Methods and systems for using computer-vision to enhance surgical tool control during surgeries
The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.
1. A computer-implemented method comprising:
receiving one or more data streams, each of the one or more data streams having been generated at and received from an electronic device configured and positioned to capture live video within a field of view during a particular surgical procedure being performed using one or more surgical tools, the one or more data streams including a sequence of images of the live video within the field of view;
inputting the one or more data streams into a model trained to recognize surgical tools from image data;
in response to inputting the one or more data streams into the model, detecting a surgical tool from the sequence of images of the one or more data streams, the surgical tool configured to perform a plurality of functions, the plurality of functions including a first function and a second function different than the first function, the detection of the surgical tool being performed by utilizing the model to recognize the surgical tool from the sequence of images of the live video, and the detection of the surgical tool indicating that the surgical tool is within the field of view;
in response to detecting the surgical tool within the field of view, outputting a first set of commands for controlling the surgical tool to perform or to regulate performance of the first function; and
in response to detecting that the surgical tool is no longer within the field of view, outputting a second set of commands for controlling the surgical tool to cease or to regulate performance of the first function, and for controlling the surgical tool with respect to the second function.
2. The method of claim 1 , wherein controlling the surgical tool with respect to the second function comprises causing the surgical tool to perform or to regulate performance of the second function.
3. The method of claim 1 , wherein controlling the surgical tool with respect to the second function comprises causing the surgical tool to cease or to regulate performance of the second function.
4. The computer-implemented method of claim 1 , further comprising:
detecting an anatomical structure from the sequence of images of the live video, the anatomical structure being detected by utilizing the model to recognize the anatomical structure from the sequence of images;
in response to detecting the anatomical structure, determining whether the surgical tool is oriented in a specific articulation, position, or orientation in relation to the anatomical structure;
when the surgical tool is not in the specific articulation, position, or orientation in relation to the anatomical structure, automatically controlling the surgical tool to cease performing the first function or to regulate performance of the first function; and
when the surgical tool is in the specific articulation, position, or orientation in relation to the anatomical structure, automatically controlling the surgical tool to perform the first function or to regulate performance of the first function.
5. The computer-implemented method of claim 1 , further comprising:
detecting an anatomical structure from the sequence of images of the live video, the anatomical structure being detected by utilizing the model to recognize the anatomical structure from the sequence of images;
in response to detecting the anatomical structure, determining whether the surgical tool is oriented in a specific articulation, position, or orientation in relation to the anatomical structure;
when the surgical tool is not in the specific articulation, position, or orientation in relation to the anatomical structure, automatically controlling the surgical tool to perform the first function or to regulate performance of the first function; and
when the surgical tool is in the specific articulation, position, or orientation in relation to the anatomical structure, automatically controlling the surgical tool to cease performing the first function or to regulate performance of the first function.
6. The computer-implemented method of claim 1 , further comprising:
detecting an object from the sequence of images of the live video, the object being detected by utilizing the model to recognize the object from the sequence of images;
determining a distance between the surgical tool and the object;
comparing the determined distance to a threshold distance;
when the determined distance is greater than or equal to the threshold distance, automatically controlling the surgical tool to cease performing the first function or to regulate performance of the first function; and
when the determined distance is less than the threshold distance, automatically controlling the surgical tool to perform the first function or to regulate performance of the first function.
7. The computer-implemented method of claim 1 , further comprising:
detecting an object from the sequence of images of the live video, the object being detected by utilizing the model to recognize the object from the sequence of images;
determining a distance between the surgical tool and the object;
comparing the determined distance to a threshold distance;
when the determined distance is less the threshold distance, automatically controlling the surgical tool to cease performing the first function or to regulate performance of the first function; and
when the determined distance is greater than or equal to the threshold distance, automatically controlling the surgical tool to perform the first function or to regulate performance of the first function.
8. The computer-implemented method of claim 1 , further comprising:
identifying that the particular surgical procedure comprises a plurality of sequential phases;
determining that the first function is to be performed during a phase of the plurality of sequential phases of the particular surgical procedure;
detecting that the surgical procedure is in the phase of the plurality of sequential phases, the phase being detected by utilizing the model to recognize the phase from the sequence of images; and
in response to detecting that the surgical procedure is in the phase of the plurality of sequential phases, facilitating controlling the surgical tool to perform or to regulate performance of the first function.
9. The computer-implemented method of claim 1 , wherein outputting the first set of commands in response to detecting the surgical tool within the field of view includes controlling the surgical tool with respect to the second function to cease or to regulate performance of the second function.
10. A system, comprising:
one or more data processors; and
a non-transitory computer-readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform operations comprising:
receiving one or more data streams, each of the one or more data streams having been generated at and received from an electronic device configured and positioned to capture live video within a field of view during a particular surgical procedure being performed using one or more surgical tools, the one or more data streams including a sequence of images of the live video within the field of view;
inputting the one or more data streams into a model trained to recognize surgical tools from image data;
in response to inputting the one or more data streams into the model, detecting a surgical tool from the sequence of images of the one or more data streams, the surgical tool configured to perform a plurality of functions, the plurality of functions including a first function and a second function different than the first function, the detection of the surgical tool being performed by utilizing the model to recognize the surgical tool from the sequence of images of the live video, and the detection of the surgical tool indicating that the surgical tool is within the field of view;
in response to detecting the surgical tool within the field of view, outputting a first set of commands for controlling the surgical tool to perform or to regulate performance of the first function; and
in response to detecting that the surgical tool is no longer within the field of view, outputting a second set of commands for controlling the surgical tool to cease or to regulate performance of the first function, and for controlling the surgical tool with respect to the second function.
11. The system of claim 10 , wherein controlling the surgical tool with respect to the second function comprises causing the surgical tool to perform or to regulate performance of the second function.
12. The system of claim 10 , wherein controlling the surgical tool with respect to the second function comprises causing the surgical tool to cease or to regulate performance of the second function.
13. The system of claim 10 , wherein the operations further comprise:
detecting an anatomical structure from the sequence of images of the live video, the anatomical structure being detected by utilizing the model to recognize the anatomical structure from the sequence of images;
in response to detecting the anatomical structure, determining whether the surgical tool is oriented in a specific articulation, position, or orientation in relation to the anatomical structure;
when the surgical tool is not in the specific articulation, position, or orientation in relation to the anatomical structure, automatically controlling the surgical tool to cease performing the first function or to regulate performance of the first function; and
when the surgical tool is in the specific articulation, position, or orientation in relation to the anatomical structure, automatically controlling the surgical tool to perform the first function or to regulate performance of the first function.
14. The system of claim 10 , wherein the operations further comprise:
detecting an anatomical structure from the sequence of images of the live video, the anatomical structure being detected by utilizing the model to recognize the anatomical structure from the sequence of images;
in response to detecting the anatomical structure, determining whether the surgical tool is oriented in a specific articulation, position, or orientation in relation to the anatomical structure;
when the surgical tool is not in the specific articulation, position, or orientation in relation to the anatomical structure, automatically controlling the surgical tool to perform the first function or to regulate performance of the first function; and
when the surgical tool is in the specific articulation, position, or orientation in relation to the anatomical structure, automatically controlling the surgical tool to cease performing the first function or to regulate performance of the first function.
15. The system of claim 10 , wherein the operations further comprise:
detecting an object from the sequence of images of the live video, the object being detected by utilizing the model to recognize the object from the sequence of images;
determining a distance between the surgical tool and the object;
comparing the determined distance to a threshold distance;
when the determined distance is greater than or equal to the threshold distance, automatically controlling the surgical tool to cease performing the first function or to regulate performance of the first function; and
when the determined distance is less than the threshold distance, automatically controlling the surgical tool to perform the first function or to regulate performance of the first function.
16. The system of claim 10 , wherein the operations further comprise:
detecting an object from the sequence of images of the live video, the object being detected by utilizing the model to recognize the object from the sequence of images;
determining a distance between the surgical tool and the object;
comparing the determined distance to a threshold distance;
when the determined distance is less the threshold distance, automatically controlling the surgical tool to cease performing the first function or to regulate performance of the first function; and
when the determined distance is greater than or equal to the threshold distance, automatically controlling the surgical tool to perform the first function or to regulate performance of the first function.
17. The system of claim 10 , wherein the operations further comprise:
identifying that the particular surgical procedure comprises a plurality of sequential phases;
determining that the first function is to be performed during a phase of the plurality of sequential phases of the particular surgical procedure;
detecting that the surgical procedure is in the phase of the plurality of sequential phases, the phase being detected by utilizing the model to recognize the phase from the sequence of images; and
in response to detecting that the surgical procedure is in the phase of the plurality of sequential phases, facilitating controlling the surgical tool to perform or to regulate performance of the first function.
18. The system of claim 10 , wherein outputting the first set of commands in response to detecting the surgical tool within the field of view includes controlling the surgical tool with respect to the second function to cease or to regulate performance of the second function.
19. A computer program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause a data processing apparatus to perform operations comprising:
receiving one or more data streams, each of the one or more data streams having been generated at and received from an electronic device configured and positioned to capture live video within a field of view during a particular surgical procedure being performed using one or more surgical tools, the one or more data streams including a sequence of images of the live video within the field of view;
inputting the one or more data streams into a model trained to recognize surgical tools from image data;
in response to inputting the one or more data streams into the model, detecting a surgical tool from the sequence of images of the one or more data streams, the surgical tool configured to perform a plurality of functions, the plurality of functions including a first function and a second function different than the first function, the detection of the surgical tool being performed by utilizing the model to recognize the surgical tool from the sequence of images of the live video, and the detection of the surgical tool indicating that the surgical tool is within the field of view;
in response to detecting the surgical tool within the field of view, outputting a first set of commands for controlling the surgical tool to perform or to regulate performance of the first function; and
in response to detecting that the surgical tool is no longer within the field of view, outputting a second set of commands for controlling the surgical tool to cease or to regulate performance of the first function, and for controlling the surgical tool with respect to the second function.
20. The computer program product of claim 19 , wherein controlling the surgical tool with respect to the second function comprises causing the surgical tool to cease or to perform or to regulate performance of the second function.