Context driven summary view of radiology findings

Patent metadata

Field	Value
Publication number	US-11289188-B2
Application number	US-201414769480-A
Country	US
Kind code	B2
Filing date	Mar 24, 2014
Priority date	Mar 29, 2013
Publication date	Mar 29, 2022
Grant date	Mar 29, 2022

Abstract

A system, method and computer readable storage medium for generating a context driven summary view of medical findings by retrieving a current study including at least one image to be analyzed, extracting current context information from the current study and storing the current context information in a database and matching the current context information with prior context information from prior studies to return a set of relevant prior studies.

First claim

What is claimed is:

1. A method for using macros related to a current medical study of a patient with steps executable by a processor, the steps comprising:
retrieving the current medical study of the patient including at least one image to be analyzed;
extracting current context information from the current medical study and storing the current context information in a database;
comparing the stored current context information to prior context information from prior studies and matching the current context information with prior context information from prior studies to identify a minimum set of findings required to be reported in the current study, the minimum set of findings including the most recent prior studies of the patient;
extracting macro context information from available macros, wherein each macro comprises predefined text which may be inserted into the current medical study;
matching the macro context information with the context information of the prior relevant studies to generate a list of relevant macros associated with the minimum set of findings required to be reported in the current study, wherein the matching the macro context information with the context information includes an ontological approach;
displaying the generated list of relevant macros in order of relevance wherein the most relevant macro is highlighted; and
inserting the predefined text of the highlighted macro into the current medical study of the patient in response to a user selection; wherein the user selection is made via a user interface and comprises one or more of the relevant macros.

2. The method of claim 1 , further comprising:
displaying a summary view of the set of relevant prior studies including finding related information for each of the relevant prior studies.

3. The method of claim 1 , further comprising:
filtering the summary view based on a user preference.

4. The method of claim 3 , wherein filtering the summary view includes one of modifying a current context, identifying a type of lesion, identifying a time period within which displayed prior studies should fall and indicating a number of prior studies to be shown.

5. The method of claim 1 , further comprising:
analyzing images of prior studies to identify and store the finding related information.

6. The method of claim 5 , wherein the finding related information includes one of an observation describing the finding and an annotation on an image associated with the observation.

7. The method of claim 6 , wherein the displayed summary view shows one of observations and key images related to a finding of each prior relevant study.

8. The method of claim 1 , wherein matching the current context information with the prior context information includes at least one of a rule based approach, an ontology approach and a data driven approach.

9. The method of claim 1 , further comprising:
selecting finding related information of one of the relevant prior studies to display further information corresponding to the selected prior relevant study.

10. A non-transitory computer readable storage medium with an executable program stored thereon, wherein the program instructs a processor to perform a method as defined in claim 1 .

11. A system for suggesting macros related to a current medical study of a patient, comprising:
a processor configured for
retrieving the current medical study of the patient including at least one image to be analyzed, extracting current context information from the current medical study and matching the current context information with prior context information from prior studies to identify a minimum set of findings required to be reported in the current study, the minimum set of findings including the most recent prior studies of the patient;
extracting macro context information from available macros;
comparing the stored current context information to prior context information from prior studies and matching the macro context information with the context information of the prior relevant studies to generate a list of relevant macros associated with the minimum set of findings required to be reported in the current study, wherein the matching the macro context information with the context information includes an ontological approach, a rule-based approach, a data driven approach which executes data mining algorithms for determining prior relevant studies, or a combination thereof,
displaying, on a display, the generated list of relevant macros in order of relevance wherein the most relevant macro is highlighted; and
using the highlighted macro in the current medical study of the patient in response to a user selection; wherein the user selection is made via a user interface and comprises one or more of the relevant macros; and
a memory storing the current and prior context information in a database.

12. A method for suggesting macros or text fragments related to a current medical study of a patient, comprising:
retrieving the current medical study of the patient including at least one image to be analyzed;
extracting current context information from the current medical study and storing the current context information in a database;
comparing the stored current context information to prior context information from prior studies and matching the current context information with prior context information from prior studies to identify a minimum set of findings required to be reported in the current study, the minimum set of findings including the most recent prior studies of the patient;
identifying and listing macros or text fragments used in the relevant prior studies, wherein the identifying and listing macros or text fragments includes an ontological approach; and
displaying, on a display, the list of macros or text fragments associated with the minimum set of findings required to be reported in the current study in order of relevance wherein the most relevant macro or text fragment is highlighted; and
using the highlighted macro or text fragment for the current medical study of the patient in response to a user selection; wherein the user selection is made via a user interface and comprises one or more of the relevant macros, automatically populating relevant fields related to a medical finding in the current medical study based on a finding from a prior study.

13. A system for suggesting macros or text fragments related to a current medical study of a patient, comprising:
a processor configured for
retrieving the current medical study of the patient including at least one image to be analyzed,
extracting current context information from the current medical study with natural language processing;
comparing the stored current context information to prior context information from prior studies and matching the current context information with prior context information from prior studies to identify a minimum set of findings required to be reported in the current study, the minimum set of findings including the most recent prior studies of the patient,
identifying and listing macros or text fragments used in the relevant prior studies, wherein the identifying and listing macros or text fragments includes an ontological approach; and
displaying, on a display device, the list of macros or text fragments associated with the minimum set of findings required to be reported in the current study in order of relevance wherein the most relevant macro or text fragment is highlighted, wherein the displayed list of macros or text fragments are selectable by the user; and
using the highlighted macro or text fragment for the current medical study of the patient in r

Assignees

• Koninklijke Philips Nv

Inventors

• Mabotuwana Thusitha Dananjaya De Silva
• Xu Ye
• Qian Yuechen
• Mankovich Gabriel Ryan

Classifications

• G06T7/0014

  using an image reference approach · CPC title

• G16H30/40

  for processing medical images, e.g. editing · CPC title

• G16H15/00

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

• G16H50/70

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• G16H30/20 Primary

  for handling medical images, e.g. DICOM, HL7 or PACS · CPC title