Devices, systems, and methods for labeling objects of interest during a medical procedure

A system, comprising:

• a display that receives a video signal to display video of a medical procedure being performed by a clinician;
• an eye tracking device that performs eye tracking of the clinician during the medical procedure to output eye tracking data;
• a memory including instructions;
• a processor that executes the instructions to:
• determine, based on the eye tracking data, that the clinician gazes at a sub-section of the display for more than a threshold amount of time during a first time period of the medical procedure;
• identify a block of the video signal that corresponds to the first time period;
• segment selected frame in the block of the video signal into a plurality of sub-regions;
• perform further processing on the plurality of sub-regions;
• and
• automatically identify an object of interest within the selected frame based on the further processing.

A method, comprising:

• determining, based on eye tracking data, that a clinician gazes at a sub-section of a display for more than a threshold amount of time during a first time period of a medical procedure, the display displaying video of the medical procedure according to a video signal;
• identifying a block of the video signal that corresponds to the first time period;
• segmenting selected frame in the block of the video signal into a plurality of sub-regions;
• performing further processing on the plurality of sub-regions;
• and
• automatically identifying an object of interest within the selected frame based on the further processing.