System and method for providing localization of radiological information utilizing radiological domain ontology

• US 8,504,511 B2
• Filed: 09/30/2009
• Issued: 08/06/2013
• Est. Priority Date: 08/05/2009
• Status: Active Grant

• Current Assignee: Fujifilm Healthcare Americas Corporation (Fujifilm Holdings Corporation)
• Original Assignee: Fujifilm Medical Systems USA Incorporated (Fujifilm Holdings Corporation)
• Inventors: Hale, Charles R., Ding, Yihong
• Primary Examiner(s): Starks, Wilbert L
• Application Number:
  US12/570,750
• Publication Number:
  US 20110033095A1
• Time in Patent Office: 1,406 Days
• Field of Search: 706/54, 706/45
• US Class Current: 706/54
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

The present invention is directed in general to a system and method that employs radiological localization ontology to localize specified and modeled radiological domain knowledge. A system and method are provided that allows for consulting the ontology in the context of the model the ontology fulfills. The result of consulting the ontology will be localized radiological information based on information provided in the consultation. Even further, such result is validated, identified and classified radiological information that is based on information provided in the consultation. By consulting the ontology the system is also able to translate designated radiological information from one localized representation to another and consult a language independent radiological domain knowledge.

Claims

1. A method programmed for execution in a computing environment for consulting and providing localized response information from a radiological domain ontology in reference to a subject, the method comprising:

defining one or more aspects of radiology functions as concept properties represented by a vocabulary of one or more instances of the radiological domain ontology, the radiological domain ontology declaring and fulfilling a model of radiological domain knowledge;

wherein said model of radiological domain knowledge comprises;

one or more findings;

one or more finding characteristics; and

object properties, wherein said object properties represent relationships among said findings and finding characteristics;

employing a context that defines a set of said radiological domain knowledge and the relationships among said set of said radiological domain knowledge, to describe said subject;

providing an informational item of interest that relates to said subject in a localized representation; and

providing a localization ontology, said localization ontology comprising;

localization language references;

localization labels for said findings, finding characteristics and object properties; and

references to said radiological domain ontology;

wherein a localized representation of said informational item of interest is identified in said localization language reference and the corresponding localization labels are identified and utilized to consult said radiological domain ontology to validate that said localized informational item of interest is radiological and resides in said radiological domain knowledge, wherein a definitive concept of said localized informational item of interest is identified from within said radiological domain knowledge, and wherein said localized informational item of interest is classified to provide said localized response regarding the subject.

2. The method of claim 1 wherein said classifying of localized informational item of interest identifies or defines said localized informational item of interest as one of a finding or a finding characteristic.

3. The method of claim 1 wherein the said provided response information from said radiological domain ontology is a list of said localization labels for all of said findings for said model of radiological domain knowledge.

4. The method of claim 3 wherein the provided response information from said radiological domain ontology is a list of all of said localization labels for all of said finding characteristics that apply to a given finding of claim 3.

5. The method of claim 1 wherein the provided response information from said radiological domain ontology is a list of all of said localization labels for all of said finding characteristics for said model of radiological domain knowledge.

6. The method of claim 1 further comprising validating that said localized informational item of interest is within a specific radiological context.

7. The method of claim 1 further comprising, providing a list of containers and container items, wherein a container is a characteristic concept and container items are individual finding characteristics that have applicability to a user interface for a given radiological finding concept.

8. The method of claim 1 wherein said localized information item of interest is provided in Spanish by a radiologist during the process of analyzing a patient X-ray.

9. A method programmed for execution in a computing environment for identifying, validating and classifying one or more localized radiological informational items, utilizing a localization ontology to localize a radiological domain ontology, the method comprising:

receiving said localized radiological informational items;

defining one or more aspects of radiology functions as concept properties represented by a vocabulary of one or more instances of said radiological domain ontology, said radiological domain ontology declaring and fulfilling a model of radiological domain knowledge

providing localization labels for said concept properties and said vocabulary of one or more instances of said radiological domain ontology;

accessing said localization labels to define said localized radiological informational item in said radiological domain knowledge;

wherein said localized radiological informational items may be validated as residing in said radiological domain knowledge, identified as a definitive concept within said radiological domain knowledge, and classified within said radiological domain knowledge;

wherein said radiological domain knowledge comprises;

one or more findings;

one or more finding characteristics; and

object properties, wherein said object properties represent relationships among said findings and finding characteristics.

10. A method programmed in a computing environment for providing localized consultation of a single radiological domain ontology the method comprising:

defining classes, properties and instances of known concepts in the radiological domain ontology in a first language;

defining at least one default localization label for each of said classes, properties and instances in each of said first language and a second language; and

providing a translation matching module for correlating one or more labels of said first language to one or more labels of said second language;

whereby the radiological domain ontology may be consulted utilizing an informational item in said second language and response is provided back in said second language.

11. A computing system for identifying, validating and classifying one or more radiological informational items, utilizing a radiological domain ontology in reference to a subject comprising:

a definition of one or more aspects of radiology functions as concept properties represented by a vocabulary of one or more instances of the radiological domain ontology, the radiological domain ontology declaring and fulfilling a model of radiological domain knowledge;

means for receiving an informational item of interest that relates to said subject, in a localized representation;

a context that defines a set of said radiological domain knowledge and the relationships among said set of said radiological domain knowledge to describe said subject;

wherein said domain knowledge comprises;

one or more findings;

one or more finding characteristics; and

object properties,

wherein said object properties represent relationships among said findings and finding characteristics;

a validation module;

an identification module;

a classification module; and

a localization layer ontology, said localization layer ontology comprising;

localization language references;

localization labels for said findings, finding characteristics and object properties; and

references to said radiological domain ontology;

wherein a localized representation of said informational item of interest is identified in said localization language reference and the corresponding localization labels are identified and utilized to consult the radiological domain ontology;

wherein said validation module validates that said localized informational item of interest is radiological and resides in said set of said radiological domain knowledge, said identification module identifies a definitive concept of said localized informational item of interest from within said set of said radiological said domain knowledge, and said classification module classifies said localized informational item of interest to provide a localized response regarding the subject.