Determination of an image series in dependence on a signature set

US10380740B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-10380740-B2
Application numberUS-201715650049-A
CountryUS
Kind codeB2
Filing dateJul 14, 2017
Priority dateJul 14, 2016
Publication dateAug 13, 2019
Grant dateAug 13, 2019

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

For the determination of an image series from a set of a number of image series, in each case of a signature is compiled for each of the number of image series. This signature is formed from a set of attributes of the respective image series. A signature from the signatures for the image series is ascertained that is most similar to a prespecified signature set. An action is performed with the image series whose signature was ascertained as the most similar signature.

First claim

Opening claim text (preview).

The invention claimed is: 1. A method for determining an image series from a set comprised of a plurality of image series, said method comprising: generating a layout comprising a plurality of segments for depiction, at a display, in which segments of the image series in said set of a plurality of image series are to be respectively displayed; for each image series in said plurality of image series, compiling, by a processor of a control computer, a signature from a set of attributes of that respective image series, and thereby obtaining a plurality of signatures; assigning, by the processor, a predetermined signature set from signatures of exemplary image series to each segment of the plurality of segments of the layout; ascertaining, by the processor, a signature among said plurality of signatures associated with the plurality of image series that is most similar to said respective assigned predetermined signature set for each segment of the plurality of segments of the layout, the ascertaining including, for each of said image series in said set of plurality of image series, determining a distance between the respective signature thereof and the predetermined signature set, and determining said most similar signature as the signature of a respective image series for which said distance is shortest, wherein each signature has the same attributes, and determining said distance as a sum of differences between attribute values of a respective signature and each signature in said predetermined signature set; and for each segment of the plurality of segments of the layout, presenting, by the processor, the image series having said most similar signature in the respective one of said segments of the layout of said display to determine a respective best match for evaluation, wherein the set of attributes includes at least one of the following attributes: a DICOM attribute of the respective image series, values extracted from pixel values of the respective image series, a pixel value histogram of the respective image series, a Fourier spectrum of the respective image series, and information about anatomical landmarks that are visible in the respective image series. 2. A method as claimed in claim 1 , wherein said distance between the respective signature thereof and the predetermined signature set is determined depending on average distances between the respective signature and each signature of the predetermined signature set. 3. A method as claimed in claim 1 wherein said distance between the respective signature thereof and the predetermined signature set is determined depending on a weighted sum distance between the respective signature and each signature of the predetermined signature set. 4. A method as claimed in claim 1 wherein determining said distance as a sum of differences between attribute values of a respective signature and each signature in said predetermined signature set. 5. A method as claimed in claim 1 comprising identifying a segment among said plurality of segments having a signature that is second most similar to said predetermined signature set, and identifying an image series having a signature that is second most similar to said predetermined image set, and displaying said image series having said second most similar signature in said segment having said second most similar signature. 6. A method as claimed in claim 1 comprising also displaying a selected image series, among said set of a plurality of image series, that does not have said most similar signature, in a different segment in said display from the segment in which said image series having the most similar signature is displayed. 7. A method as claimed in claim 1 comprising determining said distance that is shortest as an average distance that a respective image series has between all other image series in said set of a plurality of image series. 8. A method as claimed in claim 1 comprising determining said distance that is shortest as a weighted sum distance that a respective image series has between all other image series in said set of a plurality of image series. 9. A method as claimed in claim 1 wherein said distance is determined as a sum of differences between attribute values of a respective signature and each signature in said predetermined signature set. 10. A method as claimed in claim 1 wherein compiling said plurality of signatures includes compressing the respective signatures. 11. A method as claimed in claim 1 comprising determining said most similar signature by determining a degree of similarity, for each signature of each image series, to said predetermined signature set, and displaying said image series having said most similar signature only when said most similar signature has a degree of similarity that exceeds a predetermined similarity threshold. 12. A method as claimed in claim 1 comprising compiling the respective signatures of said respective image series while the respective image series is being created by an imaging system. 13. A non-transitory, computer-readable data storage medium encoded with programming instructions, said storage medium being loaded into a processor and said programming instructions causing said processor to: generate a layout comprising a plurality of segments for depiction, at a display, in which segments of the image series in said set of a plurality of image series are to be respectively displayed; for each image series in said plurality of image series, compile a signature from a set of attributes of that respective image series, and thereby obtaining a plurality of signatures; assign a predetermined signature set from signatures of exemplary image series to each segment of the plurality of segments of the layout; ascertain a signature among said plurality of signatures associated with the plurality of image series that is most similar to said respective assigned predetermined signature set for each segment of the plurality of segments, the ascertaining including, for each of said image series in said set of plurality of image series, determining a distance between the respective signature thereof and the predetermined signature set, and determining said most similar signature as the signature of a respective image series for which said distance is shortest, wherein each signature has the same attributes, and determining said distance as a sum of differences between attribute values of a respective signature and each signature in said predetermined signature set; and for each of said segments, present the image series having said most similar signature in the respective one of said segments of said display to determine a respective best match for evaluation, wherein the set of attributes includes at least one of the following attributes: a DICOM attribute of the respective image series, values extracted from pixel values of the respective image series, a pixel value histogram of the respective image series, a Fourier spectrum of the respective image series, and information about anatomical landmarks that are visible in the respective image series. 14. An imaging system for compiling a plurality of input image series and for displaying at least one image series for evaluation, comprising: means for compiling an input image series of a volume segment of an examination object, a control computer, and a display, wherein: the is control computer is configured to: create a layout comprising a plurality of segments for depiction, at at the display, in which segments of the image series in said set of a plurality of image series are to be respectively displayed; assign a predeterm

Assignees

Inventors

Classifications

  • Physics · mapped topic

  • involving thresholding · CPC title

  • Determining parameters from multiple pictures (depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85) · CPC title

  • G06T7/10Primary

    Segmentation; Edge detection (motion-based segmentation G06T7/215) · CPC title

  • for local operation · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US10380740B2 cover?
For the determination of an image series from a set of a number of image series, in each case of a signature is compiled for each of the number of image series. This signature is formed from a set of attributes of the respective image series. A signature from the signatures for the image series is ascertained that is most similar to a prespecified signature set. An action is performed with the …
Who is the assignee on this patent?
Siemens Healthcare Gmbh
What technology area does this patent fall under?
Primary CPC classification G06T7/10. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Aug 13 2019 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 6 related publications on this page (citations in our corpus or others sharing the same primary CPC).