Abstract: A trans-abdominal non-invasive fetal blood oxygen saturation detection device comprises a trans-abdominal fetal oximeter and a signal detection assembly connected to the trans-abdominal fetal oximeter. The trans-abdominal oximeter comprises a signal processing controller. The signal detection assembly comprises a light-emitting light source device and a light receiving device, wherein the light-emitting light source device, the light receiving device and a reference signal detection device are all connected to the signal processing controller. The light-emitting light source device irradiates two or more different wavelengths of light into the abdominal cavity of a pregnant woman.

Abstract: A universal electrochemical micro-sensor can be used either as a biosensor or an environmental sensor. Because of its small size and flexibility, the micro-sensor is suitable for continuous use to monitor fluids within a live subject, or as an environmental monitor. The micro-sensor can be formed on a reusable glass carrier substrate. A flexible polymer backing, together with a set of electrodes, forms a reservoir that contains an electrolytic fluid chemical reagent. During fabrication, the glass carrier substrate protects the fluid chemical reagent from degradation. A conductive micromesh further contains the reagent while allowing partial exposure to the ambient biological or atmospheric environment. The micromesh density can be altered to accommodate fluid reagents having different viscosities. Flexibility is achieved by attaching a thick polymer tape and peeling away the micro-sensor from the glass carrier substrate.

Abstract: A multi-sensor non-invasive blood glucose monitoring instrument based on impedance spectroscopy-optical method, which belongs to a blood glucose measuring instrument for human body. The blood glucose monitoring instrument comprises a detection probe, a microprocessor, a display unit and a storage unit. The detection probe comprises a temperature and humidity sensor, an LED array, a photoelectric sensor, a pair of low-frequency electrodes, and a pair of high-frequency electrodes. The high-frequency electrode employs parallel electrodes, a matching inductor is directly soldered to the positive electrode or negative electrode of the electrode, and a shielding electrode is provided around the high-frequency electrode. The distance between the two low-frequency electrodes is 1 cm-2 m, and the low-frequency electrodes can test the low-frequency impedance of the tissue stably.

Abstract: A method for calibration of a photoplethysmographic device including the steps of providing a fluid circuit (305) for blood or other liquid, a pump mechanism (310) to generate pulsatile flow of blood through the fluid circuit, a sample of excised tissue (315) in the fluid circuit through which the blood flows, and a photoplethysmographic device including an emitter and a photodetector (330) positioned on the tissue (335, 340) so that a portion of the light output by the emitter passes through the tissue and is incident on the photodetector. The method further includes the steps of energizing the pump mechanism (420) to move the blood through the tissue, energizing the emitter (425) to output light, collecting paired data from the photodetector and from one or more reference measurements (430), and processing the paired data to calibrate the photoplethysmographic device (435).

Abstract: Systems and methods for processing sensor data and self-calibration are provided. In some embodiments, systems and methods are provided which are capable of calibrating a continuous analyte sensor based on an initial sensitivity, and then continuously performing self-calibration without using, or with reduced use of, reference measurements. In certain embodiments, a sensitivity of the analyte sensor is determined by applying an estimative algorithm that is a function of certain parameters. Also described herein are systems and methods for determining a property of an analyte sensor using a stimulus signal. The sensor property can be used to compensate sensor data for sensitivity drift, or determine another property associated with the sensor, such as temperature, sensor membrane damage, moisture ingress in sensor electronics, and scaling factors.

Abstract: Systems and methods for processing sensor data and self-calibration are provided. In some embodiments, systems and methods are provided which are capable of calibrating a continuous analyte sensor based on an initial sensitivity, and then continuously performing self-calibration without using, or with reduced use of, reference measurements. In certain embodiments, a sensitivity of the analyte sensor is determined by applying an estimative algorithm that is a function of certain parameters. Also described herein are systems and methods for determining a property of an analyte sensor using a stimulus signal. The sensor property can be used to compensate sensor data for sensitivity drift, or determine another property associated with the sensor, such as temperature, sensor membrane damage, moisture ingress in sensor electronics, and scaling factors.

Abstract: Systems and methods are disclosed which provide for a “factory-calibrated” sensor. In doing so, the systems and methods include predictive prospective modeling of sensor behavior, and also include predictive modeling of physiology. With these two correction factors, a consistent determination of sensitivity can be achieved, thus achieving factory calibration.

Abstract: Systems and methods for processing sensor data and calibration of the sensors are provided. In some embodiments, the method for calibrating at least one sensor data point from an analyte sensor comprises receiving a priori calibration distribution information; receiving one or more real-time inputs that may influence calibration of the analyte sensor; forming a posteriori calibration distribution information based on the one or more real-time inputs; and converting, in real-time, at least one sensor data point calibrated sensor data based on the a posteriori calibration distribution information.

Abstract: Provided is a technique for calculating an oxygen extraction fraction by using MRI where the oxygen extraction fraction in a brain including brain parenchyma is calculated via a simple processing without an impact on an examinee, such as administration of caffeine. For this purpose, an MRI apparatus of the present invention measures a complex image of nuclear magnetic resonance signals, and calculates from thus measured complex image, a physical property distribution for obtaining a physical property image reflecting the oxygen extraction fraction. Then, thus calculated physical property distribution is separated into tissue-specific physical property distributions for at least two tissues (separated tissue images). After converting any of the separated tissue images into the oxygen extraction fraction, a distribution of the oxygen extraction fraction is estimated based on the condition that a value of any selected pixel is substantially equal to a mean value of pixels surrounding the selected pixel.

Abstract: Disclosed herein are systems and methods for a continuous analyte sensor, such as a continuous glucose sensor. One such system utilizes first and second working electrodes to measure additional analyte or non-analyte related signal. Such measurements may provide a background and/or sensitivity measurement(s) for use in processing sensor data and may be used to trigger events such as digital filtering of data or suspending display of data.

Abstract: Example systems, methods, and apparatus, including cognitive platforms, are provided for applying signal detection metrics in computer-implemented adaptive response-deadline procedures to data collected based at least in part on user interaction(s) with computerized tasks and/or interferences. The apparatus can include a response classifier for generating a quantifier of the cognitive abilities of an individual. The apparatus also can be configured to adapt the tasks and/or interferences to enhance the individual's cognitive abilities.

Abstract: Provided are systems and methods for medical diagnosis. The systems and methods may identify a coherence between paired sensor data respectively measured from a first sensor attached to a head of a subject and a second sensor attached to a body part of the subject. The systems and methods may determine an amount of volition in the subject's body based on the coherence. The systems and methods may determine a diagnosis or a treatment plan for a subject based on the amount of volition. The system and methods may be used to track interaction between individuals in a clinical setting or in a social group.

Abstract: To maintain high estimation accuracy of the activity in the autonomic nerves. An information processing apparatus according to the present technology includes: a processing section that executes a process including a correction process of specifying noise included in perspiration data acquired by a perspiration sensor on a basis of sensor data acquired by a different type of sensor than the perspiration sensor, and removing the noise from the perspiration data. According to such a technology, noise estimated according to other sensor data can be removed from the perspiration data, making it possible to maintain high accuracy in a later process of estimating activity in the autonomic nerves.

Abstract: This disclosure relates to a magnetic resonance imaging device. The magnetic resonance imaging device includes an carrying unit; an imaging unit, a controlling computer, and a signal processing computer. The signal processing computer includes a controlling module, a data processing module, an image reconstructing module, an image storing module, and an image comparing module. The image reconstructing module forms cross-sectional scanned images of an user's brain memory showing microstructure. The image comparing module is configured to analyze and compare the cross-sectional scanned images of the user's brain memory showing microstructure captured at different times so that the controlling computer shows different suggestions corresponding to different judgement results of the image comparing module. The system may comprise a dementia monitoring system that provides users with advisory dementia warnings so users may be advised to seek further medical advice.

Abstract: Detecting of a disorder associated with impaired barrier function in the gastrointestinal tract of a subject is described, including through determining bioimpedance across a subject's gastrointestinal tract wall and detecting impaired barrier function based on bioimpedance. An electrical signal is measured between first and second electrodes, at least the first electrode being located in a gastrointestinal tract of the body and one or more characteristics are determined based on the measured electrical signal. The one or more characteristics can comprise hallmarks of impaired barrier function such as leakiness and/or permeability of the gastrointestinal tract and can provide an indication of inflammatory bowel disease and/or gut inflammation.

Abstract: A method of detecting colorectal cancers using a hyperspectral sensor system includes receiving a training set of hyperspectral data from colorectal tissue that includes known normal and known cancerous tissue using the hyperspectral sensor system, applying a machine learning algorithm to the training set of hyperspectral data to provide predictor parameters for one of cancerous tissue or non-cancerous tissue, receiving measurement hyperspectral data from colorectal tissue of interest, and using the predictor parameters to classify the colorectal tissue of interest as one of cancerous tissue or non-cancerous tissue. The training set of hyperspectral data and the measurement hyperspectral data include reflection spectra across wavelength bands of light that include at least visible, near infrared and short-wave infrared regions of the electromagnetic spectrum.

Abstract: Reference imagery of dermatological conditions is compiled in a crowd-sourced database (contributed by clinicians and/or the lay public), together with associated diagnosis information. A user later submits a query image to the system (e.g., captured with a smartphone). Image-based derivatives for the query image are determined (e.g., color histograms, FFT-based metrics, etc.), and are compared against similar derivatives computed from the reference imagery. This comparison identifies diseases that are not consistent with the query image, and such information is reported to the user. Depending on the size of the database, and the specificity of the data, 90% or more of candidate conditions may be effectively ruled-out, possibly sparing the user from expensive and painful biopsy procedures, and granting some peace of mind (e.g., knowledge that an emerging pattern of small lesions on a forearm is probably not caused by shingles, bedbugs, malaria or AIDS).

Abstract: Systems and methods for reducing the chance that a patient will develop a bedsore may determine whether a caregiver physically approaches a patient and remains in close physical proximity to a patient for a time sufficient to perform a bedsore prevention action. If a planned bedsore prevention action does not appear to be performed, the systems and methods may alert the patient, the caregiver, or others. A determination may be made as to whether the patient's position has changed in a manner consistent with a bedsore prevention action.

Abstract: The present invention provides a system for selecting appropriate brain-training content for each user. The selection system includes: a storage unit for storing detection values obtained by detecting blood flow rates in the head of a user, identifiers for predetermined test content to be performed by the user at the time of the detection of the detection values, and an identifier for the user in association with one another; a calculation unit for calculating, on the basis of the detection values stored in the storage unit, brain-activity values indicating the degree of brain-activity of the user when the predetermined test content is performed by the user; and a selection unit for selecting, on the basis of the brain-activity values calculated by the calculation unit during performance of the predetermined test content, brain-training content to be performed by the user.

Abstract: Embodiments of the present disclosure provide a device for determining a location of a blood vessel and a method thereof. The device includes a plurality of sensors, a processor, and an indicating device. The plurality of sensors may detect pressure values at a plurality of skin locations in contact with the plurality of sensors. The processor may determine the location of the blood vessel based on the pressure values. The pressure value at the skin location corresponding to the location of the blood vessel is greater than the pressure values at both sides of the skin location in a direction perpendicular to a direction of the blood vessel. The indicating device may indicate the location of the blood vessel.

Abstract: The invention relates to a respiratory gas analyzer for analyzing a respiratory gas, which is configured to determine at least one sleep stage from the respiratory gas and to determine a sleep quality based on the sleep stage. Furthermore, the invention relates to a respirator which comprises such a respiratory gas analyzer, to a device for carrying out a polygraph and/or polysomnograph, which comprises such a respiratory gas analyzer, and to a method for controlling a respirator which comprises such a respiratory gas analyzer.

Abstract: A method for measuring life parameters during sleep by a device including an accelerometer attached to the body of a sleeping subject. The method includes: (a) setting a hysteresis width having a maximum hysteresis value and a minimum hysteresis value; (b) reading, from the accelerometer, values of acceleration in three axes; (c) filtering the values of acceleration in each of the three axes with a band-pass filter to obtain filtered acceleration signals; (d) combining the filtered acceleration signals to obtain a signal level; (e) checking whether the signal level is higher than the current maximum hysteresis value and if so, setting the maximum hysteresis value to the signal level and setting the minimum hysteresis value to the maximum hysteresis value decreased by the hysteresis width; and (f) signaling a breath detection when detecting a transition from a falling edge to a raising edge.

Abstract: A system and method for monitoring a patient's compliance with a medication regimen includes an electronic tag integral with or attached to a medicine delivery device such as a capsule, the tag having an antenna and a receiver/transmitter, the system also including a reader positioned externally for detecting the presence and location of the delivery device in the patient.

Abstract: A biosignal detecting garment includes: a crop top type or brassiere type garment body; an under belt that have a fastening tool capable of adjusting a chest circumference size and that is disposed in a lower portion of the garment body; at least two electrodes formed of an electroconductive fiber; a connector for installing a measurement device configured to detect a biosignal; and a wiring portion configured to electrically connect the electrodes and the connector. The electrodes, the connector, and the wiring portion are installed in the under belt, the garment body has a length from an apex of a shoulder portion of the garment body to an upper portion of the under belt of 20.0 cm or more and 35.0 cm or less, and the under belt is formed in a bag shape with two pieces stacked.

Abstract: A disposable patient interface includes a reusable sensor that removably mounts within a shoe of the disposable patient interface when at least one protrusion on opposite ends of the sensor removably lock with corresponding at least one aperture on opposite portions of the shoe. The patient interface includes a compliant structure which conforms to a patient's body upon placement thereon without causing wrinkles in the compliant structure so as to maximize adhesion of the compliant structure against skin on the patient's body when the compliant structure is conformed to muscle underlying skin on the patient's body.

Abstract: The described embodiments relate to a sensor patch that can be temporarily removed and re-applied in the same location using a side element of the sensor patch. The side element can be folded onto the sensor patch when the sensor patch is adhered to an object such as an appendage of a person. The side element can be unfolded and adhered to the appendage in order to preserve the placement of the sensor patch on the appendage. In this way, maintenance such as cleaning can be performed on the area where the sensor patch is located without having to dispose of the sensor patch. Once maintenance is completed, the side element can be folded back onto a surface of the sensor patch until maintenance is to be performed again.

Abstract: The invention relates to evaluation of maturity of arteriovenous (AV) fistula using guidewires that measure intravascular blood flow and/or pressure. The invention provides methods of evaluating AV fistula maturation using an instrumented guidewire to measure intravascular flow and/or pressure. By using a small diameter guidewire that does not interfere substantially with the flow, an accurate measurement can be made that is useful for identifying when a fistula is mature and therefore ready to be used for hemodialysis. The flow of blood through the fistula is measured using the guidewire and the measured flow and/or pressure of blood is used to determine if the fistula is mature.

Abstract: An implantable intravascular anchor for supporting a device inside a vascular lumen, the anchor comprising a first part configured to expand when extending from a catheter, and to collapse upon retraction into said catheter; a second part for supporting the device in the lumen and a third part, proximal to the first part, and configured so that, upon release from the catheter, it expands in width to engage an interior wall of the lumen and is adapted for securing the anchor against axial movement along the lumen.

Abstract: A hand-held device, such as a remote control, is provided for operation of a consumer appliance and is equipped with one or more biometric sensors to capture and report on the health condition of a user of the hand-held device. The data captured by such a hand-held device may be evaluated locally in the hand-held device itself or may be conveyed to a target consumer appliance either for local evaluation by that consumer appliance or for onward transmission to a central off-site monitoring service.

Abstract: System for filtering cardiac signals. The system includes: cardiac terminals (10a-d) adapted to collect cardiac electrophysiological potentials from a plurality of cardiac electrodes (1a-d) placed at respective cardiac locations in or on an individual (99) and a processor device (40) adapted to process one or more input signals, which are based on the collected electrophysiological potential(s). The processing includes running an adaptive filter algorithm on one or more signals based on the input signals. The adaptive filter algorithm is arranged to calculate estimated noise component(s) of the signals and arranged to subtract the estimated noise component(s) from the signals. In this way a cardiac signal is derived where the noise has been significantly reduced.

Abstract: A method of estimating concentration of a blood compound may include: removing a baseline drift from Near-Infrared (NIR) spectroscopy data to obtain drift-free spectral features; obtaining a set of global features based on the drift-free spectral features; and estimating the concentration of the blood compound by regression using the set of global features.

Abstract: Embodiments describing an approach for detecting user biomarker identifier changes based on audio preferences and generating biometric alerts based on the detected biomarker identifier changes. Receiving a user's current audio preferences. Retrieving the user's historic audio preferences and biometric data associated with the user's historic audio preferences. Analyzing the user's current audio preferences based on the user's historic audio preferences and the biometric data associated with the historic audio preferences. Creating a user biometric profile based on analyzing the user's current audio preferences, the user's historic audio preferences and the biometric data associated with the user's historic audio preferences; and outputting the user biometric profile.

Abstract: Methods and systems for stationary computed tomography are disclosed. The methods and systems include a gantry having alternating x-ray sources and x-ray detectors that are stationary during operation of the system. The gantry and pairs of x-ray sources and detectors substantially surrounds an object positioned inside the gantry during operation of the system. Dynamically adjustable collimators are positioned between the x-ray sources and the object. Each of the x-ray sources projects an x-ray beam through the collimators and through the object and the x-ray detectors receive the x-ray beam. The x-ray detectors include means for converting the x-ray beam to raw image data. One or more microprocessors control the x-ray sources and the process raw image data. A data storage device stores instructions, which upon execution by the microprocessor, control the x-ray sources and process the raw image data by converting the raw image data to a digital image.

Abstract: One or more optical video cameras connected to a monitor correlated to the position of a medical imaging device or patient allows the medical imaging device user to properly align the medical imaging device with respect to the patient for optimal patient medical imaging. The positioning device is used to reduce radiation exposure in modalities using ionizing radiation by allowing optical patient tracking rather than radiation dependent visualization. In all modalities that do or do not use ionizing radiation, it can be used to improve initial patient and/or medical imaging device position and allow users a visual feedback tool to correctly position the patient and/or medical imaging device during the exam.

Abstract: A method is provided for running a collision protection system for a medical operating device, which has a patient bed for a patient to be operated on, an image recording device having at least one movable image recording component for recording image data of the patient during the operation, and an assistance robot having a movable assistance component which during the operation is situated at least temporarily inside the patient and/or is coupled in terms of movement to an instrument situated inside the patient. In the method, an item of criticality information is determined which describes the criticality of possible collisions of components of the operating device and/or movements of the patient with regard to the interaction of the assistance robot with the patient. Depending upon the criticality information, when a criticality criterion indicating a raised criticality, (e.g.

Abstract: A cannula and method include a shaft portion having a proximal end, a distal end, a longitudinal axis and a lumen extending from the proximal end to the oppositely disposed distal end along the longitudinal axis. A hub is attached to the proximal end of the shaft portion and includes a transverse portion, which extends transversely relative to the longitudinal axis of the shaft portion. An opaque marker is disposed on the transverse portion at a position corresponding to an expanded size of an expandable element such that the opaque marker indicates the expanded size in an imaging system image.

Abstract: Disclosed is a multi-axially variable detection module of a PET apparatus, the detection module including: a gantry having a through-hole extending from a side to an opposite side of the gantry; a detection module in which a plurality of detectors for detecting gamma rays emitted from a subject are arranged annularly along an inner circumference of the gantry; and a driving means for moving the plurality of detectors constituting the detection module in a radial direction of the detection module, wherein each of the plurality of detectors is rotatable in a longitudinal direction of the detection module to vary a length thereof in the longitudinal direction, and each of the plurality of detectors include multiple detector elements which are engaged with each other in a hinged manner in a transverse direction (circumferential direction) of the detection module to form a flat or an arc shape.

Abstract: An X-ray imaging system includes an X-ray Talbot; imaging apparatus and an image processing apparatus. The image processing apparatus generates reconstruction images from the moire image taken by the X-ray Talbot imaging apparatus. The reconstruction images include a differential phase image, an absorption image and a small-angle scattering image. The X-ray imaging system performs X-ray Talbot imaging and normal X-ray imaging. X-ray Talbot imaging includes setting an exposure energy of the X-ray Talbot imaging apparatus to a first exposure energy and taking the moire image with the X-ray detector. Normal X-ray imaging includes setting the exposure energy of the X-ray Talbot imaging apparatus to a second exposure energy and taking an absorption contrast image with the X-ray detector by normal X-ray imaging.

Abstract: In a method for producing a microstructure component, which is used in particular as an x-ray phase contrast grating in an x-ray device, a material absorbing x-rays is poured into a mold able at least to be deformed about one bending axis, which is formed by a silicon substrate and which has a plurality of cutouts running in a direction of the thickness of the silicon substrate with dimensions in the micrometer range. The mold into which the material is poured is heated up to a working temperature value lying above the room temperature and below a melting temperature value of the material which is poured into it and is formed into a final contour as per specifications.

Abstract: The present invention comprises: a first X-ray irradiation apparatus and a second X-ray irradiation apparatus for irradiating a subject with X-rays; an X-ray generation unit supporting so that first and second X-rays irradiated onto the subject are detected by a set detector when the subject is irradiated with the first and second X-rays from the first and second X-ray irradiation apparatuses, respectively; and a mode selection unit for allowing selection of any one mode from among a 2D imaging mode and 3D imaging mode, wherein the angles with respect to the subject of the first and second X-ray irradiation apparatuses are determined on the basis of said any one mode selected by means of the mode selection unit from among the 2D imaging mode and 3D imaging mode. According to the present invention, the mode can be easily selected according to need from among the 2D imaging mode and 3D imaging mode.

Abstract: A medical imaging apparatus includes a radiology workstation (10) with a workstation display (14) and one or more workstation user input devices (16). A medical imaging device controller (26) includes a controller display (30) and one or more controller user input devices (32). The medical imaging device controller is connected to control a medical imaging device (40) to acquire medical images (44).

Abstract: In an X-ray imaging apparatus, an image processor concurrently displays, on an image display, a long image in which a frame indicating an imaging range of an imager is displayed and an X-ray image or a processed image containing position information that overlaps at least with position information of the frame.

Abstract: A method and apparatus correct a computed tomography (CT) image with motion artifacts. The method of correcting a CT image may include: obtaining a reconstruction image of an object by reconstructing an X-ray projection image; measuring a parameter value related to motion artifacts that occur due to movement of the object in at least one of the X-ray projection image or the reconstruction image; calculating a correction possibility for the reconstruction image based on the measured parameter value; and determining whether to perform correction on the reconstruction image based on the calculated correction possibility.

Abstract: An X-ray fluoroscopy imaging apparatus that confirms the radiation field of a radiation imaging when an operator performs an examination in an operation room. A collimator 12 has a plurality of collimator-leaves 61 positioned and forming a first X-ray radiation field E1 while performing an X-ray fluoroscopy. The apparatus allows an operator, in an operating room distant from an imaging room, to operate an aperture change to confirm the radiation field and each of the collimator-leaves 61 shifts to a position where the X-ray radiation field is reduced to a smaller dimension field E2. Visualizing a displayed X-ray image allows the operator to confirm reaching the radiation field E2.

Abstract: A system includes a probe configured to transmit ultrasound signals to a target blood vessel, and receive echo information associated with the transmitted ultrasound signals. The system may also include at least one processing device configured process the received echo information and generate an ultrasound image of the blood vessel and identify a seed position within the blood vessel based on the ultrasound image. The at least one processing device may further generate an estimated contour for a lumen of the blood vessel based on pixel intensity values associated with the ultrasound image, generate an estimated contour for the blood vessel using the pixel intensity values, determine whether a thrombus exists within the blood vessel and output image information illustrating the estimated contours of the lumen and the blood vessel.

Abstract: Described are methods and systems and system components useful for percutaneously delivering or retrieving vascular implant devices, such as filters, utilizing intravenous ultrasound (IVUS) imaging alone or in combination with external (e.g. transabdominal) ultrasound or other imaging technology. Implants deliverable by such systems, such as vena cava or other vascular filters, can have two or more echogenic markers spaced at such a distance that they are separately discernible by IVUS and/or external ultrasound imaging.

Abstract: The present invention relates to a system for indicating a position of an interventional device feature (11a) of an interventional device (11) respective an image plane (12) defined by an ultrasound imaging probe (18) of a beamforming ultrasound imaging system (15) in which the position of the interventional device feature (11a) is determined based on ultrasound signals transmitted between the ultrasound imaging probe (18) and an ultrasound transducer (16) attached to the interventional device at a predetermined distance (Lp) from the interventional device feature (11a). An icon providing unit (IPU) provides a first icon (Cde) indicative of a circular zone with a radius corresponding to the predetermined distance (Lp). The first icon (Cde) is displayed in a fused image that includes a reconstructed ultrasound image (RUI) from the beamforming ultrasound imaging system.

Abstract: For three-dimensional segmentation from two-dimensional intracardiac echocardiography imaging, the three-dimension segmentation is output by a machine-learnt multi-task generator. Rather than the brute force approach of training the generator from 2D ICE images to output a 2D segmentation, the generator is trained from 3D information, such as a sparse ICE volume assembled from the 2D ICE images. Where sufficient ground truth data is not available, computed tomography or magnetic resonance data may be used as the ground truth for the sample sparse ICE volumes. The generator is trained to output both the 3D segmentation and a complete volume (i.e., more voxels represented than in the sparse ICE volume). The 3D segmentation may be further used to project to 2D as an input with an ICE image to another network trained to output a 2D segmentation for the ICE image. Display of the 3D segmentation and/or 2D segmentation may guide ablation of tissue in the patient.

Abstract: A system for determining orientation of a distal end of a catheter. The system includes a flexible shaft having a first lumen, a second lumen, a third lumen, a fourth lumen, a first orientation pin and a second orientation pin. The first orientation pin is received within the third lumen and the second orientation pin is received within the fourth lumen. The flexible shaft includes a cross-sectional dimension and the third lumen and the fourth lumen include longitudinal axes that are located on the same half of the cross-sectional dimension of the catheter. The second lumen includes an exit port for exposing at least a portion of the second lumen of the cap portion and a ramp. A distal end of the flexible shaft is made of material permeable to ultrasound signals and the orientation pins include one or more materials that are non-permeable to ultrasound signals.

Abstract: The invention relates to an ultrasound head (2), to a medical observation device (1) and to a method for observing live biological tissue (4). In order to provide the surgeon with a means of quickly gaining information on sub-surface structure in the surgical area during the operation, the method comprises the steps of contacting the tissue (4) with an ultrasound head (2) and recording ultrasound data (36) and optical image data (34) through the ultrasound head (2). The ultrasound head (2) comprises a sensor side (6) for contacting the tissue (4) and an ultrasound receiver (10). The sensor side (6) is at least sectionwise optically transparent so that light may enter the ultrasound head (2).