Back to results
US 10,758,309 B1Granted
Methods and systems for using computer-vision to enhance surgical tool control during surgeries
AssigneeDigital Surgery Limited
InventorsAndre Chow, Danail Stoyanov, Imanol Luengo Muntion, Petros Giataganas, Jean Nehme
Life of this patent
Estimating the term…
Abstract
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.
Claims17
A computer-implemented method comprising:
- collecting a data set including a plurality of images, each image of the plurality of images capturing a portion of a surgical procedure, and the portion of the surgical procedure being performed using a surgical tool;
- training a model using the data set, the model being trained to recognize surgical tools from image data by inputting the data set into one or more machine-learning algorithms;
- 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, and 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 the trained model;
- in response to inputting the one or more data streams into the trained model, detecting a surgical tool from the sequence of images of the one or more data streams, the surgical tool being configured to perform a primary 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 one or more commands for controlling the surgical tool to perform the primary function, the detection of the surgical tool from the sequence of images of the live video causing the surgical tool to be enabled to perform the primary function, wherein detecting that the surgical tool is no longer within the field of view causes the surgical tool to cease or regulate performance of the primary function;
- and
- the surgical tool is configured to perform a plurality of functions, wherein the plurality of functions includes the primary function and a secondary function, wherein the primary function is different from the secondary function, and wherein detecting that the surgical tool is no longer within the field of view of the electronic device causes the surgical tool to be enabled to perform the secondary function.
6 more elements
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 including:
- collecting a data set including a plurality of images, each image of the plurality of images capturing a portion of a surgical procedure, and the portion of the surgical procedure being performed using a surgical tool;
- training a model using the data set, the model being trained to recognize surgical tools from image data by inputting the data set into one or more machine-learning algorithms;
- 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, and 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 the trained model;
- in response to inputting the one or more data streams into the trained model, detecting a surgical tool from the sequence of images of the one or more data streams, the surgical tool being configured to perform a primary 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 one or more commands for controlling the surgical tool to perform the primary function, the detection of the surgical tool from the sequence of images of the live video causing the surgical tool to be enabled to perform the primary function, wherein detecting that the surgical tool is no longer within the field of view causes the surgical tool to cease or regulate performance of the primary function;
- and
- the surgical tool is configured to perform a plurality of functions, wherein the plurality of functions includes the primary function and a secondary function, wherein the primary function is different from the secondary function, and wherein detecting that the surgical tool is no longer within the field of view of the electronic device causes the surgical tool to be enabled to perform the secondary function.
8 more elements
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 including:
- collecting a data set including a plurality of images, each image of the plurality of images capturing a portion of a surgical procedure, and the portion of the surgical procedure being performed using a surgical tool;
- training a model using the data set, the model being trained to recognize surgical tools from image data by inputting the data set into one or more machine-learning algorithms;
- 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, and 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 the trained model;
- in response to inputting the one or more data streams into the trained model, detecting a surgical tool from the sequence of images of the one or more data streams, the surgical tool being configured to perform a primary 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 one or more commands for controlling the surgical tool to perform the primary function, the detection of the surgical tool from the sequence of images of the live video causing the surgical tool to be enabled to perform the primary function, wherein detecting that the surgical tool is no longer within the field of view causes the surgical tool to cease or regulate performance of the primary function;
- and
- the surgical tool is configured to perform a plurality of functions, wherein the plurality of functions includes the primary function and a secondary function, wherein the primary function is different from the secondary function, and wherein detecting that the surgical tool is no longer within the field of view of the electronic device causes the surgical tool to be enabled to perform the secondary function.
6 more elements
Dependencies are inferred from the claim text.