System and Method for Extracting Radiological Information Utilizing Radiological Domain Report Ontology and Natural Language Processing

• US 20110035208A1
• Filed: 11/25/2009
• Published: 02/10/2011
• Est. Priority Date: 08/05/2009
• Status: Abandoned Application

• Current Assignee: Fujifilm Medical Systems USA Incorporated (Fujifilm Holdings Corporation)
• Original Assignee: Fujifilm Medical Systems USA Incorporated (Fujifilm Holdings Corporation)
• Inventors: Ding, Yihong, Satz, Donald E., Hale, Charles R.
• Application Number:
  US12/625,880
• Publication Number:
  US 20110035208A1
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing

Abstract

A system and method that employs radiological report domain ontology and natural language processing to specify and model historical radiological information as knowledge is provided. The system and method trains a statistical probability based natural language processing system to recognize the semantics of a radiological domain. A methodology is provided to submit portions or the entire content of textual historical radiological report to a natural language processor wherein such data is interpreted and reported in a structured hierarchy.

Claims

1. A method programmed in a computing environment for providing radiological reporting, the method comprising:

utilizing a historical radiological data source;

extracting one or more informational items from said historical radiological data source to provide said one or more informational items to a natural language processor;

said natural language processor defining select ones of said one or more informational items as report domain concepts of a radiological ontology; and

wherein said report domain concepts are categorized in the context of said radiological ontology to provide a hierarchical radiological report.

2. A method in accordance with claim 1 wherein said one or more informational items is a text phrase.

3. A method in accordance with claim 2 wherein said radiological ontology is a radiological domain report ontology.

4. A method in accordance with claim 3, further comprising providing a status notification as said natural language processor processes said one or more informational items.

5. A method in accordance with claim 4 wherein said notification is provided in response to an event, and wherein said notification indicates that said hierarchical radiological report is completed.

6. A method in accordance with claim 4 wherein said notification is provided in response to an event, and wherein said notification indicates that said hierarchical radiological report is changing.

7. A method in accordance with claim 3, further comprising training said natural language processor utilizing said radiological domain report ontology.

8. A method in accordance with claim 3, further comprising providing an interface to external applications for receiving identification of said historical radiological data source and providing data from said hierarchical radiological report.

9. A method programmed in a computing environment for consulting and providing report information from a historical radiological report, the method comprising:

defining one or more aspects of radiology report information as concept properties represented by a vocabulary of one or more instances of a radiological domain ontology, said 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;

extracting from said historical radiological report an informational item of interest;

employing a natural language processor to identify a context that defines a set of said domain knowledge and the relationships among said set of domain knowledge to describe said informational item of interest;

validating said informational item is reportable radiological information and resides in said domain of knowledge;

identifying definitive concept of said informational item from within said domain of knowledge; and

classifying said informational item into a hierarchical report.

10. A method in accordance with claim 9 wherein said classifying step defines said informational item as a finding or finding characteristic.

11. A method in accordance with claim 9, further comprising validating that said informational item of interest is within a specific radiological report context as modeled by said radiological domain ontology.

12. A method in accordance with claim 9 wherein said informational item of interest is based on clinical information.

13. A method in accordance with claim 9 wherein said informational item of interest is based on patient demographic data.

14. A method in accordance with claim 9, further comprising providing a status notification as said information items are validated.

15. A method in accordance with claim 14 wherein said notification is provided in response to an event, and wherein said notification indicates that said hierarchical report is completed.

16. A method in accordance with claim 14 wherein said notification is provided in response to an event, and wherein said notification indicates that said hierarchical report is changing.

17. A method in accordance with claim 9, further comprising training said natural language processor utilizing said radiological domain ontology.

18. A method for providing a knowledge based report of historical breast imaging information to an application program, the method comprising:

interfacing the application program to a natural language processor;

accessing a historical radiological report file including breast imaging information;

said natural language processor employing a mammographic report ontology;

said natural language processor analyzing said historical radiological report file and categorizing said breast imaging information therein to create a new radiological report; and

providing the content of said new radiological report to the application program.

19. A computing system for providing radiological reporting utilizing a radiological report domain ontology in reference to a subject comprising:

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

means for receiving an informational report item of interest from a historical radiological report, wherein said informational report item of interest relates to said subject;

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

a validation module to determine that said informational report item of interest is radiological and resides in said radiological report domain knowledge;

an identification module to determine a definitive concept of said informational report item of interest from within said radiological report domain knowledge; and

a classification module for classifying said informational report item of interest as a finding or a finding characteristic within said radiological report domain knowledge; and

a report manager for providing said finding or said finding characteristic in a hierarchical radiological report.