System and method for dynamic growing of a patient database with cases demonstrating special characteristics

Patent metadata

Field	Value
Publication number	US-9798778-B2
Application number	US-201113880200-A
Country	US
Kind code	B2
Filing date	Oct 11, 2011
Priority date	Oct 19, 2010
Publication date	Oct 24, 2017
Grant date	Oct 24, 2017

Abstract

A system and method for context-dependent data filtering for clinical decision support are disclosed. The system and method comprise determining values for characteristics of a present case, determining whether the present case is a special case based on the determined values, receiving input from a user verifying that the present case is the special case and saving the present case to a database containing a compilation of cases if the user verifies that the present case is the special case.

First claim

What is claimed is:

1. A method, comprising:
receiving, by a user interface, criteria for determining whether a present case is a special case, the criteria comprising qualitative characteristics and quantitative values corresponding to at least some of the qualitative characteristics,
wherein the present case comprises at least one medical image;

determining, by a computer processor, at least one quantitative value corresponding to at least one qualitative characteristic of the present case,
wherein the at least one qualitative characteristic of the present case relates to at least one morphological feature of the at least one medical image, and the at least one quantitative value relates to at least one measurement of the at least one morphological feature;

determining, by the computer processor, whether the present case is the special case by:
comparing the at least one qualitative characteristic and determined at least one quantitative value of the present case to the criteria, and
comparing the determined at least one quantitative value to a statistical significance threshold,
wherein the statistical significance threshold comprises a predetermined value;

receiving input from the user verifying that the present case is the special case; and
when the user verifies that the present case is the special case, saving the present case, including contents of the present case, to a database containing a compilation of cases, the database comprising an individualized database and a general database,
wherein the present case is saved to the individualized database only when the at least one qualitative characteristic and determined at least one quantitative value match or exceed the criteria,
wherein the present case is saved to the general database only when the determined at least one quantitative value matches or exceeds the statistical significance threshold.

2. The method of claim 1 , further comprising:
updating the database to reflect the addition of the present case.

3. The method of claim 2 , wherein the updating includes one of updating statistical values of the compilation of cases and applying machine learning techniques to reflect the values of the present case.

4. The method of claim 1 , wherein the present case includes a medical image, the medical image being stored in a separate database, wherein the medical image may be retrieved from the separate database based on one of the calculated values and patient information.

5. The method of claim 1 , further comprising:
selecting the characteristics of the present case, the selection including one of morphological and non-morphological characteristics for a medical image.

6. The method of claim 5 , further comprising:
calculating, when the selected characteristic is a shape of a lesion in the medical image, a distance from each voxel on a surface of the lesion to a center of the lesion; and
determining, when the selected characteristic is an enhancement characteristic of a lesion, a rim of the lesion by finding a boundary of the lesion and identifying heterogeneous regions inside the lesion.

7. The method of claim 1 , further comprising:
retrieving at least one case from the compilation of cases based on the determined quantitative values and patient information of the present case compared with the quantitative values and patient information of each of the compilation of cases.

8. The method of claim 1 , wherein the determining whether the present case is the special case further includes one of analyzing statistical criteria of the determined values, analyzing statistical criteria of the compilation of cases in the database and applying machine learning techniques to the present case and the compilation of cases.

9. A system, comprising:
a non-transitory memory storing an individualized database comprising a compilation of cases and a general database comprising a compilation of cases; and
a processing device
receiving criteria for determining whether a present case is a special case, the criteria comprising qualitative characteristics and quantitative values corresponding to at least some of the qualitative characteristics,
wherein the present case comprises at least one medical image;

determining at least one quantitative value corresponding to at least one qualitative characteristic of the present case,
wherein the at least one qualitative characteristic of the present case relates to at least one morphological feature of the at least one medical image, and the at least one quantitative value relates to at least one measurement of the at least one morphological feature;

determining whether the present case is the special case by comparing the at least one qualitative characteristic and determined at least one quantitative value of the present case to the criteria, and comparing the determined at least one quantitative value to a statistical significance threshold,
wherein the statistical significance threshold comprises a predetermined value;

receiving input from the user verifying the present case is the special case and, when the user verifies that the present case is the special case, saving the present case, including contents of the present case, to the non-transitory memory,
wherein the present case is saved to the individualized database only when the at least one qualitative characteristic and determined at least one quantitative value match or exceed the criteria,
wherein the present case is saved to the general database only when the determined at least one quantitative value matches or exceeds the statistical significance threshold.

10. The system of claim 9 , further comprising:
a further non-transitory memory storing a plurality of medical images, wherein the present case includes a medical image, the medical image being stored in the further non-transitory memory, wherein the medical image may be retrieved from the further non-transitory memory based on one of the calculated values and patient information.

11. The system of claim 10 , wherein the further non-transitory memory comprises one of a radiology information system, a hospital information system, and a picture archiving and communication system.

12. The system of claim 9 , wherein the processing device further receives a selection of the characteristics of the present case, the selection including one of morphological and non-morphological characteristics of a medical image.

13. The system of claim 12 , wherein the processing device calculates, when the selected characteristic is a shape of a lesion in the medical image, a distance from each voxel on a surface of the lesion to a center of the lesion, the processor further calculating, when the selected characteristic is an enhancement characteristic of a lesion, a rim of the lesion by finding a boundary of the lesion and identifying heterogeneous regions inside the lesion.

14. The system of claim 9 , wherein the processing device further retrieves at least one case from the compilation of cases based on the determined quantitative values and patient information of the present case compared with the quantitative values and patient information of each of the compilation of cases.

15. The system of claim 9 , wherein the processing device, when determining whether the present case is the special case, performs one of analyzing statistical criteria of the determined values, analyzing statistical criteria of the compilation of cases in the database and applying machine learning techniques to the present case and the compilation of cases.

Assignees

• Xu Ye
• Boroczky Lilla
• Simpson Mark
• Koninklijke Philips Nv

Inventors

• Xu Ye
• Boroczky Lilla
• Simpson Mark

Classifications

• G06T7/0014

  using an image reference approach · CPC title

• G06F19/3443

  Physics · mapped topic

• G06F17/3053 Primary

  Physics · mapped topic

• G16H50/70 Primary

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

• G06F16/24578 Primary

  using ranking · CPC title