Method and system for dose-optimized computed tomography scanning of a target organ

Patent metadata

Field	Value
Publication number	US-10182771-B2
Application number	US-201715429459-A
Country	US
Kind code	B2
Filing date	Feb 10, 2017
Priority date	Feb 10, 2017
Publication date	Jan 22, 2019
Grant date	Jan 22, 2019

Abstract

A method and system for dose-optimized acquisition of a computed tomography (CT) scan of a target organ is disclosed. A localizer spiral CT scan is started at a beginning of a confidence range before a target organ. Real-time localizer scan images are automatically analyzed to predict a beginning location of the target organ based on the real-time localizer scan images. A diagnostic spiral CT scan is automatically started at the predicted beginning location of the target organ. Real-time diagnostic scan images are automatically analyzed to predict an end location of the target organ where full coverage of the target organ will be reached. The diagnostic spiral CT scan is automatically stopped in response to reaching the predicted end location of the target organ. A 3D profile can be acquired using a 3D camera and used to determine the confidence range before the target organ.

First claim

The invention claimed is:

1. A method for dose-optimized acquisition of a computed tomography (CT) scan of a target organ, comprising:
starting a localizer spiral CT scan at a beginning of a confidence range before a target organ of a patient;
receiving real-time localizer scan images from the localizer spiral CT scan as a patient is moved relative to a gantry of a CT scanning device;
automatically analyzing the real-time localizer scan images to predict a beginning location of the target organ based on the real-time localizer scan images;
automatically starting a diagnostic spiral CT scan at the predicted beginning location of the target organ;
receiving real-time diagnostic scan images from the diagnostic spiral CT scan as the patient is moved relative to the gantry of the CT scanning device;
automatically analyzing the real-time diagnostic scan images to predict an end location of the target organ where full coverage of the target organ will be reached based on the real-time diagnostic scan images; and
automatically stopping the diagnostic spiral CT scan in response to reaching the predicted end location of the target organ.

2. The method of claim 1 , wherein automatically analyzing the real-time localizer scan images to predict a beginning location of the target organ based on the real-time localizer scan images comprises:
detecting one or more anatomical landmarks in the confidence range before the target organ in the real-time localizer scan images using one or more trained landmark detectors;
automatically estimating the beginning location of the target organ based on the one or more landmarks in the confidence range before the target organ detected in the in the real-time localizer scan images.

3. The method of claim 1 , wherein automatically analyzing the real-time diagnostic scan images to predict an end location of the target organ where full coverage of the target organ will be reached based on the real-time diagnostic scan images comprises:
automatically estimating an organ model of the target organ in the real-time diagnostic scan images; and
automatically estimating the end location of the target organ from the estimated organ model of the target organ.

4. The method of claim 3 , wherein estimating an organ model of the target organ in the real-time diagnostic scan images comprises:
detecting one or more anatomical landmarks in the real-time diagnostic scan images using one or more trained landmark detectors; and
fitting the organ model of the target organ to the real-time diagnostic scan images based on the one or more anatomical landmarks detected in the real-time diagnostic scan images.

5. The method of claim 1 , further comprising:
acquiring a 3D profile of the patient on a table of the CT scanning device using a 3D camera;
fitting a patient model to the 3D profile of the patient; and
automatically determining the beginning of the confidence range before the target organ of the patient based on the patient model.

6. The method of claim 5 , wherein acquiring a 3D profile of the patient on a table of the CT scanning device using a 3D camera comprises:
receiving an RGBD image of the patient on the table of the CT scanning device from the 3D camera; and
converting the RGBD image into a 3D point cloud in a coordinate system of the table of the CT scanning device.

7. The method of claim 6 , wherein fitting a patient model to the 3D profile of the patient comprises:
registering a statistical shape model of a patient body including an anatomical location of the target organ to the 3D point cloud in the coordinate system of the table of the CT scanning device.

8. The method of claim 1 , wherein the real-time localizer scan images are one of 2D projection images, reconstructed cross-sectional CT image slices, or reconstructed 3D images.

9. The method of claim 1 , wherein the real-time diagnostic scan images are one of 2D projection images, reconstructed cross-sectional CT image slices, or reconstructed 3D images.

10. The method of claim 1 , wherein the localizer spiral CT scan uses an x-ray intensity and the diagnostic spiral CT scan uses an x-ray intensity that is greater than the first x-ray intensity.

11. The method of claim 1 , further comprising:
reconstructing a 3D CT volume including the target organ from the diagnostic spiral CT scan.

12. The method of claim 1 , further comprising:
detecting an anatomical pose of the target organ in a 3D CT volume resulting from the diagnostic spiral CT scan;
automatically aligning reconstruction boxes to target organ based on the detected anatomical pose of the target organ; and
generating a reconstructed 3D CT volume with axes aligned to the anatomical pose of the target organ using the aligned reconstruction boxes.

13. The method of claim 1 , wherein the target organ is the lungs.

14. The method of claim 13 , wherein automatically analyzing the real-time localizer scan images to predict a beginning location of the target organ based on the real-time localizer scan images comprises:
automatically predicting a lung apex location based on the real-time localizer scan images prior to the lung apex location appearing in the real-time localizer scan images.

15. The method of claim 11 , wherein automatically analyzing the real-time diagnostic scan images to predict an end location of the target organ where full coverage of the target organ will be reached based on the real-time diagnostic scan images comprises:
automatically predicting a lung lobe tip location based on the real-time diagnostic scan images prior to the lung lobe tip location appearing in the real-time localizer scan images.

16. The method of claim 1 , further comprising:
acquiring a 2D image of the patient on a table of the CT scanning device using a 2D camera;
registering a patient model to the 2D image of the patient; and
automatically determining the beginning of the confidence range before the target organ of the patient based on the patient model.

17. An apparatus for dose-optimized acquisition of a computed tomography (CT) scan of a target organ, comprising:
means for starting a localizer spiral CT scan at a beginning of a confidence range before a target organ of a patient;
means for receiving real-time localizer scan images from the localizer spiral CT scan as a patient is moved relative to a gantry of a CT scanning device;
means for automatically analyzing the real-time localizer scan images to predict a beginning location of the target organ based on the real-time localizer scan images;
means for automatically starting a diagnostic spiral CT scan at the predicted beginning location of the target organ;
means for receiving real-time diagnostic scan images from the diagnostic spiral CT scan as the patient is moved relative to the gantry of the CT scanning device;
means for automatically analyzing the real-time diagnostic scan images to predict an end location of the target organ where full coverage of the target organ will be reached based on the real-time diagnostic scan images; and
means for automatically stopping the diagnostic spiral CT scan in response to reaching the predicted end location of the target organ.

18. The apparatus of claim 17 , wherein the means for automatically analyzing the real-time localizer scan images to predict a beginning location of the target organ based on the real-time localizer scan images comprises:
means for detecting one or more anatomical landmarks in the confidence range before the target organ in the real-time localizer scan images using one or

Assignees

• Siemens Healthcare Gmbh

Inventors

• Vega Fernando
• Sauer Frank

Classifications

• A61B6/542

  involving control of exposure · CPC title

• A61B6/50

  specially adapted for specific body parts; specially adapted for specific clinical applications · CPC title

• A61B6/032 Primary

  Transmission computed tomography [CT] · CPC title

• A61B6/5217

  extracting a diagnostic or physiological parameter from medical diagnostic data · CPC title

• G16H50/30

  for calculating health indices; for individual health risk assessment · CPC title