Abstract: Systems and methods for automatic detection of surgical specialty type and procedure type are disclosed. One or more classification networks may be applied to automatically process input surgical image data in order to recognize and determine a surgical specialty type and a surgical procedure type depicted in the input image data. Based on the determination made by the system, one or more output indications may be generated and one or more surgical devices may be automatically controlled, such as by being optimized for use during the surgical procedure type and/or surgical specialty type represented by the input image.

Abstract: Systems and methods for detecting, characterizing, and addressing surgical smoke are disclosed. In some embodiments, a surgical system receives image data representing an image of a surgical environment and generates sets of values based on the received image. The sets of values may include representations of atmospheric light in the image and representations of contrast values in the image. The system may determine from the sets of values whether predetermined smoke severity criteria are met, and may responsively automatically engage and/or disengage one or more surgical devices, such as a surgical smoke evacuation system and/or an image processing system (e.g., a video enhancement feature) configured to improve quality of smoky surgical images.

Abstract: An imaging system for viewing a surgical site, the imaging system including a system controller configured to: receive and process video images of the surgical site captured by an endoscopic camera coupled to an endoscope to detect at least one video signature corresponding to at least one condition that interferes with a quality of the video images; and in response to detecting the at least one video signature corresponding to the at least one condition that interferes with the quality of the video images, control a fluid system to clean a tip of the endoscope based on at least one learned preference that was learned by the system controller from user action over time

Abstract: Systems and methods for detecting, characterizing, and addressing surgical smoke are disclosed. In some embodiments, a surgical system receives image data representing an image of a surgical environment and generates sets of values based on the received image. The sets of values may include representations of atmospheric light in the image and representations of contrast values in the image. The system may determine from the sets of values whether predetermined smoke severity criteria are met, and may responsively automatically engage and/or disengage one or more surgical devices, such as a surgical smoke evacuation system and/or an image processing system (e.g., a video enhancement feature) configured to improve quality of smoky surgical images.

Abstract: A surgical system for providing an improved video image of a surgical site including a system controller that receives and processes video images to determine a video signature corresponding to a condition that interferes with a quality of the video images, with the system controller interacting with a video enhancer to enhance the video images from a video capturing device to automatically control the video enhancer to enhance the video images. The surgical system can also review the video images for a trigger event and automatically begin or stop recording of the video images upon occurrence of the trigger event.

Abstract: Systems, methods, and computer readable storage medium techniques for masking endoscopic images are disclosed. A system receives an input digital image and applies one or more denoising algorithms and one or more contour detection algorithms to detect a plurality of contours in the image. A contour having the largest area is identified. A smallest circular area enclosing the largest area contour is estimated, and a mask is applied to the image based on the circular area to generate a masked image.

Abstract: A data processing system accesses a digital resource that includes a plurality of sections and a classifier configured to detect contents representing one or more portions of a communication with increased likelihood of being cited as evidence associated with a particular one of the sections. The data processing system receives a stream of data items representing a communication and generates content for at least one of the sections. The data processing system parses one or more fields in the data items, extracts values from the one or more parsed fields, identifies, by the classifier, that the extracted values are represented in one or more portions of the contents representing the one or more portions of the communication with increased likelihood of being cited as evidence, identifies that the extracted values are associated with a particular section of the digital resource, and generates content for that particular section.

Abstract: Systems and methods for automatic detection of surgical specialty type and procedure type are disclosed. One or more classification networks may be applied to automatically process input surgical image data in order to recognize and determine a surgical specialty type and a surgical procedure type depicted in the input image data. Based on the determination made by the system, one or more output indications may be generated and one or more surgical devices may be automatically controlled, such as by being optimized for use during the surgical procedure type and/or surgical specialty type represented by the input image.

Abstract: Systems and methods for detecting, characterizing, and addressing surgical smoke are disclosed. In some embodiments, a surgical system receives image data representing an image of a surgical environment and generates sets of values based on the received image. The sets of values may include representations of atmospheric light in the image and representations of contrast values in the image. The system may determine from the sets of values whether predetermined smoke severity criteria are met, and may responsively automatically engage and/or disengage one or more surgical devices, such as a surgical smoke evacuation system and/or an image processing system (e.g., a video enhancement feature) configured to improve quality of smoky surgical images.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to facilitating corpus-based content generation, in particular, using graph-based multi-sentence compression to generate a final content output. In one embodiment, pre-existing source content is identified and retrieved from a corpus. The source content is then parsed into sentence tokens, mapped and weighted. The sentence tokens are further parsed into word tokens and weighted. The mapped word tokens are then compressed into candidate sentences to be used in a final content. The final content is assembled using ranked candidate sentences, such that the final content is organized to reduce information redundancy and optimize content cohesion.

Abstract: Embodiments are disclosed for bundling and arranging online content fragments for presentation based on content-specific metrics and inter-content constraints. For example, a content management application accesses candidate content fragments, a content-specific metric, and an inter-content constraint. The content management application computes minimum and maximum contribution values for the candidate content fragments. The content management application selects, based on the computed minimum and maximum contribution values, a subset of the candidate content fragments. The content management application applies, subject to the inter-content constraint, a bundle-selection function to the selected candidate content fragments and thereby identifies a bundle of online content fragments. The content management application outputs the identified bundle of online content fragments for presentation via an online service.

Abstract: The present invention provides a method for predicting occurrence of a chronic diseases in a patient at an early stage using a trained Deep Neural Network (DNN) using the patient's routine or preventive pathological test result data. The invention collects the past routine/preventive laboratory test results diagnosed with the chronic disease and trained a DNN using the labelled data. The embodiment of present invention that warning or predicting of a chronic disease in a patient comprising the steps of Collecting the patient's historical routine/preventive pathological test result data who are suffering from a chronic diseases; Pre-processing of collected data; training a Deep Neural Network (DNN) with the preprocessed data and feed a new patient similar set of routine/preventive pathological test result data to provide an estimate of the early detection of a chronic diseases.

Abstract: A word generation model obtains textual content and a requested topic of interest, and generates a targeted summary of the textual content tuned to the topic of interest. To do so, a topic-aware encoding model encodes the textual content with a topic label corresponding to the topic of interest to generate topic-aware encoded text. A word generation model selects a next word for the topic-based summary from the topic-aware encoded text. The word generation model is trained to generate topic-based summaries using machine learning on training data including a multitude of documents, a respective summary of each document, and a respective topic of each summary. Feedback of the selected next word is provided to the word generation model. The feedback causes the word generation model to select subsequent words for the topic-based summary based on the feedback of the next selected word.

Abstract: A natural language scene description is converted into a scene that is rendered in three dimensions by an augmented reality (AR) display device. Text-to-AR scene conversion allows a user to create an AR scene visualization through natural language text inputs that are easily created and well-understood by the user. The user can, for instance, select a pre-defined natural language description of a scene or manually enter a custom natural language description. The user can also select a physical real-world surface on which the AR scene is to be rendered. The AR scene is then rendered using the augmented reality display device according to its natural language description using 3D models of objects and humanoid characters with associated animations of those characters, as well as from extensive language-to-visual datasets. Using the display device, the user can move around the real-world environment and experience the AR scene from different angles.

Abstract: A targeted summary of textual content tuned to a target audience vocabulary is generated in a digital medium environment. A word generation model obtains textual content, and generates a targeted summary of the textual content. During the generation of the targeted summary, the words of the targeted summary generated by the word generation model are tuned to the target audience vocabulary using a linguistic preference model. The linguistic preference model is trained, using machine learning on target audience training data corresponding to a corpus of text of the target audience vocabulary, to learn word preferences of the target audience vocabulary between similar words (e.g., synonyms). After each word is generated using the word generation model and the linguistic preference model, feedback regarding the generated word is provided back to the word generation model. The feedback is utilized by the word generation model to generate subsequent words of the summary.

Abstract: A word generation model obtains textual content and a requested topic of interest, and generates a targeted summary of the textual content tuned to the topic of interest. To do so, a topic-aware encoding model encodes the textual content with a topic label corresponding to the topic of interest to generate topic-aware encoded text. A word generation model selects a next word for the topic-based summary from the topic-aware encoded text. The word generation model is trained to generate topic-based summaries using machine learning on training data including a multitude of documents, a respective summary of each document, and a respective topic of each summary. Feedback of the selected next word is provided to the word generation model. The feedback causes the word generation model to select subsequent words for the topic-based summary based on the feedback of the next selected word.

Abstract: A targeted summary of textual content tuned to a target audience vocabulary is generated in a digital medium environment. A word generation model obtains textual content, and generates a targeted summary of the textual content. During the generation of the targeted summary, the words of the targeted summary generated by the word generation model are tuned to the target audience vocabulary using a linguistic preference model. The linguistic preference model is trained, using machine learning on target audience training data corresponding to a corpus of text of the target audience vocabulary, to learn word preferences of the target audience vocabulary between similar words (e.g., synonyms). After each word is generated using the word generation model and the linguistic preference model, feedback regarding the generated word is provided back to the word generation model. The feedback is utilized by the word generation model to generate subsequent words of the summary.

Abstract: A targeted summary of textual content tuned to a target audience vocabulary is generated in a digital medium environment. A word generation model obtains textual content, and generates a targeted summary of the textual content. During the generation of the targeted summary, the words of the targeted summary generated by the word generation model are tuned to the target audience vocabulary using a linguistic preference model. The linguistic preference model is trained, using machine learning on target audience training data corresponding to a corpus of text of the target audience vocabulary, to learn word preferences of the target audience vocabulary between similar words (e.g., synonyms). After each word is generated using the word generation model and the linguistic preference model, feedback regarding the generated word is provided back to the word generation model. The feedback is utilized by the word generation model to generate subsequent words of the summary.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to facilitating corpus-based content generation, in particular, using graph-based multi-sentence compression to generate a final content output. In one embodiment, pre-existing source content is identified and retrieved from a corpus. The source content is then parsed into sentence tokens, mapped and weighted. The sentence tokens are further parsed into word tokens and weighted. The mapped word tokens are then compressed into candidate sentences to be used in a final content. The final content is assembled using ranked candidate sentences, such that the final content is organized to reduce information redundancy and optimize content cohesion.

Abstract: A targeted summary of textual content tuned to a target audience vocabulary is generated in a digital medium environment. A word generation model obtains textual content, and generates a targeted summary of the textual content. During the generation of the targeted summary, the words of the targeted summary generated by the word generation model are tuned to the target audience vocabulary using a linguistic preference model. The linguistic preference model is trained, using machine learning on target audience training data corresponding to a corpus of text of the target audience vocabulary, to learn word preferences of the target audience vocabulary between similar words (e.g., synonyms). After each word is generated using the word generation model and the linguistic preference model, feedback regarding the generated word is provided back to the word generation model. The feedback is utilized by the word generation model to generate subsequent words of the summary.