Apparatus and method for interlocking lesion locations between a guide image and a 3D tomosynthesis images composed of a plurality of 3D image slices

1. A method of interlocking a lesion location between a guide image and 3D tomosynthesis images comprising a plurality of three dimensional (3D) image slices, the method comprising:

executing a program in response to generation of a pre-set trigger signal;

receiving, from a second server, a guide image which is a two dimensional (2D) medical image of a body part, and a plurality of 3D image slices constituting 3D tomosynthesis images of the body part;

simultaneously displaying the guide image showing a plurality of pieces of lesion information detected from the plurality of 3D image slices, and at least one 3D image slice included in the plurality of 3D image slices which shows a part of the plurality of pieces of lesion information;

in response to receiving a user input of selecting a piece of lesion information among the plurality of pieces of lesion information on the guide image, changing the at least one 3D image slice to a 3D image slice, among the plurality of 3D image slices, which has a highest lesion score for a lesion corresponding to the piece of lesion information,

wherein a lesion location is displayed on the 3D image slice and the guide image and interlocked between the 3D image slice and the guide image, and

wherein a lesion score for the lesion indicates a degree of confidence of an artificial intelligence (AI) model about the lesion being malignant in each 3D image slice.

2. The method of claim 1 , further comprising:

identifying the at least one 3D image slice that is a focus slice in which a particular lesion is most clearly visible from among the plurality of 3D image slices.

3. The method of claim 1 , wherein coordinate information of a region in which the piece of lesion information is displayed on the at least one 3D image slice corresponds to coordinate information of a region in which the piece of lesion information is displayed on the guide image.

4. The method of claim 1 , wherein

the displaying further comprises displaying a slice navigation tool in a display region of the 3D image slice, and

the method further comprises performing navigation for the 3D tomosynthesis images in a depth-wise direction based on a user input received on the slice navigation tool.

5. The method of claim 4 , wherein

the slice navigation tool comprises an indicator for identifying each of the plurality of 3D image slices, and

for each of the plurality of pieces of lesion information displayed on the guide image, identification information of a focus slice in which a corresponding lesion is most clearly visible from among the plurality of 3D image slices, and a lesion score of the corresponding lesion in the focus slide are displayed at a position corresponding to the indicator of the focus slice.

6. The method of claim 1 , further comprising:

enlarging a partial region of the at least one 3D image slice; and

changing the enlarged region to another 3D image slice in response to a user input of changing the enlarged region,

wherein the at least one 3D image slice is maintained in regions other than the enlarged region even if the enlarged region is changed.

7. The method of claim 1 , wherein

the displaying further comprises displaying a pre-stored medical image in response to selection of the piece of lesion information on the 3D image slice, and

the pre-stored medical image is obtained by an external medical imaging device.

8. The method of claim 1 , further comprising:

recording feedback notes in the guide image or the at least one 3D image slice based on a user input;

generating a separate single image by merging the feedback notes in the form of an overlay on the guide image or the at least one 3D image slice; and

transmitting the single image to a first server or the second server.

9. The method of claim 8 , further comprising

receiving and displaying updated 3D tomosynthesis images from the first server or the second server when the pre-set trigger signal is generated again,

wherein the updated 3D tomosynthesis images include the plurality of 3D image slices and the single image which are interlocked with each other.

10. An apparatus for interlocking a lesion location between a guide image and 3D tomosynthesis images comprising a plurality of 3D image slices, the apparatus comprising:

a memory in which at least one program is stored; and

at least one processor operated by executing the at least one program,

wherein the at least one processor is configured to

execute a program in response to generation of a pre-set trigger signal,

receive, from a second server, a guide image which is a 2D medical image of a body part, and a plurality of 3D image slices constituting 3D tomosynthesis images of the body part,

simultaneously display the guide image showing a plurality of pieces of lesion information detected from the plurality of 3D image slices, and at least one 3D image slice included in the plurality of 3D image slices; which shows a part of the plurality of pieces of lesion information, and

in response to receiving a user input of selecting a piece of lesion information among the plurality of pieces of lesion information on the guide image, change the at least one 3D image slice to a 3D image slice, among the plurality of 3D image slices, which has a highest lesion score for a lesion corresponding to the piece of lesion information,

wherein a lesion location is displayed on the 3D image slice and the guide image and interlocked between the at least one 3D image slice and the guide image, and

wherein a lesion score for the lesion indicates a degree of confidence of an artificial intelligence (AI) model about the lesion being malignant in each 3D image slice.

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