iRecon: intelligent image reconstruction system with anticipatory execution

Patent metadata

Field	Value
Publication number	US-10275906-B2
Application number	US-201515326159-A
Country	US
Kind code	B2
Filing date	Jul 9, 2015
Priority date	Jul 16, 2014
Publication date	Apr 30, 2019
Grant date	Apr 30, 2019

Abstract

A diagnostic imaging system retrieves data ( 206 ) from a plurality of accessible data sources, the accessible data sources storing data including physiological data describing a subject to be imaged, a nature of a requested diagnostic image, image preferences of a clinician who requested the diagnostic image, and previously reconstructed images of the requested nature of the subject and/or other subjects, reconstruction parameters and/or sub-routines used to reconstruct the previously reconstructed images. The system analyzes ( 6, 12 ) the retrieved data to automatically generate reconstruction parameters and/or sub-steps specific to the nature of the requested diagnostic image, the subject, and the clinician image preferences. The system controls a display device ( 10, 216 ) to display the generated reconstruction parameters and/or sub-routines to the user for a user selection. The system sets a reconstruction processor system to reconstruct scan data using the selected reconstruction parameters and/or sub-routines.

First claim

The invention claimed is:

1. A diagnostic image generating system, comprising one or more processors configured to:
retrieve data from a plurality of accessible data sources, the accessible data sources storing data including physiological data describing a subject to be imaged, a nature of a requested diagnostic image, image preferences of a clinician who requested the diagnostic image, and previously reconstructed images of the requested nature of the subject and/or other subjects, reconstruction parameters and/or sub-routines used to reconstruct the previously reconstructed images;
analyze the retrieved data to automatically select reconstruction parameters and/or sub-steps specific to the nature of the requested diagnostic image, the subject and the clinician image preferences to reach one or more reconstruction goals, including selecting one of: a reconstruction algorithm, a number of repetitions of an iterative reconstruction algorithm, a single scatter correction algorithm, a single correction algorithm, a post processing filter, and/or a kernel size for a post processing filter; and
at least one of: control a display device to display the selected reconstruction parameters and/or sub-routines and/or set a reconstruction processor system to reconstruct scan data using the selected reconstruction parameters and/or sub-routines.

2. The system according to claim 1 , wherein the one or more processors are further configured to:
generate preview images from scan data from one of the other subjects using the selected reconstruction parameters and/or sub-routines; and
control the display to display the preview image.

3. The system according to claim 1 , wherein the one or more processors are further configured to:
select a plurality of candidate reconstruction parameters and/or sub-routines; and
generate a plurality of preview images for at least some of the candidate reconstruction parameters.

4. The system according to claim 1 , wherein the one or more processors are further configured to:
receive a selection from a user interface by which the clinician selects one of the preview images.

5. The system according to claim 4 , wherein the one or more processors are further configured to:
for the selected preview image, select variations on the selected reconstruction parameters and sub-routines; and
generate sub-images using the selected variations.

6. The system according to claim 5 , wherein the one or more processors are further configured to:
control the display to display the variations of the selected reconstruction parameters;
receive a user selection of one of the displayed preview images or sub-images; and
configure a reconstruction processor to reconstruct the scanned imaging data with the reconstruction parameters and/or sub-routines used to generate the selected preview image or sub-image.

7. The system according to claim 1 , wherein the one or more processors are further configured to:
generate additional preview images and sub-images in the background when the reconstruction processor is idle.

8. The system according to claim 1 , wherein the one or more processors are further configured to:
select a plurality of candidate scan protocols;
generate a plurality of preview images for at least some of the candidate scan protocols;
receive a selection from a user interface by which the clinician selects one of the preview images;
for the selected preview image, select variations on the selected scan protocols; and
generate sub-images using the selected variations
control the display to display the variations of the selected scan protocols;
receive a user selection of one of the displayed preview images; and
configure a reconstruction processor to reconstruct the scanned imaging data with the scan protocol used to generate the selected preview image.

9. The system according to claim 3 , wherein the one or more processors are further configured to:
analyze the selections with an artificial intelligence engine to the clinician preferences.

10. The system according to claim 1 , wherein the one or more processors are further configured to:
when no existing data is available, analyze expert opinions; and
when little data is available, analyze the available data of more similar other subjects using a similarity metric.

11. The system according to claim 1 , wherein selecting the reconstruction parameters and/or sub-routines includes:
selecting one of: reconstruction algorithms, repetitions of iterative reconstruction algorithms, single scatter correction algorithms, single correction algorithms, post processing filters, and/or kernel size for post processing filter.

12. The system according to claim 1 , wherein the one or more processors are further configured to:
to optimize reconstruction parameters and/or sub-routines, iteratively repeat:
controlling the display to display the variations of the selected reconstruction parameters;
receiving a user selection of one of the displayed preview images or sub-images; and
configuring a reconstruction processor to reconstruct the scanned imaging data with the reconstruction parameters and/or sub-routines used to generate the selected preview image or sub-image.

13. The system according to claim 3 , wherein the one or more processors are further configured to:
reconstruct scan data of the subject into a preview diagnostic image using reconstruction parameters and/or sub-routines corresponding to the selected preview image or sub-image;
in the background, reconstruct the scan data with variations of the reconstruction parameters and/or sub-routines corresponding to the selected preview images or sub-images; and
display the variations of the selected preview images or sub-images as candidate diagnostic images for a clinician selection.

14. The system according to claim 13 , wherein the one or more processors are further configured to:
reconstruct a portion of scan data into the preview images or sub-images;
to optimize reconstruction parameters and/or sub-routines, iteratively repeat:
controlling the display to display the variations of the selected reconstruction parameters;
receiving a user selection of one of the displayed preview images or sub-images; and
configuring a reconstruction processor to reconstruct the scanned imaging data with the reconstruction parameters and/or sub-routines used to generate the selected preview image or sub-image;

select one of the preview images or sub-images; and
reconstruct full set of scan data using reconstruction parameters and sub-routines corresponding to the selected preview image or sub-image.

Assignees

• Koninklijke Philips Nv

Inventors

• Tung Chi-Hua
• Dwivedi Shekhar
• Zhu Yang-Ming
• Collins John Patrick

Classifications

• G06T12/00

  Tomographic reconstruction from projections · CPC title

• G16H30/40

  for processing medical images, e.g. editing · CPC title

• G06F3/04842

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title

• G16H40/63

  for local operation · CPC title

• G06T2210/41

  Medical · CPC title