inverting and averaging operation to the determined PM transformations; and
determining the atlas data by applying the determined inverse average transformation to the model data; or
respectively applying the determined PM transformations to the respective patient images in order to determine matched patient images, averaging the matched patient images in order to determine an average matched patient image, and determining the atlas data by applying the determined inverse average transformation to the average matched patient image.

2. A method for determining data which are referred to as atlas data and comprise information on a description of an image of a general anatomical structure, wherein this image is referred to as an atlas image, the method comprising the following steps performed by a computer:
acquiring, at one or more processors of the computer, patient data which comprise a description of a set of one or more images of an anatomical structure of a set of one or more patients, wherein the set of one or more images is referred to as patient image set and the images are referred to as patient images and each patient image is associated with a parameter set which comprises one or more parameters which are obtained when the patient images are generated, wherein the one or more parameters influence representations of anatomical elements as expressed by image values in the patient images, the patient data comprising the patient image set and the parameter sets associated with the patient image set;
acquiring, at one or more of the processors of the computer, model data which comprise information on a description of an image of a model of an anatomical structure of a patient which is referred to as the model image and is associated with the parameter set;
wherein the model of an anatomical structure is referred to as the model structure and comprises a model of at least one anatomical element which is referred to as model element;
wherein the model data comprise:
model spatial information on a description of the spatial information on the model structure; and
model element representation information on a description of a plurality of representation data sets which contain information on representations of the at least one model element in the model images to be determined and are referred to as model representation data sets, wherein the model element representation information also describes a determination rule for determining respective model representation data sets for one or more respective model elements in accordance with respective parameter sets;

wherein acquiring the model data involves determining, on the basis of the model data and the patient data, a set of one or more of the model images which respectively represent at least a part of the model structure by using the spatial information on the model structure and particular model representation data sets which are determined by applying the determination rule in accordance with the one or more associated parameter sets and at least one particular model element referred to as corresponding model element, which is to be matched to at least one corresponding anatomical element represented in the patient image and referred to as patient element, the set of one or more of the model images being referred to as model image set;
determining, by one or more of the processors of the computer, matching transformations which are referred to as PM transformations and which are constituted to respectively match the patient image set to the model image set by matching images associated with the same parameter set;
determining, by one or more of the processors of the computer, an inverse average transformation by applying an inverting and averaging operation to the determined PM transformations; and
determining, by one or more of the processors of the computer, the atlas data by applying the determined inverse average transformation to the model data; or
respectively applying, by one or more of the processors of the computer, the determined PM transformations to the respective patient images in order to determine matched patient images, averaging the matched patient images in order to determine an average matched patient image, and determining the atlas data by applying the determined inverse average transformation to the average matched patient image.

3. The method according to claim 2 , wherein the inverting and averaging operation is applied by:
a) applying an inverting operation to the determined PM transformations in order to determine inverse PM transformations and then applying an averaging operation in order to average the inverse PM transformations and so determine the inverse average transformation; or

Assignees

• Brainlab Ag

Inventors

• Vilsmeier Stefan

Classifications

• G06T7/0024

  Physics · mapped topic

• G06T7/0014 Primary

  using an image reference approach · CPC title

• G06T2207/30004

  Biomedical image processing · CPC title

• G06T7/30 Primary

  Determination of transform parameters for the alignment of images, i.e. image registration · CPC title

• G16H50/50

  for simulation or modelling of medical disorders · CPC title