Abstract: An aspect includes a computer-implemented method that accesses input data including spatial data and/or sensor data temporally associated with a video stream of a surgical procedure. One or more machine-learning models predict a state of the surgical procedure based on the input data. The one or more machine-learning models detect one or more surgical instruments at least partially depicted in the video stream based on the input data. A state indicator and one or more surgical instrument indicators temporally correlated with the video stream are output. A first surgical instrument of the one or more surgical instruments is identified in the video stream, and a motion profile of the first surgical instrument is determined.

Abstract: Data captured during a surgical procedure can include multiple video streams, such as from an endoscopic camera, an external camera, etc., along with data from one or more instruments used during the surgical procedure. Transferring the surgical data over communication networks, and storing the surgical data, is therefore resource-intensive, and a technical challenge. Technical solutions are described to optimize the surgical data by intelligent compression methods that can adaptively reduce the size of certain procedural workflows. In some aspects, the compression reduces the storage/transmission resources required for a video catalogue by reducing redundancy from across the several videos stored in the video catalogue. The compression also enables faster querying and searching through a catalogue or collection of archived data.

Abstract: An aspect includes a computer-implemented method that predicts a proposed region of interest in an image from a video of a surgical procedure based on one or more contextual targets. An image adjustment is synthesized based on the proposed region of interest and the image. A modified visualization of the surgical procedure is generated by incorporating the image adjustment in a real-time output of the video of the surgical procedure. The video of the surgical procedure is displayed with the modified visualization.

Abstract: A surgical action to be performed during a surgical procedure is predicted using machine learning based on images and surgical instrumentation data. An image/video capture device such as an endoscope, a wearable camera, a stationary camera, etc., can be used to capture the image(s). A surgeon can be provided an augmented visualization of the surgical procedure by displaying one or more graphical overlays based on the findings of the machine learning to enhance the surgeon's information.

Abstract: An aspect includes a computer-implemented method that quantifies variations in surgical approaches to medical procedures. Surgical videos documenting multiple cases of a medical procedure are analyzed to identify variations in surgical approaches used by service providers when performing the medical procedure. According to some aspects, the variation in surgical approaches is quantified.

Abstract: A location of an anatomical structure in image(s) from a surgical procedure is predicted using machine learning. An image/video capture device such as an endoscope, a wearable camera, a stationary camera, etc., can be used to capture the image(s). A confidence score of the prediction of the machine learning is determined. A surgeon can be provided an augmented visualization of the surgical procedure by displaying one or more graphical overlays based on the findings of the machine learning to enhance the surgeon-s information.

Abstract: An aspect includes a computer-implemented method that accesses input data including spatial data and/or sensor data temporally associated with a video stream of a surgical procedure. One or more machine-learning models predict a state of the surgical procedure based on the input data. The one or more machine-learning models detect one or more surgical instruments at least partially depicted in the video stream based on the input data. A state indicator and one or more surgical instrument indicators temporally correlated with the video stream are output.

Abstract: An aspect includes a computer-implemented method that identifies variations in surgical approaches to medical procedures. Surgical videos documenting multiple cases of a medical procedure are analyzed to identify different surgical approaches used by service providers when performing the medical procedure. According to some aspects surgical phases are identified in each surgical video and groups of similar surgical phase sequences are grouped into surgical approaches.

Abstract: Aspects include low latency video capture and overlay through video capture circuitry. Video input associated with a surgical procedure can be provided to one or more processing devices of a video processing system to analyze the video input. An overlay received from the one or more processing devices is combined with the video input to create a blended video output of the surgical procedure. The blended video output is output to a primary display using an interface having a lower latency than a secondary display output of the video processing system.

Abstract: Techniques are described for improving computer-assisted surgical (CAS) systems, particularly, to recognize surgical phases in a video of a surgical procedure. A CAS system includes cameras that provide video stream of a surgical procedure. According to one or more aspects the surgical phases are automatically detected in the video stream using a machine learning model. Particularly, the machine learning model includes a boundary aware cascade stage network to perform surgical phase recognition.

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.

Abstract: An aspect includes a computer-implemented method that de-identifies data received from microphones. The method includes receiving data from one or more microphones and de-identifying the data. The de-identifying includes inputting the data into a machine learning system that has been trained to detect patterns in the data that are likely to identify a specific entity, and to remove the detected patterns from the data to generate de-identified data. An output from the machine learning system is received, where the output includes the de-identified data. According to some aspects, the microphones can be located in an operating room.

Abstract: The present disclosure relates to processing data streams from a surgical procedure using multiple interconnected data structures to generate and/or continuously update an electronic output. Each surgical data structure is used to determine a current node associated with a characteristic of a surgical procedure and present relevant metadata associated with the surgical procedure. Each surgical data structure includes at least one node interconnected to one or more nodes of another data structure. The interconnected nodes between one or more data structures includes relational metadata associated with the surgical procedure.

Abstract: In some embodiments, methods and systems are provided for accessing a surgical dataset including surgical data collected during performance of a surgical procedure. The surgical data can include video data of the surgical procedure. Using the surgical data, a plurality of procedural states associated with the surgical procedure can be determined. For a procedural state of the plurality of procedural states, temporal information can be identified that identifies a part of the video data to be associated with the procedural state. For the procedural state of the plurality of procedural states, electronic data can be generated that characterizes the part of the video data and outputting the electronic data associated with the plurality of procedural states.