Image selection for presentation

Patent metadata

Field	Value
Publication number	US-12475989-B2
Application number	US-202118266683-A
Country	US
Kind code	B2
Filing date	Dec 14, 2021
Priority date	Dec 16, 2020
Publication date	Nov 18, 2025
Grant date	Nov 18, 2025

Abstract

A controller ( 150 ) for selecting images for presentation includes a memory ( 151 ), a processor ( 152 ) and a receiver. The memory ( 151 ) stores instructions. The processor ( 152 ) executes the instructions. The receiver receives a stream of a plurality of images. When executed by the processor ( 152 ), the instructions cause the controller ( 150 ) to apply trained artificial intelligence to the plurality of images and generate, based on the trained artificial intelligence, a 1-dimensional stream of a plurality of values corresponding respectively to the plurality of images. Each of the plurality of values of the 1-dimensional stream indicates a significance of a corresponding image of the plurality of images according to the trained artificial intelligence. The instructions also cause the controller ( 150 ) to output the plurality of values of the 1-dimensional stream for display with the plurality of images.

First claim

We claim:

1 . A system for selecting images of an interventional medical procedure, the system comprising:
a controller comprising a memory configured to store instructions and a processor configured to execute the instructions, and when executed by the processor, the instructions cause the controller to: receive a stream of a plurality of images from an imaging system; generate, based on system information of the imaging system and procedure information of the interventional medical procedure, a 1-dimensional stream of a plurality of values corresponding respectively to the plurality of images, each of the plurality of values of the 1-dimensional stream indicating a significance of a corresponding image of the plurality of images to the interventional medical procedure; automatically save or automatically flag frames having a value indicating most significant frames, and rejecting frames having a value indicating least significant frames; and display, with one or more of the saved or automatically flagged image frames, one or more visual indicators corresponding to the values that enable a user to determine the significance of the corresponding saved image frames based on the one or more visual indicators.

2 . The system of claim 1 , wherein, when executed by the processor, the instructions further cause the controller to:
apply a trained artificial intelligence model to the plurality of images to generate the plurality of values indicating the significance of the corresponding plurality of images, the trained artificial intelligence model trained to predict significance values for images of interventional medical procedures based on imaging system information and procedural information of the interventional medical procedures.

3 . The system of claim 1 , further comprising:
the imaging system configured to generate the plurality of images during the interventional medical procedure and provide the stream of the plurality of images to the controller during the interventional medical procedure.

4 . The system of claim 1 , wherein, when executed by the processor, the instructions further cause the controller to:
receive the stream of a plurality of images as one of a plurality of streams of images from different sources that generate the plurality of streams of images.

5 . The system of claim 1 , wherein the system information of the imaging system includes at least one of imaging system position, radiation setting, exposure settings, digital subtraction angiography (DSA) information, and table position.

6 . The system of claim 1 , wherein the most significant frames have a value greater than a predetermined threshold, and the least significant frames have a value less that the predetermined threshold.

7 . The system of claim 6 , wherein the predetermined threshold is adjustable and/or may comprise more than one predetermined threshold.

8 . The system of claim 1 , wherein the visual indicators of values comprise one or more of: color-coded frames with colors varying according to the values, a heat map corresponding to the values, numerical representations of the numbers corresponding to the values, shapes with sizes corresponding to the values.

9 . A system for selecting images of an interventional medical procedure, the system comprising:
a controller comprising a memory configured to store instructions and a processor configured to execute the instructions, and when executed by the processor, the instructions cause the controller to: receive a stream of a plurality of images from an imaging system; generate, based on system information of the imaging system and procedure information of the interventional medical procedure, a 1-dimensional stream of a plurality of values corresponding respectively to the plurality of images, each of the plurality of values of the 1-dimensional stream indicating a significance of a corresponding image of the plurality of images to the interventional medical procedure; select one or more of the plurality of images based on the corresponding plurality of values; and an interface configured to display, with the selected one or more of a the plurality of images, visual representations of the 1-dimensional stream of the plurality of values adjusted on the interface based on indicators of values representing a significance of an image frame.

10 . The system of claim 9 , wherein the indicators are used to display a only a most significant frame, and reject a least significant frame.

11 . The system of claim 9 , wherein, when executed by the processor, the instructions further cause the controller to:
apply a trained artificial intelligence model to the plurality of images to generate the plurality of values indicating the significance of the corresponding plurality of images, the trained artificial intelligence model trained to predict significance values for images of interventional medical procedures based on imaging system information and procedural information of the interventional medical procedures.

12 . The system of claim 9 , wherein the imaging system is configured to generate the plurality of images during the interventional medical procedure and provide the stream of the plurality of images to the controller during the interventional medical procedure.

13 . The system of claim 9 , wherein, when executed by the processor, the instructions further cause the controller to:
receive the stream of a plurality of images as one of a plurality of streams of images from different sources that generate the plurality of streams of images.

14 . A tangible, non-transitory computer-readable medium that stores instructions, which when executed by a processor, cause the processor to:
receive a stream of a plurality of images from an imaging system; generate, based on system information of the imaging system and procedure information of the interventional medical procedure, a 1-dimensional stream of a plurality of values corresponding respectively to the plurality of images, each of the plurality of values of the 1-dimensional stream indicating a significance of a corresponding image of the plurality of images to the interventional medical procedure; and automatically save or automatically flag frames having a value indicating most significant frames, and rejecting frames having a value indicating least significant frames; and display, with one or more of the plurality of saved or automatically flagged image frames, one or more visual indicators corresponding to the values that enable a user to determine the significance of the corresponding saved image frames based on the one or more visual indicators.

15 . The tangible, non-transitory computer-readable medium of claim 14 , wherein the instructions further cause the processor to:
group, based on the plurality of values of the 1-dimensional stream, one or more sets of at least one consecutive image based on the values corresponding to the one or more sets of at least one consecutive image; and display, for each set of the one or more sets of at least one consecutive image, an indicator indicating that the one or more sets of at least one consecutive image belong to a set indicated by the indicator.

16 . The tangible, non-transitory computer-readable medium of claim 14 , wherein the instructions further cause the processor:
automatically delete at least one of the plurality of the images indicated by a value below a first threshold; and automatically storing at least one of the plurality of the images indicated by a value above a second threshold.

17 .

Assignees

• Koninklijke Philips Nv

Inventors

• Flexman Molly Lara
• Panse Ashish Sattyavrat
• Toporek Grzegorz Andrzej
• Kruecker Jochen

Classifications

• G06V10/774

  Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06V2201/03

  Recognition of patterns in medical or anatomical images · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G16H30/20 Primary

  for handling medical images, e.g. DICOM, HL7 or PACS · CPC title

• G16H30/40 Primary

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