Generation of pictorial reporting diagrams of lesions in anatomical structures

Patent metadata

Field	Value
Publication number	US-10235360-B2
Application number	US-201113997277-A
Country	US
Kind code	B2
Filing date	Dec 16, 2011
Priority date	Dec 23, 2010
Publication date	Mar 19, 2019
Grant date	Mar 19, 2019

Abstract

The invention relates to a system (SYS) for automatically extracting a location of an abnormality with respect to an anatomical structure from a report, the system comprising a tokenizer (U10) for tokenizing the report or a part of it, thereby producing a plurality of tokens, and an analyzer (U20) for identifying a semantic structure comprising identified tokens of the plurality of tokens, describing the location of the abnormality with respect to the anatomical structure. Optionally, the system further comprises a mapper (U30) for annotating a diagram representing the anatomical structure, based on the identified semantic structure describing the location of the abnormality with respect to the anatomical structure. Using the system, the location of the abnormality with respect to the anatomical structure can be extracted from each report of the plurality of reports produced over the period of time. The extracted locations may be used by a clinician for diagnostic purposes.

First claim

The invention claimed is:

1. A system for automatically extracting a location of an abnormality with respect to an anatomical structure with a body comprising a plurality of anatomical structures from a report, the system comprising:
a memory,
a display, and
a controller that controls:
a tokenizer that tokenizes the report or a part of the report, thereby producing a plurality of tokens that are stored in the memory;
an analyzer that identifies a semantic structure comprising at least one identified token of the plurality of token that describes the location of the abnormality with respect to the anatomical structure; and
a mapper that indicates the location of the abnormality with respect to the anatomical structure on the display via a diagram representing the anatomical structure by annotating the diagram based on the identified semantic structure by adding a graphic visualization of the location of the abnormality on the diagram representing the anatomical structure;

wherein the plurality of tokens includes at least one reference token that identifies a reference point in the anatomical structure;
wherein the identified token describes the location of the abnormality relative to the reference point in the anatomical structure;
wherein the diagram representing the anatomical structure includes a reference feature that corresponds to the reference point;
wherein the mapper uses the location of the abnormality relative to the reference point in the anatomical structure to determine a corresponding abnormality location on the diagram relative to the reference feature; and
wherein the mapper provides the graphic visualization of the abnormality at the abnormality location on the diagram.

2. The system of claim 1 , wherein identifying the semantic structure includes comparing conceptual tokens of the plurality of tokens to concepts of a plurality of concepts in order to determine the identified token.

3. The system of claim 2 , wherein comparing conceptual tokens of the plurality of tokens to concepts of a plurality of concepts includes computing a conceptual similarity between the conceptual tokens and the concepts.

4. The system of claim 2 , wherein identifying the semantic structure further includes comparing relational tokens, describing relations between/among the conceptual tokens, to concept relations between/among the concepts of the plurality of concepts, in order to determine relations between/among the identified conceptual tokens.

5. The system of claim 2 , wherein comparing the relational tokens to the concept relations between/among the concepts of the plurality of concepts includes computing a relational similarity between the relational tokens and the concept relations.

6. The system of claim 1 , further comprising an extractor that extracts additional information about the identified abnormality, based on the identified semantic structure, the additional information comprising a size or palpability of the abnormality; wherein the graphic visualization is indicative of the size or palpability.

7. The system of claim 1 , wherein the anatomical structure is a breast or axilla.

8. A workstation comprising the system of any one of the previous claims.

9. A method of automatically extracting a location of an abnormality with respect to an anatomical structure within a body comprising a plurality of anatomical structures from a report by a computer processor, the method comprising:
tokenizing the report or a part of the report, thereby producing a plurality of tokens;
identifying a semantic structure comprising at least one identified token of the plurality of tokens that describes the location of the abnormality; and
indicating the location of the abnormality with respect to the anatomical structure on a diagram representing the anatomical structure by annotating the diagram based on the identified semantic structure by adding a graphic visualization of the location of the abnormality on the diagram representing the anatomical structure;
wherein the plurality of tokens includes at least one reference token that identifies a reference point in the anatomical structure;
wherein the identified token describes the location of the abnormality relative to the reference point in the anatomical structure;
wherein the diagram representing the anatomical structure includes a reference feature that corresponds to the reference point;
wherein the mapper uses the location of the abnormality relative to the reference point in the anatomical structure to determine a corresponding abnormality location on the diagram relative to the reference feature; and
wherein the mapper provides the graphic visualization of the abnormality at the abnormality location on the diagram.

10. A method as claimed in claim 9 , wherein identifying the semantic structure includes comparing conceptual tokens of the plurality of tokens to concepts of a plurality of concepts in order to determine the identified token.

11. A method as claimed in claim 10 , wherein identifying the semantic structure further includes comparing relational tokens, describing relations between/among the conceptual tokens, to concept relations between/among the concepts of the plurality of concepts in order to determine relations between/among the identified conceptual tokens.

12. The method of claim 10 , wherein comparing conceptual tokens of the plurality of tokens to concepts of a plurality of concepts includes computing a conceptual similarity between the conceptual tokens and the concepts.

13. A method as claimed in claim 9 , further comprising extracting additional information about the identified abnormality, based on the identified semantic structure, the additional information comprising a size or palpability of the abnormality; wherein the graphic visualization is indicative of the size or palpability.

14. A non-transitory computer readable medium that includes a program that, when executed by a processing system, causes the system to automatically extract a location of an abnormality with respect to an anatomical structure within a body comprising a plurality of anatomical structures from a report by:
tokenizing the report or a part of the report, whereby producing a plurality of tokens;
identifying a semantic structure comprising at least one identified token of the plurality of tokens that describes the location of the abnormality; and
indicating the location of the abnormality with respect to the anatomical structure on a diagram representing the anatomical structure by annotating the diagram based on the identified semantic structure by adding a graphic visualization of the location of the abnormality on the diagram representing the anatomical structure;
wherein the plurality of tokens includes at least one reference token that identifies a reference point in the anatomical structure;
wherein the identified token describes the location of the abnormality relative to the reference point in the anatomical structure;
wherein the diagram representing the anatomical structure includes a reference feature that corresponds to the reference point;
wherein the mapper uses the location of the abnormality relative to the reference point in the anatomical structure to determine a corresponding abnormality location on the diagram relative to the reference feature; and
wherein the mapper provides the graphic visualization of the abnormality at the abnormality location on the diagram.

15. The medium of claim 14 , wherein the program causes the system to identify the semantic structure by comparing conceptual tokens of the plurality of tokens to conc

Assignees

• Sevenster Merlijn
• Qian Yuechen
• Koninklijke Philips Nv

Inventors

• Sevenster Merlijn
• Qian Yuechen

Classifications

• G16H80/00

  ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G16H15/00

  ICT specially adapted for medical reports, e.g. generation or transmission thereof · CPC title

• G06F40/40 Primary

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

• G06F40/284 Primary

  Lexical analysis, e.g. tokenisation or collocates · CPC title