Artificial intelligence-enabled localization of anatomical landmarks

Patent metadata

Field	Value
Publication number	US-11475559-B2
Application number	US-201816764009-A
Country	US
Kind code	B2
Filing date	Nov 16, 2018
Priority date	Nov 17, 2017
Publication date	Oct 18, 2022
Grant date	Oct 18, 2022

Abstract

The present disclosure relates to a method for medical imaging method for locating anatomical landmarks of a predetermining defined anatomy. The method comprises: a) providing a machine learning model for predicting anatomical landmarks in image data obtained using a set of acquisition parameters and for predicting a subsequent set of acquisition parameters of the set of acquisition parameters for subsequent acquisition of image data; b) determining 5 a current set of acquisition parameters; c) receiving survey image data representing a slice of the anatomy, the survey image data having the current set of current acquisition parameters; d) identifying anatomical landmarks in the received image data using the machine learning model; e) predicting another set of acquisition parameters using the machine learning model and repeating steps c)-e) for a predefined number of repetitions using the predicted set of 10 acquisition parameters as the current set of parameters; and f) providing the identified anatomical landmarks.

First claim

The invention claimed is:

1. A medical imaging method for locating anatomical landmarks of a predefined anatomy, the method comprising:
a) accessing a machine learning model for predicting anatomical landmarks in image data obtained using a set of acquisition parameters and for predicting a subsequent set of acquisition parameters of the set of acquisition parameters for subsequent acquisition of image data;
b) determining a current set of acquisition parameters;
c) receiving survey image data representing a slice of the anatomy, the survey image data having the current set of current acquisition parameters;
d) identifying anatomical landmarks in the received survey image data using the machine learning model;
e1) predicting using the machine learning model additional anatomical landmarks from the already identified anatomical landmarks
e2: predicting a next survey image slice using the machine learning model containing one or more relevant anatomical landmarks and
e3) predicting another set of acquisition parameters for the predicting next survey image slice using the machine learning model and repeating steps c)-e1 to 3) for a predefined number of repetitions using the predicted set of acquisition parameters as the current set of parameters; and
providing the identified anatomical landmarks.

2. The method of claim 1 , step e) further comprising assigning a confidence level to the identified anatomical landmarks using the machine learning model, wherein the number of repetitions is the number of repetitions required for obtaining the confidence level higher than a predefined threshold.

3. The method of claim 1 , further comprising providing a training set of image data with a known set of landmarks and multiple sets of acquisition parameters, and executing learning algorithm on the training set for generating the machine learning model.

4. The method of claim 3 , wherein the training set is indicative of the location of each of the set of landmarks.

5. The method of claim 3 , wherein the training set comprises image data representing a 3D volume of the anatomy.

6. The method of claim 3 , wherein executing of the learning algorithm comprises determining from the training set image data representing a slice corresponding to a given set of parameters, and executing the learning algorithm on the slice.

7. The method of claim 6 , wherein the determining from the training set image data representing a slice corresponding to a given set of parameters is performed using a multi-planar reformatting method.

8. The method of claim 1 , wherein the set of acquisition parameters comprises at least one of the following types:
an indication of a slice of the anatomy;
voxel size of the image data;
number of voxels in the image data;
the center of voxel in the image data; or
the 3D orientation of the slice.

9. The method of claim 1 , wherein the machine learning model is a deep learning model.

10. The method of claim 1 , wherein the predicted set of parameters comprises different values for the set of parameters and/or modified set of parameter, the modified set of parameters may comprise echo time (TE), repetition time (TR), and/or flip angle of the image data.

11. The method of claim 1 , further comprising: performing a scan planning of subsequent medical images using the provided anatomical landmarks.

12. A non-transitory computer readable medium comprising machine executable instructions stored thereon that when executed by a processor, causes the processor to perform the method of claim 1 .

13. A medical analysis system, comprising: a memory containing machine executable instructions; and a processor for controlling the medical analysis system, wherein execution of the machine executable instructions causes the processor to:
a) access a machine learning model for predicting anatomical landmarks in image data obtained using a set of acquisition parameters and for predicting a subsequent set of acquisition parameters of the set of acquisition parameters for subsequent acquiring of image data;
b) determine a current set of acquisition parameters;
c) receive survey image data representing a slice of the anatomy, the survey image data having the current set of current acquisition parameters;
d) identify anatomical landmarks in the acquired survey image data using the machine learning model;
e1) predict using the machine learning model additional anatomical landmarks from the already identified anatomical landmarks
e2) predicting a next survey image slice using the machine learning model containing one or more relevant anatomical landmarks
e3) predict another set of acquisition parameters for the predicted next survey image slice using the machine learning model; and repeating steps c)-e1 to 3) for a predefined number of repetitions using the predicted set of acquisition parameters as the current set of parameters; and
provide the identified anatomical landmarks.

14. A magnetic resonance imaging (MRI) system comprising the medical analysis system of claim 13 , wherein the MRI system is configured to acquire the survey image data.

Assignees

• Koninklijke Philips Nv

Inventors

• Wenzel Fabian
• Brosch Tom

Classifications

• G06T2207/20081

  Training; Learning · CPC title

• G01R33/543 Primary

  Control of the operation of the MR system, e.g. setting of acquisition parameters prior to or during MR data acquisition, dynamic shimming, use of one or more scout images for scan plane prescription (G01R33/546 takes precedence) · CPC title

• G01R33/5608

  Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels (image data processing or generation, in general G06T) · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06N20/00

  Machine learning · CPC title