Systems and methods for computer-assisted search of image slices for indications of a finding

Patent metadata

Field	Value
Publication number	US-11409786-B2
Application number	US-201816605517-A
Country	US
Kind code	B2
Filing date	Apr 20, 2018
Priority date	Apr 20, 2017
Publication date	Aug 9, 2022
Grant date	Aug 9, 2022

Abstract

The present disclosure pertains to computer-assisted search of image slices. In some embodiments, an image slice having a detected finding (and representing a cross section of at least a portion of an individual) may be determined. A search space may be reduce to a subset of image slices respectively representing a cross section corresponding to the cross section represented by the determined image slice. The search space reduction may comprise filtering a set of image slices based on the cross section represented by the determined image slice. Image slice information related to the determined image slice and related one or more image slices (of the image slices subset) may be obtained based on the search space reduction. A determination of whether indications of the detected finding exist in the image slices (of the image slices subset) may be effectuated based on the image slice information.

First claim

What is claimed is:

1. A system for facilitating computer-assisted search of image slices for indications of a finding, the system comprising:
one or more hardware processors configured by machine-readable instructions to:
determine an image slice that comprises a detected finding related to an individual, the determined image slice representing a cross section of at least a portion of the individual during an examination of the individual;
reduce a search space to a subset of image slices comprising image slices that respectively represent a cross section corresponding to the cross section represented by the determined image slice, wherein reducing the search space comprises filtering a set of image slices based on the cross section represented by the determined image slice, the image slices set comprising image slices that respectively represent a cross section of at least a portion of the individual during one or more other examinations of the individual, wherein the one or more other examinations of the individual comprises one or more prior examinations of the individual that occurred at least a predetermined threshold amount of time prior to the examination of the individual;
obtain first image slice information related to the determined image slice;
obtain, based on the search space reduction, second image slice information related to one or more image slices of the image slices subset; and
determine, based on the first image slice information and the second image slice information, whether one or more indications of the detected finding exist in the one or more image slices of the image slices subset.

2. The system of claim 1 , wherein the one or more hardware processors are configured to provide, via a user interface, a representation of an indication of the detected finding responsive to a determination that one or more indications of the detected finding exist in the one or more image slices of the image slices subset.

3. The system of claim 1 , wherein the first image slice information comprises information identifying characteristics related to the determined image slice, and the information identifying the characteristics related to the determined image slice comprises annotations associated with the determined image slice or characteristic vectors of objects represented in the determined image slice, and wherein the second image slice information comprises information identifying characteristics related to the one or more image slices of the image slices subset, and the information identifying the characteristics related to the one or more image slices comprises annotations associated with the one or more image slices or characteristic vectors of objects represented in the one or more image slices.

4. The system of claim 1 , wherein the one or more hardware processors are configured to reduce the search space to the image slices subset by:
selecting the image slices set based on image slices of the image slices set being associated with the selected one or more other examinations; and
filtering the selected image slices set based on the cross section represented by the determined image slice by selecting at least one image slice of the image slices subset based on the at least one image slice representing a cross section corresponding to the cross section represented by the determined image slice such that the reduced search space comprises the at least one image slice.

5. The system of claim 1 , wherein reducing the search space to the image slices subset comprises filtering the image slices subset by (i) selecting a first image slice of the image slices subset based on the first image slice representing a cross section corresponding to the cross section represented by the determined image slice and (ii) selecting a second image slice of the image slices subset based on the second image slice being within a threshold proximity of the first image slice.

6. The system of claim 5 , wherein the one or more hardware processors are configured to:
determine, in the determined image slice, a region comprising the detected finding, the region being a portion of the determined image slice;
determine size information associated with the region of the determined image slice, the size information comprising information identifying a size of the region of the determined image slice with respect to a first dimension or information identifying a size of the region of the determined image slice with respect to a second dimension different from the first dimension; and
determine the threshold proximity based on the size information.

7. The system of claim 1 , wherein the one or more hardware processors are configured to:
determine, in the determined image slice, a region comprising the detected finding, the region being a portion of the determined image slice; and
further reduce the search space by reducing the search space to one or more regions of the one or more image slices of the image slices subset based on the one or more regions corresponding to the region of the determined image slice,
wherein obtaining the first image slice information and the second image slice information is based on the further search space reduction.

8. A method of facilitating computer-assisted search of image slices for indications of a finding, the method comprising:
determining an image slice that comprises a detected finding related to an individual, the determined image slice representing a cross section of at least a portion of the individual during an examination of the individual;
reducing a search space to a subset of image slices comprising image slices that respectively represent a cross section corresponding to the cross section represented by the determined image slice, wherein reducing the search space comprises filtering a set of image slices based on the cross section represented by the determined image slice, the image slices set comprising image slices that respectively represent a cross section of at least a portion of the individual during one or more other examinations of the individual, wherein the one or more other examinations of the individual comprises one or more prior examinations of the individual that occurred at least a predetermined threshold amount of time prior to the examination of the individual;
obtaining first image slice information related to the determined image slice;
obtaining, based on the search space reduction, second image slice information related to one or more image slices of the image slices subset; and
determining, based on the first image slice information and the second image slice information, whether one or more indications of the detected finding exist in the one or more image slices of the image slices subset.

9. The method of claim 8 ,
wherein the method further comprises providing, via a user interface, a representation of an indication of the detected finding responsive to a determination that one or more indications of the detected finding exist in the one or more image slices of the image slices subset.

10. The system of claim 8 , wherein the first image slice information comprises information identifying characteristics related to the determined image slice, and the information identifying the characteristics related to the determined image slice comprises annotations associated with the determined image slice or characteristic vectors of objects represented in the determined image slice, and wherein the second image slice information comprises information identifying characteristics related to the one or more image slices of the image slices subset, and the information identifying the characteristics related to the one or more image slices comprises annotations

Assignees

• Koninklijke Philips Nv
• Univ Chicago

Inventors

• Trilisky Igor
• Sevenster Merlijn
• Tahmasebi Maraghoosh Amir Mohammad
• Chang Paul Joseph

Classifications

• G06F16/535 Primary

  Filtering based on additional data, e.g. user or group profiles · CPC title

• G06F16/58 Primary

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06V10/92 Primary

  using spatial domain filters, e.g. joint transform correlators · CPC title

• G06F16/583

  using metadata automatically derived from the content · CPC title

• G16H50/50

  for simulation or modelling of medical disorders · CPC title