Computer-aided diagnosis method and apparatus

• US 9,760,689 B2
• Filed: 09/13/2013
• Issued: 09/12/2017
• Est. Priority Date: 11/16/2012
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Chang, Chu-Ho, Seong, Yeong-Kyeong
• Primary Examiner(s): Fitzpatrick, Atiba O
• Application Number:
  US14/026,509
• Publication Number:
  US 20140142413A1
• Time in Patent Office: 1,460 Days
• Field of Search: None
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

A computer-aided diagnosis (CAD) method includes extracting a lesion feature value of a lesion feature of a lesion from a captured lesion image; receiving additional information; and diagnosing the lesion based on a combination of the extracted lesion feature value and the received additional information.

Claims

1. A computer-aided diagnosis (CAD) method performed at a processor, the method comprising:

extracting at least one lesion feature value from a captured lesion image comprising at least one lesion;

receiving, at a user interface, at least one additional information comprising information needed to diagnose the at least one lesion based on the captured lesion image,

wherein the user interface comprises;

a lesion image display area configured to display the captured lesion image, and

an additional information input area configured to;

receive the at least one additional information,

display at least one additional information field for selection by a user, and

in response to one of the at least one additional information field being selected by the user, display at least one sub-field of the selected additional information field;

diagnosing the at least one lesion based on the extracted at least one lesion feature value and the received at least one additional information; and

displaying the captured lesion image,

wherein the at least one additional information, that is based on the captured lesion image, affects a diagnosis of the at least one lesion.

2. The CAD method of claim 1, wherein the diagnosing comprises:

comparing the extracted at least one lesion feature value and the received at least one additional information with a lesion diagnosis model; and

diagnosing the at least one lesion based on a result of the comparing.

3. The CAD method of claim 2, wherein the lesion diagnosis model is generated based on:

at least one lesion feature value extracted from previously captured lesion images; and

at least one additional information for the previously captured lesion images.

4. The CAD method of claim 3, wherein the lesion diagnosis model comprises:

at least one combination of the at least one lesion feature value extracted from the previously captured lesion images and the at least one additional information for the previously captured lesion images; and

at least one diagnosis result corresponding to the at least one combination.

5. The CAD method of claim 1, wherein the at least one additional information comprises at least one medical record and patient information that affect the diagnosis of the at least one lesion.

6. The CAD method of claim 1, wherein the additional information input area is further configured to display, if at least one of the extracted at least one lesion feature value is less than a reference value, at least one additional information field for at least one corresponding lesion feature.

7. The CAD method of claim 1, wherein the additional information input area is further configured to display at least one additional information field having a greater influence on the diagnosis of the at least one lesion differently from at least one additional information field having a lesser influence on the diagnosis of the at least one lesion.

8. The CAD method of claim 1, wherein the additional information input area is further configured to receive at least one text-type additional information from the user.

9. The CAD method of claim 1, wherein the additional information input area is further configured to receive at least one audio-type additional information from the user.

10. A computer-aided (CAD) apparatus comprising:

at least one processor configured to extract at least one lesion feature value from a captured lesion image comprising at least one lesion; and

an interface configured to receive at least one additional information comprising information about the at least one lesion based on the captured lesion image,

wherein the interface comprises a user interface comprising;

a lesion image display area configured to display the captured lesion image, and

an additional information input area configured to receive the at least one additional information, display at least one additional information field for selection by a user, and in response to one of the at least one additional information field being selected by the user, display at least one sub-field of the selected additional information field,

wherein the at least one processor is further configured to diagnose the at least one lesion based on the extracted at least one lesion feature value and the received at least one additional information, and

wherein the at least one additional information, that is based on the captured lesion image, affects a diagnosis of the at least one lesion.

11. The CAD apparatus of claim 10, further comprising a database configured to store a lesion diagnosis model,

wherein the at least one processor is further configured to:

compare the extracted at least one lesion feature value and the received at least one additional information with the lesion diagnosis model; and

diagnose the at least one lesion based on a result of the comparing.

12. The CAD apparatus of claim 11, wherein the lesion diagnosis model is generated based on:

at least one lesion feature value extracted from previously captured lesion images; and

at least one additional information for the previously captured lesion images.

13. The CAD apparatus of claim 12, wherein the lesion diagnosis model comprises:

at least one combination of the at least one lesion feature value extracted from the previously captured lesion images and the at least one additional information for the previously captured lesion images; and

at least one diagnosis result corresponding to the at least one combination.

14. The CAD apparatus of claim 10, wherein the at least one additional information comprises at least one medical record and patient information that affect the diagnosis of the at least one lesion.

15. The CAD apparatus of claim 10, wherein the user interface is further configured to display, if at least one of the extracted at least one lesion feature value is less than a reference value, at least one additional information field for at least one corresponding lesion feature.

16. The CAD apparatus of claim 10, wherein the user interface is further configured to display at least one additional information field having a greater influence on the diagnosis of the at least one lesion differently from at least one additional information field having a lesser influence on the diagnosis of the at least one lesion.

17. The CAD apparatus of claim 10, wherein the additional information input area is further configured to receive at least one of text-type additional information and audio-type additional information from the user.

18. A method of generating a lesion diagnosis model, the method comprising:

extracting at least one lesion feature value from each of captured lesion images;

receiving, by a user interface, at least one additional information comprising information about the at least one lesion for each of the captured lesion images,

wherein the user interface comprises;

a lesion image display area configured to display at least one of the captured lesion images, and

an additional information input area configured to receive the at least one additional information, display at least one additional information field for selection by a user, and in response to one of the at least one additional information field being selected by the user, display at least one sub-field of the selected additional information field;

generating a lesion diagnosis model based on at least one combination of the at least one lesion feature value and the at least one additional information, and at least one diagnosis result corresponding to the at least one combination; and

storing the generated lesion diagnosis model in a database,

wherein the at least one additional information, that is based on the captured lesion image, affects a diagnosis of the at least one lesion.

19. The method of claim 18,

wherein each of the at least one combination comprises at least one lesion feature value and at least one additional information, and

wherein each of the at least one diagnosis result corresponds to at least one of the at least one combination.

20. The method of claim 18, wherein the at least one additional information comprises information about at least one lesion feature from which the at least one lesion feature value is extracted.

21. The method of claim 20, wherein the at least one additional information further comprises at least one medical record and patient information affecting the diagnosis of the at least one lesion from which the at least one lesion feature value is extracted.

22. The method of claim 18,

wherein the receiving comprises receiving the at least one additional information from the user, and

wherein the at least one diagnosis result corresponding to the at least one combination is determined by the user based on the captured lesion images.