Philips Patente

The invention concerns a computer-implemented method for optimizing an examination, wherein the method comprises the steps of instructing the patient by displaying instructions via a user interface for simulating the examination; receiving image data comprising information about at least one portion of the patient via an optical sensor; analyzing, by a processor, the image data from the patient when the patient has been instructed; determining visible patient properties based on the analyzed image data; providing the visible patient properties to an external examination unit; and adapting a workflow of the examination based on the determined visible patient properties. The invention further concerns a system for optimizing an examination.

A method and system for object instance segmentation. Imaging and/or audio data is obtained, and a plurality of prompts for an object instance in the imaging and/or audio data is defined. Each prompt is provided to a prompt-based segmentation model to generate a respective initial segmentation mask for each prompt. At least some of the initial segmentation masks are processed to generate a final segmentation mask for the object instance.

Disclosed is a medical imaging method comprising receiving (200) reference medical camera data (122). The method further comprises receiving (202) reference anatomical keypoint data (126) by inputting the reference medical camera data into an anatomical keypoint detection neural network (124). The method comprises iteratively generating (204) synthetic medical camera data (138) by: generating (206) intermediate medical camera data (130) by inputting the reference medical camera data into an image synthesis machine learning module (128); receiving (208) intermediate anatomical keypoint data (132) from the anatomical keypoint detection neural network; calculating (210) a loss function (134) using the intermediate anatomical keypoint data and the reference anatomical keypoint data; providing (214) the intermediate medical camera data as synthetic medical camera data (138) if the loss function meets (212) a predetermined convergence criterion; and otherwise, modifying (216) the image synthesis machine learning module using the loss function and repeating the iterative steps.

Disclosed herein is a method of magnetic resonance imaging. The method comprises receiving (200) a sequence of magnetic resonance imaging scans (122) to be performed on a single examination subject (318) during a continuous time interval for a magnetic resonance imaging system (302).The method further comprises receiving (202) metadata (124) descriptive of the single examination subject and the magnetic resonance imaging system. The method further comprises receiving (204) a set of inter-scan time intervals (126) for time intervals between the sequence of magnetic resonance imaging scans in response to inputting the metadata and the sequence of magnetic resonance imaging scans into a trained artificial intelligence module (132). The set of inter-scan time intervals comprises: paired time intervals (128) and confidence levels (130) of the time intervals. The method further comprises providing (206) the set of inter-scan time intervals as control data for the magnetic resonance imaging system.

Disclosed is a computer-implemented method (100) for performing image quality checks using a control system (200), the method comprising by the control system (200): receiving (102) screen capture medical image data (202) of a user interface (204) of a medical imaging system (206); extracting (104) exam context information (208) and medical images (210) from the screen capture medical image data (202); based on the extracted exam context information (208), selecting (106) an image evaluation protocol (212), wherein the image evaluation protocol (212) comprises at least one image metric (214); executing (108) the image evaluation protocol (212) on the extracted medical images (210), resulting in at least one value of the at least one image metric (214); and based on the at least one value of the at least one image metric (214), providing (110) a control signal (216) to the medical imaging system (206).

An audio apparatus renders a stereo signal and comprises a weight processor (105) determining frequency subband downmix weights from spatial parameters for the stereo signal. A downmixer (107) determines a mono downmix by downmixing the stereo signal using the downmix weights. A residual circuit (109) arranged to generate at least a first residual signal from a first channel of the stereo signal by generating frequency subband residual weights from the downmix weights, generating frequency subband compensation values downmix and the residual weights; and generating frequency subband values of the residual signal by compensation of the channel by the compensation values. A renderer (111) renders an output stereo signal by a directional rendering of the downmix to generate a first intermediate stereo signal and a second rendering of the residual signals to generate a second intermediate stereo signal with the output stereo signal being generated by combining the intermediate stereo signals.

An audio apparatus comprises a first renderer (205) applying a directional rendering to a mono downmix with the rendering being based on a channel transfer function retrieved from a store (211) storing transfer functions for different directions. The rendering is for a direction determined in response to spatial upmix parameters provided for the downmix by a direction determining circuit (209). A second intermediate stereo signal may be rendered from a decorrelated version of the mono downmix by a second renderer (217) using a predetermined rendering, such as for example from a specific direction/position that is not signal dependent. A combiner (219) generates an output stereo signal by combining the intermediate stereo signals. An adapter (221) adapts the level of the first intermediate stereo signal relative to the level of the second intermediate stereo signal in the output stereo signal dependent on a first scaling value determined from the spatial parameters.

Disclosed herein is a method for synchronizing MRI data acquisitions of a heart of a subject (118) with a cardiac cycle of the heart using photoplethysmography data (320; 410). The method comprises receiving the photoplethysmography data (320; 410), detecting a first cardiac trigger (322; 412), which is indicative of a start of a first ventricular systole (420) of a first cardiac cycle, using the received photoplethysmography data (320; 410), and, in response to the detecting of the first cardiac trigger (322; 412), performing a time-delayed first triggering of a first magnetic resonance imaging data acquisition before a start of a ventricular contraction of a second ventricular systole (434) of a second cardiac cycle following the first cardiac cycle.

There is provided a method for remote servicing and technical support of imaging equipment that involves obtaining information from a local node with at least one imaging system is disclosed. The method establishes a two-way secure communication channel between a local and a remote node operator, wherein identity confirmation of the remote operator occurs through a database, granting access to the local node's imaging system peripheral devices upon approval. The method includes generating media events transmitted to the remote node, transmitting information streams via a e.g. WebRTC channel, and allowing remote operators to access multiple local systems. The method also involves capturing local node screens with a virtual camera module and transmitting peripheral device inputs to the remote node. A receiver module on the remote node receives shared screens and emulated inputs, enabling remote change requests through keyboard and mouse events.

In the field of transmission of a rotational motion from one member to another, an adjustable transmission system (1) is provided which is configured to selectively transmit a rotational motion of a primary member (10) about a rotational axis (R) to a secondary member (20), to cause the secondary member (20) to selectively rotate about the rotational axis (R). The transmission system (1) comprises a coupling member (30) which is configured to selectively be in first and second axial positions relative to the primary member (10), for decoupling from and coupling to the secondary member (20), respectively, wherein the primary member (10) is configured to enable displacement of the coupling member (30) in axial direction on the basis of changes of the direction of the rotational motion, and wherein use is made of a pattern of guiding channels (12) which are engaged by a guided element (31).

An audio apparatus comprises a downmixer (107) generating a mono downmix by downmixing a stereo signal resulting from applying downmix filters (103, 105) to an input stereo signal. Residual filters (109,113) generate compensation signals from the mono downmix and residual signals are generated by compensators (111, 115) compensating the input channel signals by the compensation signals. A renderer 117 renders the mono downmix and residual signals to generate an output stereo signal. The filter responses of the downmix filter (103, 105) and the residual filters (109,113) for a given channel have a fixed relationship, typically being complex conjugates in the frequency domain, and are updated by an adapter (119) to reduce error values determined from the residual signals. The error values may be energy or power level measures for the residual signals.

A mechanism for generating a query response to a search query for use in a clinical environment. A conversion module is configured to convert metadata, produced during segmentation mesh modification by a model-based segmentation method, into a text-based file. A search module is configured to process the search query and the text-based file to produce a query response to a user at an output user interface.

An imaging system is used for capturing images of a subject during X-ray examination. It comprises a video camera system, separate to the X-ray image generation, for generating video camera images. The video camera images are processed to determine that a captured video camera image is synchronized with an X-ray exposure, based on saturation of one or more pixels of the captured video camera image. Timing information can then be generated associating the timing of the video camera images with the timing of the X-ray exposure.

In a magnetic resonance imaging (MRI) room, a raw fringe magnetic field compensating structure includes an active compensating coil adapted to reduce the target magnetic flux density outside a magnet apparatus of an MR in a defined area. The active compensating coils are not disposed in or on the magnet apparatus. A method of compensating a raw fringe magnetic field is also disclosed.

Disclosed herein is a method of magnetic resonance imaging, comprising: acquiring intrascan subject motion data; and acquiring k-space data (144) by controlling a magnetic resonance imaging system (102) with pulse sequence commands (142), wherein the pulse sequence commands (142) define an original subsampling pattern (300) and are configured to acquire the k-space data (144) as multiple shots of k-space data; generating an effective subsampling pattern (302) by modifying an original subsampling pattern (300) using a rigid body transformation with the intrascan subject motion data; identifying gaps in the effective subsampling pattern (302) based on a difference between the original subsampling pattern (300) and the effective subsampling pattern (302); generating updated pulse sequence commands (150) configured to acquire gap-located sampling points within the identified gaps in the effective subsampling pattern (302); and acquiring additional k-space data (152) in multiple shots by controlling the magnetic resonance imaging system (102) with the updated pulse sequence commands (150).

The subject-matter of the present disclosure relates to an x-ray radiography 'XR' apparatus (100). The apparatus comprises a first image sensor (104) configured to capture an X-ray image of a target area (106), a second image sensor (114) arranged with a field of view comprising the target area in a first direction (116), and a mirror (118) disposed within the field of view of the second image sensor (114), and arranged at an angle to provide the second image sensor (114) with a view of the target area (106) from a second direction (120) at least partly orthogonal to the first direction (116).

Disclosed herein is a method of magnetic resonance imaging. The method comprises receiving (200) groups of k-space data descriptive. The groups of k-space data comprise group specific imaging k-space data and group specific navigator k-space data. The method further comprises determining (202) group specific subject positions using the group specific navigator k-space data of the groups of k-space data. The method further comprises initializing (204) group specific motion parameters of a joint optimization using the group specific subject positions. The method further comprises reconstructing (206) a motion corrected magnetic resonance image by performing the joint optimization on the group specific imaging k-space data of the groups of k-space data. The joint optimization is configured to simultaneously reconstruct the motion corrected magnetic resonance image while determining the group specific motion parameters. The method further comprises providing (208) the motion corrected magnetic resonance image descriptive of the field of view.

There is provided a computer-implemented method comprising receiving use data representative of use of a respiratory support device by a subject. The method comprises determining, based on the use data, a feature value for each of a plurality of features. The plurality of features are human-interpretable features representative of use of the respiratory support device. The method comprises providing the feature values as input data to a machine learning model. The machine learning model is trained to generate predicted use data based on the feature values. The method comprises using the machine learning model to generate predicted use data representative of a predicted use of the respiratory support device by the subject, and determining an importance indicator for each of the plurality of features. The importance indicators are representative of a contribution of the corresponding feature to the predicted use. The method comprises generating an output signal indicative based on the importance indicators and the predicted use data. The output signal is representative of a likelihood the subject will stop using the respiratory support device.

It would be desirable to provide a sensor apparatus that facilitates precise mapping of signals to sensor nodes in an image coordinate system. There is therefore provided a sensor apparatus (110) comprising a plurality of sensor nodes. The sensor apparatus is configured to be used in conjunction with an imaging device (104). The imaging device is configured to acquire image data, wherein the image data uses an image coordinate system. The sensor apparatus comprises a plurality of fiducial markers each having a uniquely identifiable pattern which is detectable by the imaging device. The sensor apparatus is configured to hold the fiducial markers in a predetermined spatial relationship with the sensor nodes for mapping of signals obtained from the sensor nodes to locations of the sensor nodes in the image coordinate system.

An image processing system (100) and related method. The image processing system comprises an input interface (102) configured to receive X-ray image data of an object acquired by an X-ray imaging apparatus during a scan and to receive camera image data of the object acquired by a camera system having a field of view of the object. A geometry determiner (104) of the system is configured to analyze the camera image data of the object to determine geometry information of the object and distance information of the object to a detector of the X-ray imaging apparatus. A scatter estimation module (106) of the system is configured to estimate a scatter profile of scatter present in the X-ray image data by use of the determined geometry information of the object and the determined distance information of the object to the detector of the X-ray imaging apparatus.

Proposed concepts thus aim to provide schemes, solutions, concepts, designs, methods and systems pertaining to generating a medical image file. In particular, embodiments aim to provide a method for generating a medical image file by finding a region of interest in a medical image (and thereby, or separately, region(s) of non-interest) and then processing the image so that the region of interest and the region(s) of non-interest have different resolutions to one another (with the region of non-interest having a lower resolution than the region of interest). In other words, it is proposed that by identifying a region of interest in a medical image, comprising an anatomical feature, a modified medical image can be generated with spatially-varied resolution.

Proposed concepts thus aim to provide a method for determining the decomposition matrix of a pair of CT images. In particular, embodiments aim to provide a method for determining the decomposition matrix based on values of pixels in each image of the pair of CT images that are determined to depict bone tissue of the subject.

An optical measurement device (100) for obtaining optical measurements from a tissue region (110), is provided. The optical measurement device includes an optical source (120); an optical detector (130); a first optical waveguide (140); and a second optical waveguide (150). In one option, i) a proximal end portion (140<Pep>) of the first optical waveguide adjoining the proximal end (140') of the first optical waveguide, and at least a portion of the optical source (120), are in direct contact with a first material (160) having a refractive index (n<1>) that is less than a refractive index (n<3>) of the first optical waveguide (140), and also less than a refractive index (n<S>) of the optical source (120), for containing the optical radiation within the first optical waveguide (140) and/or within the optical source (120), respectively. In another option, ii) a proximal end portion (150<Pep>) of the second optical waveguide adjoining the proximal end (150') of the second optical waveguide, and at least a portion of the optical detector (130), are in direct contact with a first material (160) having a refractive index (n<1>) that is less than a refractive index (n<3>) of the second optical waveguide (150), and also less than a refractive index (n<D>) of the optical detector (130), for containing the optical radiation within the second optical waveguide (150) and/or within the optical detector (130), respectively.

A wireless power system comprises a power receiver (105) receiving power from a power transmitter (101) which comprises an output resonance circuit comprising a transmitter coil (103) and a capacitor (303). A driver (301) generates a drive signal for the output resonance circuit to generate an inductive power transfer signal. A frequency determiner (313) provides a reduced load sensitivity operating frequency for the drive signal and a frequency controller (311) changes the operating frequency of the drive signal to the reduced load sensitivity operating frequency in response to receiving a load change message from the power receiver. A transmitter (309) transmits a load change acknowledge message to the power receiver (105) to indicate the change of frequency. The frequency controller (311) changes the operating frequency from the reduced load sensitivity operating frequency to a load dependent operating frequency in response to determining that the power receiver (105) has performed the load change.

Proposed concepts aim to provide methods and systems pertaining to determining a noise scaling value. In particular, embodiments aim to provide a method for determining a noise scaling value for a determined noise residuum based on a comparison of the values of pixels of a modified image with one or more weighted sums of one or more values of neighboring pixels of the modified image.

An apparatus comprises a first receiver (103) receiving a plurality of audio capture signals comprising audio of a scene captured by one or more audio capture devices. A second receiver (101) receives an image capture signal comprising at least one image representing a capture frustum of the scene. A third receiver (105) receives metadata comprising capture region indications for at least some of the audio capture signals where a capture region indication for an audio capture signal is indicative of a region of audio capture of the scene for the audio capture signal. An image generator (107) generates a view image of the scene for a view frustum from the image capture signal, and an audio generator (109) generates an output audio signal representing the scene by mixing the plurality of audio capture signals in dependence on the view frustum and the capture region indications.

The invention relates to a server device for data transfer with an isolated target device. The server device includes an external communication interface to communicate with a remote server for sending device data and receiving update packets containing target device identification and payload data. A data processor partitions a coverage area into bounded sections, generates a stochastic model of location states and transitions, maps the area, and determines routes for guiding a mobile device to the target device.The mobile device features a communication interface to receive updates and instructions from the server device and connect to the target device to deliver the update. It also includes a security interface for capturing a user's security feature and a mobile processing unit to authorize the data transfer when identifications match. Also a corresponding method and system are disclosed.

The present invention provides a cooling system (1) for an in-bore equipment of a medical apparatus, comprising: a compact fan (11) which is resistant to magnetic interference, a radio frequency, RF, shield (12) comprising a RF shielding housing (111) which completely encloses the compact fan (11), wherein the housing (111) comprises an air-in duct (112) and an air-out duct (113), and RF shielding mesh parts (121, 122) covering the air-in duct (112) and the air-out duct (113). In this way, a solution for efficient and localized cooling inside the bore of the medical apparatus is provided, to enhance the performance, the efficiency of medical apparatus and to improve the patient comfort.

Disclosed is a computer-implemented method (100) for performing image quality checks using a control system (200), the method comprising by the control system (200): receiving (102) screen capture medical image data (202) of a user interface (204) of a medical imaging system (206); extracting (104) exam context information (208) and medical images (210) from the screen capture medical image data (202); based on the extracted exam context information (208), selecting (106) an image evaluation protocol (212), wherein the image evaluation protocol (212) comprises at least one image metric (214); executing (108) the image evaluation protocol (212) on the extracted medical images (210), resulting in at least one value of the at least one image metric (214); and based on the at least one value of the at least one image metric (214), providing (110) a control signal (216) to the medical imaging system (206).

Disclosed is a computer-implemented method (100) for detecting anatomical keypoints (200) using a camera configured to image at least a portion of a body of a subject (202), the method comprising: receiving (102) image data (204), receiving (104) anatomical keypoint data in response to inputting the image data (204) into an anatomical keypoint detection neural network, determining (106) the set of anatomical keypoints (200), detecting (108) a set of body parts of the body in the image data (204), resulting in cropped image data (206); receiving (110) body part specific keypoint data in response to inputting the cropped image data (206) into at least one body part specific keypoint detection neural network, determining (112) the set of body part specific keypoints (208); and augmenting (114) the anatomical keypoints (200) by the body part specific keypoints (208).

Proposed concepts thus aim to provide schemes, solutions, concept, designs, methods and systems pertaining to operating a CT system. In particular, embodiments aim to a method for operating a CT system. This can be achieved by slowly varying a kVp level of an X-ray tube of the CT system (as opposed to having to use an expensive fast-switching kVp generator, for example) so that each voxel of the scanned volume is scanned/imaged under at least n different kVp levels, where n is 2 or more. In other words, by slowly varying the kVp level of an X-ray tube during rotation of the gantry of the CT system, every voxel of a scanned volume will be seen under at least n different kVp levels, thus enabling spectral CT imaging without any specialized hardware, thus facilitating spectral imaging even in a standard, one source, one detector CT system.

The invention relates to a method for predicting an outcome for a prostate cancer. Particularly the method is based on the expression levels of markers genes determined in a prostate cancer sample from the subject. The invention further relates to a kit for determining the gene expression levels and uses thereof in determining an outcome for a subject with prostate cancer. The invention also relates to therapies for use in the treatment of prostate cancer.

Proposed concepts thus aim to provide schemes, solutions, concepts, designs, methods and systems pertaining to generating a model for predicting focal spot degradation. In particular, embodiments aim to provide a method for generating a model for predicting focal spot degradation by generating a first sub-model describing a relationship between medical image data and a focal spot shape, and a second sub-model describing a relationship between a focal spot shape and a focal spot degradation score. A composite model is then generated based on the first and second sub-models. The composite model, which can be a machine-learning model, can thus be used to predict the focal spot degradation score from the medical image data.

A mechanism for processing ultrasound data comprising one or more sequences of ultrasound frames captured during ultrasound imaging of a fetus. The ultrasound frames are processed to classify each ultrasound frame as a heart frame or a non-heart frame. Any clusters of ultrasound frames meeting predetermined criteria are identified, which criteria make use of the classifications of the ultrasound frames. A quality value is produced for each cluster of ultrasound frames.

The present invention relates to a computer-implemented method for converting image data of an X-ray detector to a predefined data format of an X-ray control device. The method comprises receiving a request from the X-ray control device to provide an X-ray image, the request comprising a set of predefined image parameters of the X-ray image, sending a trigger signal to the X-ray detector to provide X-ray image data acquired with the X-ray detector, and receiving the X-ray image data acquired by the X-ray detector from the X-ray detector. The method comprises further processing the received X-ray image data, thereby generating a processed X-ray image comprising the predefined image parameters, and providing the processed X-ray image to the X-ray control device.

Proposed concepts thus aim to provide schemes, solutions, concept, designs, methods and systems pertaining to compensating for motion during a CT scan. In particular, embodiments aim to provide a method for compensating for motion during a CT scan by obtaining two CT scan volumes of the same portion of a subject (and which at least partially overlap in time) and then taking one slice of one of the CT scan volumes and generating a reference motion state (i.e., a ground truth reference) based on the subject's motion state at the point of time of the selected slice. Based on this reference motion state and the first and second CT scan volumes, a time-dependent rigid transformation function can be generated (i.e., a transformation function which only uses rigid transformations) and then either applied directly to the first and second CT scan volumes to compensate for their motion or applied to the original projection data to generate a motion-compensated CT scan volume from scratch.

The present disclosure relates generally to the use of medical devices for the treatment of vascular conditions. In particular, the present disclosure provides devices and methods for using laser-induced pressure waves created within a sheath to disrupt intimal and medial calcium within the vasculature. The present disclosure also provides treatment mode selection systems that may be used with such devices and methods.

A defibrillation system employs one or more of a wearable biosensor (40) configured to monitor a ventilation of the patient, a wearable injector (50) configured to administer a medication to the patient, a digital stethoscope (60) configured to monitor a heart of the patient; and ambient sensor (70, 80)(s) configured to monitor ambient sound and/or ambient light. The defibrillation system further employs a defibrillator (20) including a defibrillation controller (21) configured to implement a resuscitation protocol in accordance with one or more of a monitoring of the ventilation of the patient by the wearable biosensor (40), an administering of the medication to the patient by the wearable injector (50), a monitoring of the heart of the patient by the digital stethoscope (60), and a monitoring of one of ambient sound and ambient light by the at least one ambient sensor (70, 80).

Disclosed is an intraluminal imaging system, including a processor circuit in communication with an intraluminal imaging catheter, and configured to receive a plurality of intraluminal images obtained by an imaging component of the intraluminal imaging catheter while the intraluminal imaging catheter is moved through a body lumen of a patient. The processor circuit is further configured to automatically identify based on image recognition different vein segments as the imaging component of the intraluminal imaging catheter passes through the vessel, and output to a screen display a label of the identified vein segment and a current frame provided by the intraluminal imaging catheter.

A method for configuring a CT image data set to improve interoperability without increasing data package size. The method comprises compiling CT image data into a DICOM data object with DICOM metadata, and wherein the compiled CT image data includes both images compressed in a form that is DICOM readable and images compressed in a form that is not DICOM readable.