Method and program for providing feedback on surgical outcome

1. A device for providing a feedback on a surgical outcome based on artificial intelligence, comprising:

an image sensor configured to capture a surgical image of an actual surgical process; and

a processor configured to:

generate actual surgical data based on the surgical image,

divide the actual surgical data into a plurality of detailed surgical operations to obtain actual surgical cue sheet data composed of the plurality of detailed surgical operations,

obtain reference cue sheet data about the actual surgery, and

provide feedback by comparing the actual surgical cue sheet data with the reference cue sheet data,

wherein the reference cue sheet data includes at least one of optimized cue sheet data about the actual surgery and referenced virtual surgical cue sheet data,

wherein the optimized cue sheet data includes cue sheet data calculated by an optimized surgical process by learning one or more cue sheet data, and

wherein the reference cue sheet data includes cue sheet data for virtual surgery or actual surgery performed for constructing big data for learning or guiding a surgical process.

2. The device of claim 1 , wherein the actual surgical data is divided into the plurality of detailed surgical operations, based on at least one of a surgery target portion, a type of surgical tool, a number of surgical tools, a position of the surgical tool, an orientation of the surgical tool, and movement of the surgical tool included in the actual surgical data.

3. The device of claim 1 , wherein at least one of a standardized name and standardized code data is assigned to each of the plurality of detailed surgical operations.

4. The device of claim 1 , wherein the processor is further configure to determine whether at least one surgical error is included in the actual surgical cue sheet data by comparing the plurality of detailed surgical operations included in the actual surgical cue sheet data with a plurality of detailed surgical operations included in the reference cue sheet data, and

wherein the at least one surgical error includes at least one of an unnecessary detailed surgical operation, a missing detailed surgical operation, and an incorrect detailed surgical operation.

5. The device of claim 4 , wherein the processor is further configured to determine whether a detailed surgical operation included in the actual surgical cue sheet data is incorrect by comparing motion of surgical tool corresponding to a detailed surgical operation included in the reference cue sheet data with motion of surgical tool corresponding to the detailed surgical operation included in the actual surgical cue sheet data.

6. The device of claim 1 , wherein the processor is further configured to:

detect an occurrence of an event from the actual surgical data,

determine a cause of the event by analyzing a detailed surgical operation before occurring the event included in the actual surgical cue sheet data, and

wherein the event includes at least one of bleeding information, foreign object information and nerve damage information.

7. The device of claim 1 , wherein the processor is further configured to obtain optimized cue sheet data for each situation classified according to a physical condition and a surgical target portion condition when obtaining the reference cue sheet data.

8. The device of claim 1 , wherein the processor is further configured to:

add the actual surgical cue sheet data to to-be-learned cue sheet data, and

perform reinforcement learning on a model for the obtaining optimized cue sheet data using the to-be-learned cue sheet data.

9. The device claim 1 , wherein the processor is further configured to:

obtain information about prognosis corresponding to each of one or more actual surgical cue sheet data including the actual surgical cue sheet data,

perform reinforcement learning based on information about the one or more actual surgical cue sheet data and the prognosis, and

determine a correlation between at least one detailed surgical operation included in the one or more actual surgical cue sheet data and the prognosis based on a result of the reinforcement learning.

10. The device claim 1 , further comprising:

a display; and

wherein the processor is further configured to:

extract a first image of one or more detailed surgical operation corresponding to a situation of surgical error or a second image of one or more detailed surgical operation including a situation of event, and

play the first image or the second image through the display.

11. A method for providing a feedback on a surgical outcome based on artificial intelligence, performed by a device, the method comprising:

capturing, by an image sensor of the device, a surgical image of an actual surgical process;

generating, by a processor of the device, actual surgical data based on the surgical image;

dividing, by the processor, the actual surgical data into a plurality of detailed surgical operations to obtain actual surgical cue sheet data composed of the plurality of detailed surgical operations;

obtaining, by the processor, reference cue sheet data about the actual surgery; and

providing, by the processor, feedback by comparing the actual surgical cue sheet data with the reference cue sheet data,

wherein the reference cue sheet data includes at least one of optimized cue sheet data about the actual surgery and referenced virtual surgical cue sheet data,

wherein the optimized cue sheet data includes cue sheet data calculated by an optimized surgical process by learning one or more cue sheet data, and

wherein the reference cue sheet data includes cue sheet data for virtual surgery or actual surgery performed for constructing big data for learning or guiding a surgical process.