Alerta

DEVICE AND METHOD FOR PREDICTING EARLY DEMENTIA IN ELDERLY PERSON BY USING ARTIFICIAL INTELLIGENCE

Resumen de: WO2026151252A1

According to one embodiment of the present invention, a device for predicting early dementia in an elderly person by using artificial intelligence comprises: an image data collection unit on which a subject draws an additional picture over an image on which stimulus symbols are printed, and which collects image data; an analysis unit for performing, on the image data, machine learning using a pre-stored artificial neural network model, and analyzing the dementia prediction degree; and an output unit for outputting dementia prediction information about the subject's degree of dementia analyzed by the analysis unit.

IDENTIFIER FOR A MEDICAL DEVICE

Resumen de: US20260204403A1

0000 For identification for medical devices, the medical device is formed by a generic electronics module and a removable identification module. By using an identifier on a removable module, the identifier may be associated with different electronics modules to form the medical device at different times. The removable module may include electronic paper, label, and/or memory for storing and/or displaying information about the medical device. The removable module may allow for settings to be provided for any connected electronics module, avoiding reconfiguring by the user. A service organization does not need to re-ship back repaired components, instead providing a replacement electronics module to form the complete medical device with the user kept identification module.

MONITORING AND VISUALIZING GAIT OF A USER OF AN ASSISTIVE DEVICE

Resumen de: US20260198849A1

0000 Embodiments disclosed herein provide a mobile device for monitoring and visualizing a gait of a user. The mobile device includes a camera, an I/O interface, a memory comprising an application and a processor connected to the memory. The processor is configured to start a gait session to receive a measurement data from plurality of sensors of the user wearing an assistive device, the gait session initializes the measurement data reception from the plurality of sensors. Further, the processor activates the camera to record a video data of the user concurrently receiving the measurement data from the plurality of sensors during the gait session. The processor applies timestamps to frames of the video data of the user with respect to the measurement data based on the initialization signal to obtain time-synchronized gait visualization data.

DEEP BRAIN STIMULATION

Resumen de: US20260199683A1

A method for supporting deep brain stimulation (DBS) programming includes receiving pre-operative magnetic resonance imaging (MRI) data and post-operative computed tomography (CT) data of a patient having an implanted DBS lead and registers the MRI and CT data into a common spatial reference frame. Anatomical and device-related features, including DBS lead placement and one or more neural regions of interest, are extracted from the registered images. A patient-specific electrical conductivity model of brain tissue is generated based on the MRI data. Using the conductivity model and a representation of the DBS lead, electric field distributions corresponding to one or more DBS contact configurations are simulated. The simulated electric field is optimized by determining stimulation parameters that increase electric field exposure within the neural regions of interest while limiting exposure outside those regions. One or more DBS stimulation settings are output for clinical programming of the DBS lead.

LANGUAGE-GUIDED NAVIGATION ASSISTANT FOR MEDICAL IMAGE ACQUISITION

Resumen de: US20260199024A1

Systems and methods for language-guided navigation assistance for medical image acquisition are provided. An initial image depicting a view of an image acquisition device at an initial position and a target image depicting a view of a target position are received. A trajectory between the initial position and the target position is determined based on the initial image and the target image. Text-based descriptions are generated for each step of the trajectory using a machine learning based vision-language model. One or more keyframes are selected from the trajectory based on the text-based descriptions. A particular natural language instruction for navigating the image acquisition device to a particular keyframe of the one or more keyframes to are generated. The natural language instructions are output.

System and Method of Using DENSE Deep Networks to Predict Myocardial Strain

Resumen de: US20260198865A1

0000 A neural network predicts a sequence of myocardial motions from cardiac image data of a heart of a subject. DENSE cardiac magnetic resonance contour videos of cine data are used as input, and the output provides predicted displacement fields, supervised by the DENSE displacements. In the testing phase, DENSE data are no longer required; the trained network takes standard cine CMR bSSFP contour videos as input and predicts the final displacements.

GENERATION OF INSTRUCTIONS FOR TREATMENT PLANNING USING LANGUAGE MODELS

Resumen de: US20260204413A1

A method includes obtaining treatment provider instructions expressed in natural language. The treatment provider instructions are associated with treatment of a dental patient. The method further includes providing the treatment provider instructions and a prompt including rules for a domain-specific format for dental treatment plans to a trained AI model. The method further includes obtaining, as output from the AI model, machine-readable instructions related to the treatment provider instructions structured according to the domain-specific format. The method further includes causing a treatment planning algorithm to be adjusted based on the machine-readable instructions.

LONGITUDINAL QUANTITATIVE ULTRASOUND MONITORING

Resumen de: US20260198899A1

0000 For longitudinal monitoring in quantitative ultrasound (QUS) imaging. User variability is reduced by loading the same settings from a baseline or earlier examination for a follow-up examination. Artificial intelligence (AI), given these same settings, guides placement of the field of view (FOV) and/or region of interest (ROI) in the patient for the follow-up examination. User variability is reduced, allowing for more accurate comparison between different examinations. Tools or applications using the longitudinal study may be more accurate, so the tools or applications are made more accessible on a variety of platforms rather than just the ultrasound scanner.

MACHINE LEARNING MODEL TO ESTIMATE SYSTOLIC AND DIASTOLIC BLOOD PRESSURE FROM ACQUIRED BLOOD PRESSURE DATA

Resumen de: US20260198791A1

0000 A wearable ear-mounted cardiovascular device acquires blood pressure data while applying controlled confining pressure to ear tissue and sensing arterial pulsatility with a force sensor. The waveform data are processed to extract multiple features from inflation, deflation, compression, and decompression segments, including pressures at characteristic changes in oscillation trend, oscillation amplitudes, frequency-domain descriptors, and waveform-derived statistics. Separate machine learning regression models, such as Support Vector Machines, use distinct feature sets to estimate systolic and diastolic blood pressure relative to reference arm cuff measurements. The trained models provide real-time, cuffless blood pressure values from the ear device, and can operate with stepwise compression or in a passive ear-clip configuration calibrated intermittently using external blood pressure devices.

METHODS AND SYSTEMS FOR IDENTIFYING REGIONS OF INTEREST FROM THREE-DIMENSIONAL MEDICAL IMAGE DATA

Resumen de: US20260203896A1

0000 Embodiments of the present disclosure provide methods and systems for identifying regions of interest from three-dimensional (3D) anatomical image data. An example method includes analyzing a three-dimensional (3D) data set of one or more medical images using an artificial intelligence (Al) model to identify two-dimensional (2D) regions of interest in the 3D data set having an increased probability of a diagnostic state, and providing the regions of interest to another process for additional analysis. In some embodiments, said analyzing the 3D data set includes generating a 3D heat map, a 3D segmentation, or both, of the 3D data set using the Al model, and identifying the regions of interest using another Al model, wherein each region of the regions of interest includes a respective 2D data set.

DETERMINATION OF DIRECTION REVERSAL EXITS FOR ROBOTICALLY CONTROLLED ENDOSCOPES

Resumen de: US20260199043A1

0000 A method for robotically controlling an endoscope comprises: navigating an elongate shaft in a patient body, the elongate shaft including a tip at a distal end, articulating the tip in a first direction with a first pull wire coupled to a dual-wire pulley, reversing articulation of the tip to a second direction with a second pull wire coupled to the dual-wire pulley based on a nonlinear response region of a kinematic model, determining an end point of the nonlinear response region, and, when articulation of the tip in the second direction reaches the end point, articulating the tip based on a linear response region.

SYSTEMS AND METHODS FOR TRANSPORT AND DISTRACTION

Resumen de: AU2024394477A1

A transport device for increasing biological activity within a patient includes a base including a first end, a second end, an upper surface located between the first end and the second end, and a lower surface located between the first end and the second end, a base anchor configured to statically couple the base to a first portion of a bone of a subject, a translatable anchor configured to engage a growth stimulator, a leadscrew dynamically coupling the base to the translatable anchor, wherein the leadscrew is configured to rotate about a leadscrew axis while substantially maintaining its longitudinal position along the leadscrew axis in relation to the base, such that the growth stimulator, when engaged with the translatable anchor, is capable of independent movement in relation to the base along a stimulation axis that includes at least some transverse displacement with respect to the bone when the base is coupled to the bone via the base anchor, and a screw drive rotatably coupled to the leadscrew and configured to couple to a rotatable mating tool that is configured to rotate the leadscrew via the screw drive.

SYSTEM AND METHOD FOR TRACKING INTRA-BODY STEERABLE ASSEMBLY

Resumen de: US20260199021A1

A system and method for determining positional information of a steerable assembly within a body (optionally comprising an animal (e.g., human) body) utilizes a rigid guide tube having a bore through which the steerable assembly and Fiber Bragg Grating (FBG) sensors, the guide tube having a non-linear shape that is conferred to the steerable assembly and is detectable by a FBG detector to define an origin of the steerable assembly. Continued passage of the steerable assembly through the rigid guide tube at a gate position thereof causes the origin to change with time, and the origin is used in conjunction with the FBG sensors to determine a 3D trajectory of the steerable assembly in the body. The 3D trajectory may be further updated responsive to sensing of relative position and relative orientation between the guide tube and the body.

3D PRINTING OF HIGH CELL DENSITY VASCULARIZED TISSUE

Resumen de: US20260199555A1

0000 A composition and method for 3D bioprinting adds a contrast agent having a relatively high refractive index to a photopolymerizable bioink composition in which cells are encapsulated so that the refractive index of the composition substantially matches the refractive index of the encapsulated cells.

EVALUATING MORPHOLOGY AND OPERATION OF A JOINT

Resumen de: US20260204382A1

0000 Described herein are example techniques for evaluating morphology and/or operation of a joint of an animal. In embodiments, a computer model of the joint is prepared and analyzed. An amount of translation movement and an amount of rotation movement to be simulated are determined and used in simulated movement of the bone(s) of the joint across many different positions. The positions that are simulated with the computer model may correspond to different positions of the bone during operation of the joint, such as (in the case of a human hip joint) positions a bone may take during walking, running, or other movements. These positions may be automatically simulated based on the amounts of translation and rotation. In some embodiments, determined information regarding the morphology and/or operation of the joint from the simulation may be used to determine a recommendation of whether and/or how to treat improper operation of the joint.

RADIATION DOSIMETRY APPARATUS AND RELATED METHODS

Resumen de: US20260199706A1

A radiation dosimetry apparatus comprises a body that supports scintillator elements that emit light when exposed to radiation. The body may be shaped to conform to contours of a portion of a patient's anatomy. Radiation intensity and dose may be determined by processing images obtained by one or more cameras to measure intensity of light emitted by different ones of the scintillator elements. The scintillator elements may be distributed non-uniformly based on a patient-specific radiation treatment plan. Scintillator elements may be arranged to provide increased spatial resolution and/or dose resolution in higher dose regions and/or regions corresponding to organs at risk. Radiation dosimeter apparatuses may be fabricated by additive manufacturing. Design and fabrication of the radiation dosimetry apparatuses may be integrated into workflows in clinical radiation treatment settings. Methods and systems for fabricating, calibrating, and using the radiation dosimetry apparatuses are described.

TECHNIQUES FOR SECURING MODELS USING A BALL PLUNGER

Resumen de: US20260200166A1

0000 The present disclosure discusses techniques for securing thermoform models, including a locator plate for receiving and securing individually unique dental models having a polygon cutout, wherein the locator plate has at least one ball plunger positioned within a raised polygon, the at least one ball plunger having a cylindrical body, a spring, and a ball extending partially outside the cylindrical body. The present disclosure also includes a system for thermoforming an orthodontic aligner and methods thereof.

A METHOD FOR GENERATING A TRAY INSTRUMENT LAYOUT

Resumen de: US20260204407A1

The present disclosure generally relates to a method for generating a tray instrument layout, where the tray instrument layout is adapted taking into account a type of surgical procedure to be performed, available surgical instruments and a procedural order for performing the surgical procedure. The present disclosure further relates to a corresponding computer system and computer program product.

SWEAT SENSOR HAVING DUJIANGYAN-INSPIRED DIVERSION STRUCTURE

Resumen de: WO2026148698A1

The present invention relates to a sweat sensor having a Dujiangyan-inspired diversion structure. The sweat sensor comprises a detection layer and a sealing layer provided on the detection layer; the detection layer is provided with a sample collection hole, a sample flow channel communicated with the sample collection hole and extending to the outside of the detection layer, and a plurality of detection chambers arranged on one side of the sample flow channel; one end of each detection chamber is connected to the sample flow channel by means of a first flow channel, and the other end is connected to the sample flow channel by means of a second flow channel; the sample flow channel, the first flow channel, the detection chamber, and the second flow channel define a diversion dike; a sample enters the sample flow channel from the sample collection hole, and after being diverted by the diversion dikes, a part of the sample flows to the detection chambers along the first flow channels; a plurality of water stop grooves are provided on the side wall of the sample flow channel distant from the diversion dikes; and sample detection chips are arranged in the detection chambers. The sweat sensor designed in the present application exhibits reduced sweat evaporation loss and a more accurate sweat detection result.

3D PRINTED SPLINT OR CAST FOR AN ARTICULATING JOINT

Resumen de: US20260199118A1

0000 A splint, brace, or any other orthosis for supporting a patient's limb having an articulating joint includes first and second portions configured to connect to the patient's limb, a latching mechanism constructed of a strap, elastic material or fabric to connect the first and second portions and a lattice shape or holes placed automatically or manually by design software on first and second portions to provide air circulation. The first portion being configured for mounting to the patient's limb at a first side of the articulating joint and the second portion configured for mounting to the patient's limb at a second side of the articulating joint.

DEVICES, SYSTEMS, AND METHODS FOR DETECTION OF MEDICAL DEVICE

Resumen de: US20260199627A1

0000 An air adapter tube for diagnosis and/or treatment of a respiratory disorder includes a tubular body configured to transport pressurized treatment air between a proximal end of the tubular body and a distal end of the tubular body, the proximal end being configured to connect to a patient interface, and the distal end being configured for connection to an air delivery tube; and a sensor being configured to generate a signal based on air passing at the proximal end for diagnosis and/or treatment of a respiratory disorder.

A METHOD FOR PRODUCING A THREE-DIMENSIONAL MICROPOROUS FILAMENT CONSTRUCT

Resumen de: US20260199977A1

A method for producing a three-dimensional macro-porous filament construct having interconnected microporous filaments may include preparing a mixture of particles of metal(s), metal alloy(s), binder(s), a first liquid solvent for the binder(s), and optionally dispersant(s). Particles containing a removable additive are dispersed in the mixture. The mixture is deposited in a three-dimensional pattern of interconnected filaments, creating a three-dimensional filament-based porous green structure that is then contacted with a second solvent (a non-solvent for the binder(s)) to induce phase inversion. At least part of the filaments are transformed to a solid state. The removable additive is removed to create additional micro-porosity in the phase inverted porous structure, and the structure is subjected to a thermal treatment. The removal agent includes the second liquid solvent or is a third liquid solvent distinct from the second.

Neural Network Techniques for Appliance Creation in Digital Oral Care

Resumen de: US20260199058A1

0000 Systems and methods are disclosed for generating a three-dimensional (3D) representation of oral care data for use in oral care treatment. The systems and methods involve receiving an input 3D representation of a patient's dentition and encoding the 3D representation into a lower-dimensional first latent representation using a trained first machine learning (ML) module. Subsequently, a trained second ML module, comprising a trained transformer encoder model or a trained transformer decoder model, is executed to generate a second latent representation using the first latent representation. The second latent representation is then reconstructed into a 3D oral care representation (e.g., a tooth restoration design, an appliance component, a fixture model component, etc.) by a decoder. Finally, the processing circuitry outputs the reconstructed 3D representation of oral care data. These systems and methods enable efficient and accurate generation of oral care data, facilitating improved oral care appliance generation, treatment planning and analysis.

Transformers for Final Setups and Intermediate Staging in Clear Tray Aligners

Resumen de: US20260199057A1

0000 Systems and technique are disclosed for generating transforms and oral care appliances for oral care treatment. The method involves receiving a first three-dimensional (3D) representation of oral care data and utilizing processing circuitry to execute a machine learning (ML) model that includes at least one transformer. The ML model generates at least one transform based on the input data. The processing circuitry applies the generated transform to the first 3D representation, placing it in a desired pose relative to a second 3D representation or a global coordinate system axis. Based on this application, the method further generates aspects of one or more oral care appliances associated with either the first 3D representation or the second 3D representation. These systems and techniques enable the efficient generation of transforms and oral care appliances, facilitating improved treatment planning and customization in oral care applications.

MOLD OF BIODEGRADABLE MATERIAL FOR DENTAL ALIGNER AND METHOD OF MANUFACTURE THEREFOR

Nº publicación: US20260199062A1 16/07/2026

Solicitante:

STRATASYS INC [US]
Stratasys, Inc.

Resumen de: US20260199062A1

The invention is in the field of additive manufacturing. There is provided a positive model of one or more teeth and/or gum, suitable for producing a dental aligner, the model comprising a polyhydroxyalkanoate (PHA). There is also provided such a model, comprising sintering or fusing a powder comprising a polyhydroxyalkanoate (PHA).