Abstract: Various embodiments discussed herein enable client applications to be heavily integrated with a voice assistant in order to perform commands associated with voice utterances of users via voice assistant functionality and also seamlessly cause client applications to automatically perform native functions as part of executing the voice utterance. Such heavy integration also allows particular embodiments to support multi-modal input from a user for a single conversational interaction. In this way, client application user interface interactions, such as clicks, touch gestures, or text inputs are executed alternative or in addition to the voice utterances.

Abstract: Techniques for providing adaptive assistive technology for assisting users with visual impairment can be used on a computing device. These techniques include displaying content to a user, capturing a series of images or video of the user using a camera, analyzing the series of images or video to determine whether the user is exhibiting behavior or characteristics indicative of visual impairment, and rendering a magnification user interface on the display configured to magnify at least a portion of the content of the display based on a determination that the user is exhibiting behavior or characteristics indicative of visual impairment. The magnification user interface may be controlled based on head and/or eye movements of the user of the computing device.

Abstract: Systems and methods for determining a semantic image understanding of medical imaging studies are provided. A plurality of medical imaging studies associated with a plurality of medical imaging modalities is provided. Metadata associated with each of the plurality of medical imaging studies is generated by performing a plurality of semantic image analysis tasks using one or more machine learning based networks. The metadata associated with each of the plurality of medical imaging studies is output.

Abstract: A method for manufacturing a propeller for a propeller pump includes providing a base propeller including a hub extending from an axial end in the axial direction, and a plurality of blades fixedly connected to the hub, each blade including a pressure side, a suction side, a leading edge, an initial trailing edge, and a blade tip extending from the leading edge to the initial trailing edge at the end of the blade facing away from the hub, trimming each of the blades of the base propeller the axial direction, and forming a modified trailing edge bye removing a part of the initial trailing edge along the entire pressure side from the hub to the blade tip.

Abstract: Systems, methods, and storage media for optimizing automated modelling of resource allocation are disclosed. Exemplary implementations include operations for: receive or retrieve by a computer system, operational information associated with a plurality of users; allocate, by the computer system, at least a first time portion to at least a first task associated with a first user of the plurality of users based on analysis of the operational information; and dynamically modify, by the computer system, the first time portion responsive to receiving or retrieving additional operational information over time.

Abstract: A method and system for non-invasive assessment and therapy planning for coronary artery disease from medical image data of a patient is disclosed. Geometric features representing at least a portion of a coronary artery tree of the patient are extracted from medical image data. Lesions are detected in coronary artery tree of the patient and a hemodynamic quantity of interest is computed at a plurality of points along the coronary artery tree including multiple points within the lesions based on the extracted geometric features using a machine learning model, resulting in an estimated pullback curve for the hemodynamic quantity of interest.

Abstract: Systems and methods for generating an updated segmentation of an initial segmentation are provided. An initial segmentation of an anatomical object from an input medical image is received. User input modifying the initial segmentation is received. An updated segmentation of the anatomical object in the input medical image is generated using a machine learning based network based on at least one of the initial segmentation and the user input. The updated segmentation is output.

Abstract: Systems, methods, and storage media for optimizing automated modelling of resource allocation are disclosed. Exemplary implementations include operations for: receive or retrieve by a computer system, operational information associated with a plurality of users; allocate, by the computer system, at least a first time portion to at least a first task associated with a first user of the plurality of users based on analysis of the operational information; and dynamically modify, by the computer system, the first time portion responsive to receiving or retrieving additional operational information over time.

Abstract: A medical knowledge base in a digital, clinical system is upgraded. A storage with a knowledge base, being a SNOMED knowledge base, is provided in a web ontology format. Procedural data, representing clinical procedures for evaluation of a patient's health state, is received. The received procedural data is mapped in a set of SNOMED expressions. The SNOMED expressions are converted into statements in the web ontology format. The SNOMED knowledge base is upgraded with the received procedural data by adding the statements in the SNOMED knowledge base for providing a processable file with an upgraded version of the SNOMED knowledge base.

Abstract: A method includes processing at least one input dataset (using a multi-level processing algorithm, one or more of the at least one input dataset comprising imaging data of an echocardiography of a cardiovascular system of a patient. The multi-level processing algorithm comprises a multi-task level and a consolidation-task level. An input of the consolidation-task level is coupled to an output of the multi-task level. The multi-task level is configured to determine multiple diagnostic metrics of the cardiovascular system based on the at least one input dataset. The consolidation-task level is configured to determine a fitness of the cardiovascular system of the patient.

Abstract: A method and system for non-invasive assessment and therapy planning for coronary artery disease from medical image data of a patient is disclosed. Geometric features representing at least a portion of a coronary artery tree of the patient are extracted from medical image data. Lesions are detected in coronary artery tree of the patient and a hemodynamic quantity of interest is computed at a plurality of points along the coronary artery tree including multiple points within the lesions based on the extracted geometric features using a machine learning model, resulting in an estimated pullback curve for the hemodynamic quantity of interest.

Abstract: Systems, methods, and storage media for optimizing automated modelling of resource allocation are disclosed. Exemplary implementations include operations for: receive or retrieve by a computer system, operational information associated with a plurality of users; allocate, by the computer system, at least a first time portion to at least a first task associated with a first user of the plurality of users based on analysis of the operational information; and dynamically modify, by the computer system, the first time portion responsive to receiving or retrieving additional operational information over time.

Abstract: Disclosed is an impeller for a pump for conveying waste water having a support body which can be rotated about an axis of rotation (A) and on which two blades for conveying are provided, wherein the blades each have an inlet region which extends from an inlet edge up to an apex, wherein the wall thickness increases at its end side remote from the support body in the inlet region from the inlet edge and reaches its maximum value at the apex, wherein the blade converges in the inlet region in an axial direction from the support body to the end side with respect to the wall thickness. A base plate is furthermore proposed for interaction with such an impeller as well as a pump for conveying waste water.

Abstract: A method for the positioning of a cover disk with respect to an open impeller of a pump arranged in a pump housing. An adjustment bolt is first screwed so far into a threaded bore of the cover disk until it comes into contact with the pump housing. An identifier is subsequently applied which indicates a position of a first marking of the adjustment bolt. The adjustment bolt is then screwed in further until a second marking reaches the identifier. The described steps are repeated for at least one further adjustment bolt.

Abstract: A method for the positioning of a cover disk with respect to an open impeller of a pump arranged in a pump housing. An adjustment bolt is first screwed so far into a threaded bore of the cover disk until it comes into contact with the pump housing. An identifier is subsequently applied which indicates a position of a first marking of the adjustment bolt. The adjustment bolt is then screwed in further until a second marking reaches the identifier. The described steps are repeated for at least one further adjustment bolt.

Abstract: Described herein, in a preferred embodiment, is a leonardite-based polyurethane resin binder that may be used, among other applications, as a binder in combination with foundry aggregate, e.g., sand, for molding or casting metal parts. The binders described herein comprise a humic substance, preferably leonardite, first mixed with a foundry aggregate and then the humic-aggregate mixture is combined with a polymerizable polyol, an isocyanate, and a polymerization catalyst to make a polyurethane resin binder in situ in a foundry aggregate, such as sand. The lignite is added as a solid to the foundry aggregate, and improves the binder performance of the lignite-containing part of the binder components.

Abstract: An impeller for a pump for conveying waste water is proposed having a support body (32) which can be rotated about an axis of rotation (A and on which two blades (31) for conveying are provided, wherein the blades (31) each have an inlet region (311) which extends from an inlet edge (310) up to an apex (S), wherein the wall thickness (31) increases at its end side (350) remote from the support body (32) in the inlet region (311)) from the inlet edge (310) and reaches its maximum value at the apex (S), wherein the blade (31) converges in the inlet region (311) in an axial direction from the support body (32) to the end side (350) with respect to the wall thickness. A base plate is furthermore proposed for interaction with such an impeller as well as a pump for conveying waste water.

Abstract: This disclosure relates to a process for producing titanium dioxide, comprising: a) reacting a alloy comprising silicon and aluminum having a melting point of about 482° C. to about 660° C., with chlorine gas at temperatures above 190° C. to form chlorides of silicon and aluminum; b) adding titanium tetrachloride to the chlorides of silicon and aluminum of step (a); c) oxidizing the chlorides of silicon and aluminum and titanium tetrachloride of step (b); and d) forming titanium dioxide.

Abstract: Described herein, in a preferred embodiment, is a leonardite-based polyurethane resin binder that may be used, among other applications, as a binder in combination with foundry aggregate, e.g., sand, for molding or casting metal parts. The binders described herein comprise a humic substance, preferably leonardite, first mixed with a foundry aggregate and then the humic-aggregate mixture is combined with a polymerizable polyol, an isocyanate, and a polymerization catalyst to make a polyurethane resin binder in situ in a foundry aggregate, such as sand. The lignite is added as a solid to the foundry aggregate, and improves the binder performance of the lignite-containing part of the binder components.