Computer vision based control of an energy generator

A computer-implemented method for controlling an energy generator, the method includes:

• receiving image data of a surgical site and an electrosurgical instrument through an endoscope, the electrosurgical instrument including a pair of jaws;
• estimating an angle of the jaws based on the received image;
• determining a tissue type and a tissue thickness of tissue grasped by the pair of jaws based on the estimated angle;
• outputting radio frequency (RF) energy to the electrosurgical instrument from an energy generator;
• and
• controlling RF energy based on the determined thickness.

A computer-implemented method for controlling an energy generator, the method comprising:

• receiving image data of a surgical site and an electrosurgical instrument through an endoscope, wherein the electrosurgical instrument includes a pair of jaws and at least two fiducial markers, with one of the at least two fiducial markers disposed on one jaw of the pair of jaws;
• identifying the at least two fiducial markers within the image;
• based on identifying the at least two fiducial markers, estimating an initial jaw angle of the pair of jaws while grasping the tissue;
• performing an error correction on the initial estimate of the jaw angle using a machine learning network to generate a corrected estimate of the jaw angle;
• based on the corrected estimate of the jaw angle, determining a thickness of tissue grasped by the pair of jaws and at least one of tissue type or tissue conductivity based on the image;
• outputting radio frequency (RF) energy to the electrosurgical instrument from an energy generator;
• and
• controlling RF energy based on at least one of the determined thickness, tissue type, or tissue conductivity.