Abstract: The cutting device for the placement of a knee prosthesis includes a bracket and a cutting guide mounted with the ability to move on the bracket. The bracket includes a first marker for identifying it and a fixing element for fixing it to a bone. The cutting guide includes a second marker for identifying it and a slot defining a cutting plane suited to guiding a cutting tool. The invention also relates to an assistance device and to a system having the cutting device. The invention finally relates to an assistance method and to a computer program product and to a data recording medium for executing the method.

Abstract: Drug delivery devices and methods are provided for delivering one or more drugs into a biological tissue. The devices include microneedles that may be separable from the drug delivery devices, control drug release rate and/or direction, or a combination thereof. When the microneedles are separable, a force applied to the drug delivery devices may be effective to penetrate a biological tissue with the microneedles and then to separate the microneedles from the drug delivery devices. The drug delivery devices may be capable of achieving discrete periods of drug release. Methods for delivery drug with microneedles also are provided.

Abstract: The method of performing an operation on a body part of a patient uses a mixed reality (MR) device worn by the user. A visual representation of an operating scene includes a virtual anatomical feature representing an actual anatomical feature of the patient. A position and/or orientation of the visual representation relative to the anatomical feature of the patient is first adjusted to be superposed with the anatomical feature of the patient. The visual representation is displayed by the MR device superposed with the anatomical feature of the patient in a field of vision of the user. The position and/or orientation of the visual representation is repeatedly or continuously adjusted, so that, when the MR device moves relative to the anatomical feature of the patient, the visual representation remains superposed with the anatomical feature of the patient.

Abstract: A method for visualizing patient dentition acquires a contour image of patient dentition and segments the contour image to identify one or more segmented teeth. At least one deciduous tooth among the one or more segmented teeth is identified. A virtual model of a target dentition arrangement of the patient dentition is generated, wherein the at least one deciduous tooth is replaced by a replacement permanent tooth.

Abstract: A microneedle array is provided for administrating a drug or other substance into a biological tissue. The array includes a base substrate; a primary funnel portion extending from one side of the base substrate; and two or more solid microneedles extending from the primary funnel portion, wherein the two or more microneedles comprise the substance of interest. Methods for making an array of microneedles are also provided. The method may include providing a non-porous and gas-permeable mold having a two or more cavities each of which defines a microneedle; filling the cavities with a fluid material which includes a substance of interest and a liquid vehicle; drying the fluid material to remove at least a portion of the liquid vehicle and form a plurality of microneedles that include the substance of interest, wherein the filling is conducted with a pressure differential applied between opposed surfaces of the mold.

Abstract: A microneedle array is provided for administrating a drug or other substance into a biological tissue. The array includes a base substrate; a primary funnel portion extending from one side of the base substrate; and two or more solid microneedles extending from the primary funnel portion, wherein the two or more microneedles comprise the substance of interest. Methods for making an array of microneedles are also provided. The method may include providing a non-porous and gas-permeable mold having a two or more cavities each of which defines a microneedle; filling the cavities with a fluid material which includes a substance of interest and a liquid vehicle; drying the fluid material to remove at least a portion of the liquid vehicle and form a plurality of microneedles that include the substance of interest, wherein the filling is conducted with a pressure differential applied between opposed surfaces of the mold.

Abstract: Microneedle patches and systems, and methods for use of such patches and systems. In one aspect, a microneedle patch is provided including a tab portion for handling the microneedle patch. In another aspect, a system is provided including a microneedle patch and a tray for housing the microneedle patch. In still another aspect, various indicators providing for providing feedback prior to, during, and after administration of the microneedle patch are provided. Advantageously, the described microneedle patches and systems provide improved handling and ease of application of the microneedle patches to skin for the delivery of therapeutic agents.

Abstract: Method for automatically assigning numeric labels to teeth in a dental arch map provides a segmented 3D surface image of patient dentition having identified individual teeth and determined tooth position in the dental arch. A tooth contour for the identified teeth is defined. The tooth type is identified as one of incisor, canine, premolar, or molar. A display of the tooth contour is labeled with an assigned tooth number according to the tooth position, tooth contour, and tooth type. The labeled mapping is displayed.

Abstract: Method and/or apparatus embodiments for 3-D cephalometric analysis of a patient according to the application can display reconstructed volume image data from a computed tomographic scan of a patient's head including segmented dentition elements having an initial arrangement from one or more 2D/3D views; can compute and display a plurality of cephalometric parameters for the patient according to the reconstructed volume image data; then use the patient specific cephalometric parameters and population biometry data, to identify one or more maxillofacial/dental abnormalities; and compose patient specific treatment plans to correct selected dentition abnormalities using maxillofacial/dental structure, which can be composed in a final tooth arrangement in a final virtual CT volume. One or more aligners can be generated to incrementally move dentition from the initial arrangement to the final tooth arrangement.

Abstract: Microneedle patches and systems, and methods for use of such patches and systems. In one aspect, a microneedle patch is provided including a tab portion for handling the microneedle patch. In another aspect, a system is provided including a microneedle patch and a tray for housing the microneedle patch. In still another aspect, various indicators providing for providing feedback prior to, during, and after administration of the microneedle patch are provided. Advantageously, the described microneedle patches and systems provide improved handling and ease of application of the microneedle patches to skin for the delivery of therapeutic agents.

Abstract: The method of fitting a knee prosthesis in a knee of a patient includes displaying, by a visual display device of a mobile augmented reality navigation system worn or carried by a user performing or assisting at least one navigation-assisted stage of the method, at least one visual element superposed on a view of at least a portion of a surgical scene of the fitting of the knee prosthesis. The visual element can be a 3D model of at least one portion of the knee of the patient, a 3D model of another component of the surgical scene, information relative to the at least one portion of the knee of the patient, and/or information relative to the other component of the surgical scene.

Abstract: Method and/or apparatus embodiments can provide a virtual orthodontic base, adapted to each virtual 3D dental model of the teeth (e.g., upper and lower jaw). The virtual orthodontic base should match each 3D model (e.g., size), conform to prescribed dimensional requirements and still be rapidly calculated. The 3D virtual teeth model can be provided or reconstructed (e.g., from a laser scanning, intra oral camera scanning or x-ray scan of a plaster, a negative impression (e.g., alginate or silicon) of a patient's dentition or directly from the patient's mouth).

Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.

Abstract: A method for generating a dental arch map for a patient acquires a 3D surface image of patient dentition and automatically segments the 3D surface image to identify individual teeth. A mapping of outlines is formed for the identified teeth. The mapping is labeled according to a tooth numbering scheme and the labeled mapping is displayed.

Abstract: A neural network system is proposed to select actions to be performed by an agent interacting with an environment to perform a task in an attempt to achieve a specified result. The system may include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.

Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.

Abstract: The devices 400, 500 include microneedles 450, 550 that may be separable from the drug delivery devices, control drug release rate and/or direction, or a combination thereof. When the microneedles are separable, a force applied to the drug delivery devices may be effective to penetrate a biological tissue with the microneedles and then to separate the microneedles from the drug delivery devices. The drug delivery devices may be capable of achieving discrete periods of drug release.

Abstract: A neural network system is proposed to select actions to be performed by an agent interacting with an environment to perform a task in an attempt to achieve a specified result. The system may include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.