Image sequence analysis

Patent metadata

Field	Value
Publication number	US-2024127432-A1
Application number	US-202218276482-A
Country	US
Kind code	A1
Filing date	Jan 24, 2022
Priority date	Feb 12, 2021
Publication date	Apr 18, 2024
Grant date	—

Abstract

A system and method for achieving more accurate results when applying an image processing task to a series of medical images of a patient, without significantly increasing processing resource. The proposed system and method is based on receiving a plurality of image sequences of a particular anatomical region, each capturing cyclical movement of an anatomical object. Each image sequence is supplied to a classifier module which employs use of one or more machine learning algorithms to derive at least one score for each image sequence indicative of predicted success or quality of a result of the image processing task if applied to the given image series. This permits an assessment to be made in advance of which of the plurality of image series is most likely to result in the best (e.g. highest quality, or greatest amount of information) results from the image processing task. This allows maximization of the quality of image processing results, without the need to actually process each of the image series with the image processing task, which would consume a large amount of processing resource and consume time.

First claim

1 . A system for assessing candidate image series of a cyclically moving anatomical object for application of an image processing task, the system comprising:
a classifier module comprising at least one machine learning algorithm, the machine learning algorithm being adapted to receive as input an image series of a cyclically moving object and to generate as an output at least one score, the score being representative of a predicted measure of success of a particular image processing task if it were to be applied to the image series; and a control module adapted to:
receive a plurality of candidate image series of the cyclically moving anatomical object,
supply each image series as an input to the classifier module to thereby obtain the at least one score for each of the plurality of image series, and
identify a best subset of the plurality of image series for application of the image processing task based on the at least one score for each image series.

2 . A system as claimed in claim 1 , wherein the system further includes an image processing module adapted to receive as input an image series, to apply the image processing task to the input image series, and to generate an output processed image series.

3 . A system as claimed in claim 2 , wherein the control module is adapted to supply only the identified best subset of image series to the image processing module.

4 . A system as claimed in claim 3 , wherein the control module is adapted to store a record of the received plurality of image series in a memory, and is adapted to delete from the memory at least each of the received image series which are not included in the identified best subset of image series without supplying the image series to the image processing module.

5 . A system as claimed in claim 1 , wherein the one or more machine learning algorithms of the classifier module are adapted to generate a plurality of different scores, each representing a different measure of predicted success of the image processing task.

6 . A system as claimed in claim 5 , wherein the control module is further adapted to:
determine an overall score for each of the plurality of image series from the respective plurality of scores for each image series; and identify a best subset of the image series for application of the image processing task based on the overall score for each image series.

7 . A system as claimed in claim 1 , wherein the method comprises ranking the plurality of image series according to the at least one score or the overall score.

8 . A system as claimed in claim 1 , wherein the at least one machine learning algorithm is a machine learning algorithm which has been trained using a training data set comprising a plurality of sample image series, each having been manually tagged with the at least one score.

9 . A system as claimed in claim 1 , wherein the image processing task comprises an image segmentation of one or more anatomical areas of the cyclically moving anatomical object.

10 . A system as claimed in claim 9 , wherein at least one score includes:
a score indicative of predicted correspondence between shapes or outlines generated in the segmentation when applied to the image series and the shapes or outlines present in the image series; and/or a score indicative of predicted correspondence between a mesh geometry generated in the segmentation when applied to the image series and a geometry of a pre-defined anatomical object of interest.

11 . A system as claimed in claim 1 , wherein the received plurality of image series comprises a plurality of ultrasound image series.

12 . A system as claimed in claim 1 , further comprising an ultrasound imaging apparatus, and wherein the control module is adapted to receive the plurality of image series from the ultrasound imaging apparatus.

13 . A computer implemented method comprising:
receiving a plurality of image series of a cyclically moving anatomical object; applying to each of the plurality of image series a classifier operation, wherein the classifier operation comprises at least one machine learning algorithm, the at least one machine learning algorithm being adapted to receive as input an image series of a cyclically moving object and to generate as an output at least one score, the at least one score being representative of a predicted measure of success of a particular image processing task if it were to be applied to the image series, identifying a best subset of the plurality of image series for application of the image processing task based on the at least one score for each image series.

14 . A method as claimed in claim 13 , further comprising applying the image processing task only to the identified best subset of the plurality of image series.

15 . A computer program product comprising computer program code configured, when run on a processor, to cause the processor to perform a method in accordance with claim 13 .

Assignees

• Koninklijke Philips Nv

Inventors

• Groth Alexandra
• Lossau Tanja
• Waechter-Stehle Irina
• Weber Frank Michael
• Peters Jochen
• Wild Sebastian
• Ewald Arne
• Goossen Andre

Classifications

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06T1/60

  Memory management · CPC title

• G06T7/12

  Edge-based segmentation · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title