Abstract: Some embodiments are directed to a second cryptographic device (20) and a first cryptographic device (10). The first and second cryptographic devices may be configured to transfer a key seed. The key seed may be protected using a public key from one party and a private key from the other party. For example, a public key may be obtained from a private key through a noisy multiplication. At least one of the first and second cryptographic device may validate an obtained public key, e.g., to avoid leakage of the key seed or of a private key.

Abstract: A hair-removal apparatus is provided that comprises a hair-removal device with a movable hair-removal component, which comprises at least a first hair-contacting member and a second hair-contacting member, which are movable relative to each other and which are configured and arranged to mutually co-operate for removing hairs by mutually exerting a contact force, a pressing component configured and arranged to generate said contact force by exerting a pressing force on the movable hair-removal component during operation, a skin proximity sensing component, and a force adjusting component. The skin proximity sensing component is configured and arranged to detect a relative distance between the movable hair-removal component and a portion of the skin with hairs to be removed. The force adjusting component is configured and arranged to adjust, during operation, the pressing force exerted by the pressing component in dependence on the relative distance detected by the skin proximity sensing component.

Abstract: A breast pump device (1) is equipped with or used in conjunction with an acoustic milk expression assessment system (6) for the purpose of obtaining an indication about a fat content of expressed milk. The acoustic milk expression assessment system (6) includes an acoustic sensor (61) and a processor (62) configured to process an acoustic signal received from the acoustic sensor (61) during operation of the breast pump device (1) when a milk receptacle (4) is used with the device (1). By recording sound during a pumping session, it is possible to determine a frequency shift in the sound of droplets falling down in the receptacle (4) and hitting a surface of the milk contained by the receptacle (4) with respect to a reference situation of a liquid having 0% fat content, which can be taken as a factor in estimating a value related to the fat content of the milk.

Abstract: Some embodiments are directed to a categorization system for categorizing a sensitive data field in a dataset, e.g., a disease classification according to the ICD classification. A client device is to obtain categories for one or more records of the dataset. The client device determines categorization data for the categorization. The categorization data comprises homomorphic encryptions of possible values of the sensitive data field and encodings of the categories associated to the respective possible values, thus keeping the categorization secret. A data provider device stores the dataset and determines homomorphic encryption indicating differences between the value of the sensitive data field for a record and respective possible values. A categorization device determines which of those encryptions indicates a match and provides a category encoding associated with a matching possible value to the client device. The client device associates the encoded category to the record.

Abstract: Some embodiments are directed to a container builder (110) for building a container image for providing an individualized network service based on sensitive data (122) in a database (121). The container builder (110) retrieves the sensitive data (122) from the database (121), builds the container image (140), and provides it for deployment to a cloud service provider (111). The container image (140) comprises the sensitive data (122) and instructions that, when deployed as a container, cause the container to provide the individualized network service based on the sensitive data (122) comprised in the container image (140).

Abstract: A method for controlling compression of data includes accessing genomic annotation data in one of a plurality of first file formats, extracting attributes from the genomic annotation data, dividing the genomic annotation data into multiple chunks, and processing the extracted attributes and chunks into correlated information. The method also includes selecting different compressors for the attributes and chunks identified in the correlated information and generating a file in a second file format that includes the correlated information and information indicative of the different compressors for the chunks and attributes indicated in the correlated information. The information indicative of the different compressors is processed into the second file format to allow selective decompression of the attributes and chunks indicated in correlated information.

Abstract: Disclosed herein is a medical system (100, 300, 500) comprising a memory (110) storing machine executable instructions (120) and a convolutional neural network (122). The convolutional neural network is configured for receiving an initial Dixon magnetic resonance image (124, 126) as input. The convolutional neural network is configured for identifying one or more water-fat swap regions (128) in the initial Dixon magnetic resonance image. The medical system further comprises a processor (104) for controlling the medical system. Execution of the machine executable instructions causes the processor to: receive (200) the initial Dixon magnetic resonance image; and receive (204) the one or more water-fat swap regions from the convolutional neural network in response to inputting the initial Dixon magnetic resonance image into the convolutional neural network.

Abstract: The present disclosure pertains to a system for providing client-side physiological condition estimations during a live video session. In some embodiments, the system includes a first client computer system that is caused to: (i) store a neural network on one or more computer-readable storage media of the first client computer system, (ii) obtain a live video stream of an individual via a camera of the first client computer system during a video streaming session between the first client computer system and a second client computer system, (iii) provide, during the video streaming session, video data of the live video stream as input to the neural network to obtain physiological condition information from the neural network, and (iv) provide, during the video streaming session, the physiological condition information for presentation at the second client computer system.

Abstract: The present invention relates to a medical imaging apparatus. The apparatus comprises an ultrasound acquisition unit including an ultrasound probe for acquiring ultrasound image data of a patient. An image data interface is provided for receiving 3D medical image data of the patient and a position determining unit for determining a position of the ultrasound probe. A calibration unit determines a transfer function between the ultrasound image data and the 3D medical image data at a plurality of positions (C) of the ultrasound probe and provides a corresponding plurality of calibrated transfer functions and calibration positions. A computation unit synchronizes the ultrasound image data and the 3D medical image data on the basis of a position of the ultrasound probe and the plurality of calibrated transfer functions, said computation unit is further adapted to weight the calibrated transfer functions on the basis of a position of the ultrasound probe.

Abstract: The invention relates to a computer-implemented Bayesian inference method for performing Bayesian inference in a Bayesian network, which includes a continuous child node (3) and its discrete parent node (2) having two states. Being provided with a calibrated continuous probability distribution of the observations of the child node (3) for each of the two states of the parent node (2), the inferring for a new observation of the child node (3) for which the state of the parent node (2) is not known of the probability of at least a first state of the parent node (2) makes use of masses of portions of the probability distributions that depend on a locational relationship of the probability distributions and the value of the new observation. This may ensure that the inferred probability of the first state of the parent node (2) monotonically changes with monotonically changing values of the new observation.

Abstract: The present disclosure describes ultrasound imaging systems and methods that may be used to image, for example, breast tissue. An ultrasound imaging system according to one embodiment may include a probe, a sensor attached to the probe and operatively associated with a position tracking system, a processor configured to receive probe position data from the position tracking system. The user interface may be configured to provide instructions for placement of the probe at a plurality of anatomical landmarks of a selected breast of the subject and receive user input to record the spatial location of the probe at each of the plurality of anatomical landmarks. The processor may be configured to determine a scan area based on the spatial location of the probe at each of the plurality of anatomical landmarks and generate a scan pattern for the selected breast. The processor may be further configured to monitor movement of the probe.

Abstract: A method for controlling oxygen mix for a single-limb non-invasive ventilator comprising a pressure controller, and both a blower and a pressurized oxygen source downstream of the blower, each comprising a controller and a flow valve controlling flow, comprising: (i) generating a flow trajectory; (ii) providing the generated flow trajectory to a pair of complimentary flow coupling filters comprising a blower flow coupling filter and an oxygen flow coupling filter; (iii) generating an output from each of the filters, comprising an input flow trajectory for the blower flow controller and an input flow trajectory for the oxygen flow controller; and (iv) adjusting, by the blower flow controller and/or oxygen flow controller based on the input flow trajectory, target pressure, and oxygen mix, the blower speed controller and/or the pressurized oxygen source proportional flow valve.

Abstract: Some embodiments are directed to a public-key encryption device (20) and a private-key decryption device (10). The public-key encryption device is configured to compute a second public-key matrix (u), the second public-key matrix (u) having fewer matrix elements than the first public-key matrix (b) of the private-key decryption device. This reduces computation and bandwidth requirements at the side of the public-key encryption device.

Abstract: A drinks machine has an output nozzle for delivering hot water or steam, Steam is used by a milk frothing unit whereas hot water is delivered by the output nozzle directly to the exterior of the drinks machine for collection in a drinks vessel. A single nozzle is thus provided for steam or hot water delivery and there is no need for any accessory when delivering hot water. This means that there is reduced cost, fewer components to lose, and simplified cleaning, in that only per-use cleaning of the milk frothing unit is required, not the fixed parts of the appliance associated with the milk frothing unit.

Abstract: An ultrasound (US) system (10) includes a US scanner (14) and a US probe (12) operatively connected to the US scanner.

Abstract: A method for power management of a wearable device or an implantable device comprising a sensor, the sensor configured for providing a physiological information of a user, the sensor being further configured to be operated in at least two power modes comprising a first power mode and a second power mode, wherein in the first power mode the physiological information of the user is gathered and in the second power mode the sensor consumes less power than in the first power mode, the method comprising: receiving a signal being indicative of whether a health device which is configured to treat a health condition of the user is in use, wherein the health device is positioned at a different location with respect to the user than the wearable device or the implantable device; and based on the signal operating the sensor for a time duration in the first power mode; and operating the sensor in the second power mode thereafter.

Abstract: A respiratory monitoring system includes (10) a mechanical ventilator (12) configurable to perform a ventilation mode in that includes an inhalation gas delivery phase and provides extrinsic positive end-expiratory pressure (PEEP) at a PEEP level during an exhalation phase. A breathing tubing circuit (26) includes: a patient port (28), a gas inlet line (16) connected to supply gas from the mechanical ventilator to the patient port, a gas flow meter (30) connected to measure gas flow into lungs of the patient, and a pressure sensor (32) connected to measure gas pressure at the patient port. At least one processor (38) is programmed to: compute a proxy pressure comprising an integral of gas flow into the lungs measured by the gas flow meter; and trigger the inhalation gas delivery phase of the ventilation mode when the proxy pressure decreases below a trigger pressure threshold.

Abstract: There is provided a system (100) for performing image motion compensation. The system comprises a light source (110), an imaging unit (120), and a control unit (130). The light source is configured to provide multiplexed illumination to an object in a plurality of color channels, the imaging unit is configured to capture a first image and a second image of the object in the plurality of color channels, and the control unit is configured to determine an estimated motion of pixels between the first image and the second image in a first color channel, and to generate a first motion compensated image by extrapolating the estimated motion of pixels between the first image and the second image to at least another one of the plurality of color channels.

Abstract: A device includes a medical instrument mounting structure; a base; and a gearless longitudinal translation device connected to and enabling longitudinal movement of the medical instrument mounting structure with respect to the base. The gearless longitudinal translation device includes: a first friction wheel having at least a first beveled side surface, and a second friction wheel having at least a second beveled surface; a first linear rod disposed between the first and second friction wheels and in contact with the first and second beveled surfaces; and a control mechanism attached to the first and second friction wheels for rotating the first and second friction wheels. Rotation of the first and second friction wheels causes a longitudinal displacement of the first linear rod with respect to the first and second friction wheels, which in turn causes the medical instrument mounting structure to be longitudinally displaced with respect to the base.