Lesion classification apparatus, and method of modifying lesion classification data

1. A method of changing lesion classification data, the method, performed at a lesion classification system including one or more processors, comprising:

determining, by the one or more processors, at least one mass which is included in an image of an object;

determining, by the one or more processors, whether the at least one mass corresponds to a lesion by using first data including at least one first information;

selecting, by the one or more processors, in response to a user input, a false negative (FN) mass from among the at least one mass, wherein the selected FN mass is a mass previously determined as not corresponding to a lesion, and the user input indicates that the selected FN mass corresponds to a lesion; and

changing, by the one or more processors, the first data to second data by using second information of the selected FN mass,

wherein the second data is used for determining whether the at least one mass corresponds to a lesion.

2. The method of claim 1 , wherein the changing comprises adding the second information to the first data.

3. The method of claim 1 , wherein the changing comprises deleting one of the at least one first information, and adding the second information to the first data.

4. The method of claim 1 , wherein the changing comprises determining whether to change the first data to the second data by comparing lesion classification performance of the first data with lesion classification performance of the second data.

5. The method of claim 1 , wherein the selecting of the FN mass comprises:

receiving a selection of a first region of the image; and

selecting a mass included in the first region as the FN mass.

6. The method of claim 5 , wherein the receiving of the selection comprises displaying a lesion probability of the selected mass included in the first region.

7. The method of claim 5 , wherein the selecting of the mass included in the first region comprises:

selecting one of a plurality of masses included in the first region as the FN mass, based on lesion probabilities of the plurality of masses.

8. The method of claim 5 , wherein the selecting of the FN mass further comprises:

determining a border of the FN mass; and

extracting the second information from the selected FN mass.

9. The method of claim 8 , wherein the determining of the border of the FN mass comprises:

determining the border of the FN mass based on the user input.

10. The method of claim 8 , wherein the determining of the border of the FN mass comprises:

determining the border of the FN mass by using a border extraction algorithm.

11. The method of claim 8 , wherein the determining of the border of the FN mass comprises:

changing brightness values of pixels included in the first region to a first brightness value or a second brightness value, based on a threshold brightness value; and

determining the border as outlined by the pixels changed to the first brightness value or the second brightness value using a border extraction algorithm.

12. The method of claim 1 , wherein the method of changing the lesion classification data is performed by a sparse representation (SR) lesion classification apparatus, and the first data includes a dictionary of the SR lesion classification apparatus.

13. A non-transitory computer-readable recording medium having recorded thereon a computer program for implementing the method of claim 1 .

14. A lesion classification system comprising:

one or more processors configured to:

determine at least one mass included in an image of an object;

determine whether the at least one mass corresponds to a lesion by using first data including at least one first information;

select, in response to a user input, a false negative (FN) mass from among the at least one mass, wherein the selected FN mass has been determined as not corresponding to the lesion and is determined as corresponding to the lesion; and

change the first data to a second data by using a second information of the FN mass,

wherein the second data is used for determination of the lesion.

15. The lesion classification system of claim 14 , wherein the one or more processors are configured to add the second information to the first data.

16. The lesion classification system of claim 14 , wherein the one or more processors are configured to delete one of the at least one first-information, and add the second information to the first data.

17. The lesion classification system of claim 14 , wherein the one or more processors are configured to determine whether to change the first data to the second data by comparing lesion classification performance of the first data with lesion classification performance of the second data.

18. The lesion classification system of claim 14 , wherein the lesion classification system further comprises a display configured to display the image,

wherein the one or more processors are configured to receive a selection of a first region of the image displayed in the display, and selects a mass included in the first region as the FN mass.

19. The lesion classification system of claim 18 , wherein the display is configured to display a lesion probability of the mass included in the first region to the user.