Abstract: Embodiments described herein provide various examples of a surgical video analysis system for segmenting surgical videos of a given surgical procedure into shorter video segments and labeling/tagging these video segments with multiple categories of machine learning descriptors. In one aspect, a process for processing surgical videos recorded during performed surgeries of a surgical procedure includes the steps of: receiving a diverse set of surgical videos associated with the surgical procedure; receiving a set of predefined phases for the surgical procedure and a set of machine learning descriptors identified for each predefined phase in the set of predefined phases; for each received surgical video, segmenting the surgical video into a set of video segments based on the set of predefined phases and for each segment of the surgical video of a given predefined phase, annotating the video segment with a corresponding set of machine learning descriptors for the given predefined phase.

Abstract: A method for calculating coronary artery fractional flow reserve includes determining myocardial volume by extracting myocardial images; locating a coronary artery inlet and accurately segmenting coronary arteries; generating a grid model required for calculation by edge detection of coronary artery volume data; determining myocardial blood flow in a rest state and CFR by non-invasive measurement; calculating the total flow at the coronary artery inlet in a maximum hyperemia state; determining the flow in different blood vessels in the coronary artery tree in the maximum hyperemia state and then determining flow velocity V1 in the maximum hyperemia state; using V1 as the flow velocity at the coronary artery inlet and calculating a pressure drop ?P from the coronary artery inlet to a distal end of a coronary stenosis, and a mean intracoronary pressure Pd at the distal end of the stenosis Pd=Pa??P, and calculating fractional flow reserve.

Abstract: Exemplary system, method, and computer-accessible medium can be provided for effectuating a video overlay during a medical procedure(s) performed on a patient(s) can include, for example, receiving a live video(s) of the medical procedure(s) performed on the patient(s), identifying, in real time, a target area(s), an area of danger(s) and/or at least partially obscured anatomical structures of significance on a patient's anatomy by applying a machine learning procedure to the live video(s), and providing the video overlay based on the identification of the target area(s) and the area of danger(s). The video overlay can be continuously modified, in real-time, using the machine learning procedure. The medical procedure(s) can be a gallbladder surgery. The machine learning procedure can include a neural network, which can be a convolutional neural network.

Abstract: The invention provides methods and apparatus for image processing that perform image segmentation on data sets in two- and/or three-dimensions so as to resolve structures that have the same or similar grey values (and that would otherwise render with the same or similar intensity values) and that, thereby, facilitate visualization and processing of those data sets.

Abstract: Disclosed is an intraluminal ultrasound imaging system, including a processor circuit in communication with an intraluminal ultrasound imaging catheter, and configured to receive a plurality of intraluminal ultrasound images from the imaging catheter during movement of the imaging catheter within a body lumen of a patient, the body lumen comprising a plurality of segments. The processor circuit is further configured to generate a marker to be applied to an intraluminal ultrasound image of the plurality of intraluminal ultrasound images, wherein the marker is generated based on the movement of the intraluminal ultrasound imaging catheter, and wherein the marker is representative of a segment of the plurality of segments, and output to a display the marker and the plurality of intraluminal ultrasound images shown successively.

Abstract: An example assembly for use with a vacuum system and an esophageal positioning device esophageal positioning device includes an introducer, in which the esophageal positioning device includes a handle, a first segment, a second segment and an articulation driving mechanism. The first segment being coupled to the handle. The second segment being pivotally connected to the first segment. The articulation driving mechanism being configured to pivot the second segment about the first segment upon articulation.

Abstract: A plant growth lighting fixture has two or more of a blue light source, a green light source, and a red light source and a reflective-type circularly polarizing plate having two or more of a blue-reflecting cholesteric liquid crystal layer having a center wavelength of an effective wavelength range in blue light, a green-reflecting cholesteric liquid crystal layer having a center wavelength of an effective wavelength range in green light, and a red-reflecting cholesteric liquid crystal layer having a center wavelength of an effective wavelength range in red light. The wavelength ranges of the emission center wavelengths as the light sources and the wavelength ranges of the center wavelength of the effective wavelength range as the reflective-type circularly polarizing plate are wavelength ranges of the same colors, and the reflective-type circularly polarizing plate has a polarization correction layer having a phase difference in a thickness direction.

Abstract: A magnetic manipulation system and method for moving and navigating a magnetic device in a body are provided. The system includes a robotic parallel mechanism having at least three electromagnets and at least three electromagnetic coils coupled to the at least three electromagnets, respectively. The electromagnetic coils are actuated to keep the electromagnets in static conditions or move the electromagnets along a desired trajectory, a current control unit supplying currents to the electromagnetic coils which have soft iron cores. The currents supplied by the control unit are configured to generate dynamic magnetic field in the soft iron core's linear region. The current control unit and the robotic parallel mechanism are configured to generate desired dynamic magnetic fields in desired positions within a workspace to control a magnetic device, and a three-dimensional position sensor is configured for performing a close loop control of the robotic parallel mechanism.

Abstract: A device to image registration method includes obtaining image data of a device, the device including a plurality of fiducials arranged as a fiducial frame on the device; detecting fiducial objects within the image data; cropping the image data to generate cropped image data; applying a feature enhancement to the cropped image data to enhance the fiducial objects; generating a candidate list of candidate objects based on the feature enhancement, and determining a common plane based on at least three points in the candidate list; determining a representative point for each candidate object; determining outlier candidate objects based on the common plane; determining resultant objects by extracting the outlier candidate objects from the candidate list; and registering the resultant objects to the device by matching the representative points of the resultant objects with a model of the fiducial frame.

Abstract: A method is provided for detecting an undesirable event or condition in a patient. The method may comprise receiving a first input signal from an UWB radar configured to monitor an environment occupied by the patient and including information representative of the patient's motion. Data derived from the first input signal is processed using a pattern recognition model to detect and classify patterns in the data derived from the first input signal as indicative or predictive of an undesirable event or condition involving the patient. When a pattern is classified as indicative or predictive of an undesirable event or condition in the patient an alarm is issued. A log of data derived from the first input signal and associated with a detection of a pattern classified as indicative or predictive of an undesirable event enables further machine learning in order to create an updated pattern recognition model based on individual patient behavior.

Abstract: A computer implemented method comprises receiving a model of a tissue region, steering a distal end of a catheter within a body to a first area of a tissue region, and obtaining a first image from the distal end of the catheter of the first area of the tissue region. The method further comprises mapping the first image of the first area of the tissue region to the model of the tissue region and displaying the first image of the first area of the tissue region on the model of the tissue region.

Abstract: An electrosurgical connection unit for a surgical robot arm to connect an electrosurgical instrument attached to the arm to an electrosurgical generator. The electrosurgical connection unit includes an input port connectable to the electrosurgical generator, the input port configured to receive a driving electrosurgical signal and output one or more activation signals; an output port connectable to the electrosurgical instrument, the output port configured to output the driving electrosurgical signal received on the input port; one or more activation switch units, wherein activation of an activation switch unit causes an activation signal to be output from the input port indicating a driving electrosurgical signal with a desired waveform is to be activated; and a control unit configured to selectively activate one of the one or more activation switch units in response to a control signal.

Abstract: A laser eye surgery system includes a laser to generate a laser beam. A topography measurement system measures corneal topography. A processor is coupled to the laser and the topography measurement system, the processor embodying instructions to measure a first corneal topography of the eye, A first curvature of the cornea is determined. A target curvature of the cornea that treats the eye is determined. A first set of incisions and a set of partial incisions in the cornea smaller than the first set of incisions are determined. The set of partial incisions is incised on the cornea by the laser beam. A second corneal topography is measured. A second curvature of the cornea is determined. The second curvature is determined to differ from the target curvature and a second set of incisions are determined. The second set of incisions is incised on the cornea.

Abstract: A method is for generating a synthetic mammogram. In an embodiment, the method incudes acquisition of a plurality of projection data sets at a plurality of projection angles; and generation of at least one synthetic mammogram with an image property essentially equivalent to a conventional full-field digital mammography acquisition based on several projection data sets.

Abstract: A railway track defect detection system may include a mobile defect detection platform and a modal parameter analyzer. The platform may include an excitation mechanism (e.g., an excitation hammer or wheels that are in contact with a railway track) to apply multiple impact forces to the railway track while the platform travels along the railway track, and a laser Doppler vibrometer to capture, while the platform travels along the railway track, vibration data representing vibrations of the railway track caused by application of the multiple impact forces by the excitation mechanism. The modal parameter analyzer may be configured to detect, based on the vibration data captured by the laser Doppler vibrometer, a defect in the railway track. For example, changes in vibration amplitudes, mode shapes, damping ratios, or a natural frequency derived from the received vibration data may indicate the presence of a defect in the railway track.

Abstract: This document relates to technologies of projecting an incision marker onto a patient using a movable gantry carrying a medical imaging system and at least one laser which is adjustable relative to the gantry. The medical imaging system is used for capturing a fluoroscopic or x-ray image of at least a part of the patient from a viewing direction. Then a virtual marker is set in the captured image in order to indicate a point or region of interest, for example as a point or at least one line of an incision. Then the laser is used to indicate, from a projection direction different from the viewing direction, the point or region of interest onto the surface of the patient, thus making the point or region of interest visible from the outside.

Abstract: A system for monitoring free flap patency includes transmit and receive transducers structured to be coupled to a blood vessel, and a plurality of circuitry modules structured to insonify a blood flow volume within the blood vessel and receive a scattered signal from the receive transducer, extract a baseband Doppler blood flow signal, VBASEBAND, from the scattered signal, extract a plurality of features from VBASEBAND, and classify the plurality of features and generate a binary signal based on the classification of the plurality of features, wherein the binary signal will have a first state responsive to the classification of the plurality of features indicating that a flow rate within the blood vessel is less than a predetermined level and a second state responsive to the classification of the plurality of features indicating the flow rate within the blood vessel is greater than or equal to the predetermined level.

Abstract: Z maps combined with a standardized stimulus in the form of a targeted arterial partial pressures of carbon dioxide provide surprisingly enhanced images for the assessment of pathological CVR. For example, the z-map assessment of patients with known steno-occlusive diseases of the cervico-cerebral vasculature showed an enhanced resolution of the presence, localization, and severity of the pathological CVR. Z-map have been found to be useful to reduce the confounding effects of test-to-test, subject-to-subject, and platform-to-platform variability for comparison of CVR images showing the importance of combining this analysis with the standardized stimulus.

Abstract: The present disclosure relates to an imaging system for creating an image of an examination object comprising a system component and a control component. The system component has a component property that is able to assume a value in a first value range established by the imaging system. A corresponding system component of another imaging system comprises a corresponding component property with another value range with an overlap range with the first value range. The control component is embodied to control the use of the system component on the creation of the image, wherein the control component can be operated in a compatibility mode. In the compatibility mode, the control component is configured, on the creation of the image, to only allow values that lie within the overlap range for the component property of the system component.

Abstract: Apparatus and methods are described including an endoluminal device configured to move along a portion of a lumen of a subject's body, an extraluminal imaging device, and at least one computer processor. While the endoluminal device moves along the portion of the lumen, a display displays an extraluminal image of the lumen in which a first indication of a location of the lumen is shown. The extraluminal imaging device acquires a sequence of extraluminal images of the endoluminal device moving along the portion of the lumen. The indication of the location of the lumen that is displayed is updated based upon the acquired sequence of extraluminal images, and the acquired sequence of images is displayed with the updated indication of the location of the lumen overlaid upon the images. Other applications are also described.

Abstract: A system and method for enhanced navigation for use during a surgical procedure including planning a navigation path to a target using a first data set of computed tomography images previously acquired; navigating a marker placement device to the target using the navigation path; placing a plurality of markers in tissue proximate the target; acquiring a second data set of computed tomography images including the plurality of markers; planning a second navigation path to a second target using the second data set of computed tomography images; navigating a medical instrument to a second target; capturing fluoroscopic data of tissue proximate the target; and registering the fluoroscopic data to the second data set of computed tomography images based on marker position and orientation within the real-time fluoroscopic data and the second data set of computed tomography images.

Abstract: A system for performing an interventional procedure includes an interventional instrument and a control system. The instrument includes a catheter and an interventional tool extendable from the catheter. The control system includes a processor and a memory comprising machine-readable instructions that cause the control system to: receive a model of an anatomic structure, the anatomic structure including a plurality of passageways; identify a target structure in the model; receive information about a maximum extension length the interventional tool can be extended relative to a distal tip of the catheter; based upon the received information about the maximum extension length, identify a planned deployment location for positioning the distal tip of the catheter to perform the interventional procedure on the target structure; determine a navigational path for the catheter to the target structure; and navigate the catheter to the identified planned deployment location via computer control or based on user input.

Abstract: An example device includes an elongated body defining a lumen, the elongated body comprising a proximal portion and a distal portion; and one or more sensors configured to: stimulate a fluorescence response from one or more fluorescent probes released into a fluid and flowing with the fluid through the lumen; and detect the fluorescence response, wherein the fluorescence response is indicative of a composition of the fluid.

Abstract: A biological information management system includes a first information device including a first communication unit and a second information device including a second communication unit. The first information device is attached to a portion of a subject where a positional relationship with a reference position of the subject changes. The second information device is attached to the reference position or a portion where the positional relationship with the reference position changes. The first information device outputs biological abnormality/normality determination information based on a radio field intensity and a signal waveform of a radio wave received by transmission of a first signal between the first communication unit and the second communication unit when the first information device and the second information device have a predetermined positional relationship.

Abstract: A method for fabricating a biosensor for metastasis diagnosis. The method includes coating a photoresist layer on a substrate layer, forming a patterned region by patterning the photoresist layer utilizing a photolithography process, forming a nano-roughened patterned region by forming a plurality of nano-features on the patterned region, stripping the photoresist layer from the substrate layer, forming an array of microelectrodes and a corresponding array of electrical connections on the nano-roughened patterned region by depositing a gold/titanium (Au/Ti) bilayer on the substrate layer with the nano-roughened patterned region and forming a metastatic cell sensing trap on at least one microelectrode of the array of microelectrodes. Where, forming the metastatic cell sensing trap includes placing a solution of Human Umbilical Vein Endothelial Cells (HUVECs) on the biosensor and forcing an attachment between at least one HUVEC of the HUVECs and the at least one microelectrode on the biosensor.

Abstract: A system for determining a location for a surgical procedure, having a 3D spatial mapping camera, the 3D spatial mapping camera configured to map a bone. The system also includes a marker attached to a distal end section of the bone, such that the 3D spatial mapping camera is configured to capture a plurality of images of the marker as the bone is rotated in a non-linear path. The images also include data identifying a location of the marker. The system also includes a computer system that receives the data from the images captured by the 3D spatial mapping camera and determines a location of a mechanical axis of the bone, and a mixed reality display, where the computer system is configured to send the location of the mechanical axis to the mixed reality display and the mixed reality display is configured to provide a virtual display of the mechanical axis of the bone.

Abstract: A method and system are for acquiring a dataset created via an imaging modality, the dataset describing a 3D-shape of a 3D-object; adapting, in dependence on the 3D-shape of the 3D-object, a flat 2D-grid of intersecting grid lines to follow a surface curvature of the 3D-object to create an adapted grid, a distance between two neighbouring intersections, along the grid lines of the adapted grid following the surface curvature of the 3D-object, being equal to a respective corresponding distance between a respective two neighbouring intersections of the flat 2D-grid before the adapting; and outputting the adapted grid for display over at least one of the 3D-object and a virtual model of the 3D-object.

Abstract: A low radiation, intra-operative method using two-dimensional imaging to register the positions of surgical implants relative to their pre-operative planned positions. Intraoperatively, a pair of two-dimensional fluoroscope images in different planes or a single three-dimensional image is acquired and compared to a set of three-dimensional pre-operative images, to allow registration of the implant region anatomy. A second set of intraoperative fluoroscope images is acquired of the surgical area with implants in place. The second set of images is compared with the first set of intraoperative images to ascertain alignment of the implants. Registration between first and second intraoperative image sets is accomplished using the implants themselves as fiducial markers, and the process repeated until an acceptable configuration of the implants is obtained. The method is particularly advantageous for spinal surgery.

Abstract: A body part recognition method and apparatus, a smart cushion, a device, and a medium. The method includes: collecting a plurality of vibration signals by using a plurality of sensor units in a two-dimensional sensor array provided in a smart cushion; obtaining statistics about short-term vibration energy characteristic of each of the sensor units on the basis of the vibration signal collected by the each sensor unit; determining a position of the each sensor unit having a highest short-term vibration energy characteristic as a position of the buttocks; and recognizing the positions of body parts other than the buttocks on the basis of the position of the buttocks using a dynamic programming algorithm or/and a greedy algorithm.

Abstract: A surgical access assembly and method of use is disclosed. The surgical access assembly comprises an outer sheath and an obturator. The outer sheath and obturator are configured to be delivered to an area of interest within the brain. Either the outer sheath or the obturator may be configured to operate with a navigational system to track the location of either within the brain. Once positioned at a desired location, the obturator is removed, leaving a distal end of the outer sheath adjacent an area of interest, and creating a working corridor. Interrogation of the area of interest may be performed to evaluate a disorder and/or abnormality, as well as evaluate treatment regimes. Interventional devices may also be introduced to the area of interest, as well as a variety of treatments.

Abstract: The present disclosure provides a method and system for processing multi-modality images. The method may include obtaining multi-modality images; registering the multi-modality images; fusing the multi-modality images; generating a reconstructed image based on a fusion result of the multi-modality images; and determining a removal range with respect to a focus based on the reconstructed image. The multi-modality images may include at least three modalities. The multi-modality images may include a focus.

Abstract: Embodiments described provide an ultrasound method, and an ultrasound apparatus and computer program product operable to perform that method. In some embodiments, the method allows for provision of a multi-transducer ultrasound imaging system by providing a robust method to accurately localize the transducers in the system in order to beamform a final image. The method and apparatus described allow for improvements in imaging quality in terms of resolution, depth penetration, contrast and signal to noise ratio (SNR).

Abstract: The present invention relates to a device for endoscopy or endosonography-guided transluminal interventions whereby two luminal structures in the body may be drawn toward each other and a fluid conduit formed in between. The device may have a hollow central member to which is coupled a distal retention member and in one embodiment a proximal retention member. The retention members may each be positioned inside one of the luminal structures and expanded from a first condition to an expanded second condition having an increased radius. The length of the central member may be shortened and its diameter expanded to approximate the two retention members and thereby the luminal structures.

Abstract: A sensor for motion or gesture sensing may be configured to emit radio frequency signals such as for pulsed range gated sensing. The sensor may include a radio frequency transmitter configured to emit the pulses and a receiver configured to receive reflected ones of the emitted radio frequency signals. The received pulses may be processed by a motion channel and/or a gesture channel. The gesture channel may produce signals for further processing for identification of one or more different motion gestures such as by calculating and evaluating features from any of the amplitude, phase and frequency of the output signals of the gesture channel. The sensing apparatus may optionally serve as a monitor for evaluating user activities, such as by counting activities. The sensor may optionally serve as a user control interface for many different devices by generating control signal(s) based on identification of one or more different motion gestures.

Abstract: Disclosed is the electronic architecture, including component arrangement and use of switches, and power saving method for use in a dual mode USTA instrumentation. In an embodiment, the instrument architecture includes US and TA analog components, including a transducer, TA preamplifier, pulser, switches, and AFE (or ADC with programmable amplifier) arranged in a way which allows efficient usage of the same transducer elements, electronic components, wiring, and AFE channels in both US and TA modalities. The operation with fast power control over the TA preamplifier is described, which allows turning off the TA preamplifier power between TA measurements cycles with or without US measurement between TA measurements. TA preamplifier energy saving allows such designs to reduce TA preamplifier power consumption many times, which enables TA preamplifier integration inside transducer housing or probe housing, and/or the use of the TA preamplifier in portable battery-operated or hand-held devices.

Abstract: A method and a device for determining a device parameter of a hearing device to be worn at the ear of a user, the method comprising: obtaining image data of one or more images, the image data including first image data of a first image of the outer human ear at a first angle; identifying, based on the first image data, a first anatomical landmark and a second anatomical landmark of the outer human ear using a processor; identifying the position of the first anatomical landmark and the second anatomical landmark in the first image; determining the device parameter of the hearing device based on the first anatomical landmark and the second anatomical landmark; and outputting the device parameter.

Abstract: A system and method for generating at least one optimized functional images of a lesion region of a subject is provided. The system includes a diffuse optical tomography (DOT) device, and a computing device. The DOT device is configured to acquire lesion functional data of an imaging volume including the lesion region of the breast and reference functional data from a corresponding imaging volume including healthy tissue within a contralateral breast. The computing device is programmed to generate at least one functional image of the breast by reconstructing the functional data at the plurality of regions including the lesion region and the surrounding adjacent background region. The functional images may be reconstructed by an optimization method regularized a preliminary estimate generated by applying a truncated pseudoinverse matrix of a weight matrix to the functional data. The optimized functional images relate to levels of hemoglobin at the voxels.

Abstract: A probe generates location signals, and has an electrode at a distal end that acquires from heart chamber surface positions electrical signals due to a conduction wave traversing the surface. A processor derives LATs from the electrical signals, calculates a first time difference between LATs at a first pair of positions and a second time difference between LATs at a second pair of positions. The processor calculates first and second LAT-derived distances as products of the first and second time differences with a conduction wave velocity, identifies an arrhythmia origin at a surface location where a first difference in distances from the location to the first pair of the positions is equal to the first LAT-derived distance, and a second difference in distances from the location to the second pair of the positions is equal to the second LAT-derived distance, and marks the origin on a surface representation.

Abstract: In a non-invasive optical detection system and method, sample light is delivered into a scattering medium. A first portion of the sample light passing through a volume of interest exits the scattering medium as signal light, and a second portion of the sample light passing through a volume of non-interest exits the scattering medium as background light that is combined with the signal light to create a sample light pattern. Reference light is combined with the sample light pattern to create an interference light pattern having a holographic beat component. Ultrasound is emitted into the volume of non-interest in a manner that decorrelates the background light of the sample light pattern from the holographic beat component. The holographic beat component is detected during the measurement period. An optical parameter of the volume of interest is determined based on the detected holographic beat component.

Abstract: Anatomical and functional assessment of coronary artery disease (CAD) using machine learning and computational modeling techniques deploying methodologies for non-invasive Fractional Flow Reserve (FFR) quantification based on angiographically derived anatomy and hemodynamics data, relying on machine learning algorithms for image segmentation and flow assessment, and relying on accurate physics-based computational fluid dynamics (CFD) simulation for computation of the FFR.

Abstract: A signal processing apparatus relays communication of control signals between a controller and a plurality of processing modules, and includes: a communication device configured to perform communication of the control signals with the plurality of processing modules; a plurality of first storages provided respectively to correspond to the plurality of processing modules, the plurality of first storages being configured to store the control signals written by the controller; a second storage configured to store: address information indicating each communication address assigned to each of the plurality of processing modules; and correspondence information indicating correspondence relationships between the plurality of first storages and a plurality of module-side storages respectively included in the plurality of processing modules; and a synchronization processor configured to synchronize the plurality of first storages with the plurality of corresponding module-side storages via the communication device bas

Abstract: A method is for controlling a medical imaging system. The method includes providing a data record for a patient, the data record including indication data; mapping at least the indication data into an ontology; providing a control data library including control data records for at least one medical imaging system; automatically determining a control data record from the control data library as a function of the at least indication data mapped into the ontology, via at least one of an inference and numerical modeling; and controlling the medical imaging system with the control data record automatically determined. Furthermore, a related control facility and a medical imaging system are also disclosed.

Abstract: A mm-wave system includes transmission of a millimeter wave (mm-wave) signal by a plurality of transmitters to multiple objects, and receiving of return—mm-wave signals from the multiple objects by a plurality of receivers. A processor is configured to perform an algorithm to derive complex-valued samples and angle measurements from each receiver to identify one object from another object. The processor further extracts signal waveforms that correspond to each object and process the extracted signal waveforms to estimate breathing rate and heart rate of the identified object.

Abstract: A fluid separation device includes a centrifuge in which a fluid is separated into at least two components, with an interface therebetween. At least a portion of one of the separated fluid components is removed from the centrifuge and flows through a vessel. Light is reflected off of the separated fluid component in the vessel and received and analyzed to determine its main wavelength. If the main wavelength is higher than a maximum value, a target location of the interface is changed. If the main wavelength is less than the maximum value, then the location of the interface is compared to the target location. When the interface is sufficiently close to the target location, the optical density of the separated fluid component in the vessel is compared to a minimum value. If the optical density is less than the minimum value, the target location of the interface is changed.

Abstract: A system and method for the use of the results from a structural analysis of a patient's bone from a clinical scan, to be used clinically to manage patients in a widespread and consistent fashion.

Abstract: Systems and methods for reconstructing medical images are disclosed. Measurement data from positron emission tomography (PET) data, and measurement data from an anatomy modality, such as magnetic resonance (MR) data or computed tomography (CT) data, is received from an image scanning system. A PET image is generated based on the PET measurement data, and an anatomy image is generated based on the anatomy measurement data. A trained neural network is applied to the PET image and the anatomy image to generate an attenuation map. The neural network may be trained based on anatomy and PET images. In some examples, the trained neural network generates an initial attenuation map based on the anatomy image, registers the initial attenuation map to the PET image, and generates an enhanced attenuation map based on the registration. Further, a corrected image is reconstructed based on the generated attenuation map and the PET image.

Abstract: A medication inventory system may include a medication tray that includes partitions defining compartments and having a tray identifier associated therewith, and each compartment may store a respective medication. The system may include an imaging apparatus, and a processor and an associated memory cooperating with the imaging apparatus to determine the tray identifier of the medication tray, and maintain in the memory a desired respective medication within each compartment based upon the tray identifier. A respective medication image of the medication within each compartment may be obtained and machine learning may be used to determine a medication within each compartment based upon the respective medication image.

Abstract: Pre-surgical planning can use a three-dimensional model of an anatomical structure having a plurality of fiduciary points and a surgical mark integrated into the three-dimensional model using a contrast material. A model image of the three-dimensional model can be superimposed with a diagnostic image of the anatomical structure using the plurality of fiduciary points in order to create a superimposed image.

Abstract: A dual modality endocavity imaging and treatment system for detection of cancer and targeted biopsy and treatment procedures, comprising: a housing; a nuclear detector system housed within the housing and configured for detecting nuclear radiation imaging data; an ultrasound detector system housed within the housing for detecting ultrasound imaging data; a needle associated with the housing and adjustably positionable relative thereto; and a data processing module configured to receive the nuclear radiation imaging data and the ultrasound imaging data and to generate and output an image showing the relative position of the needle and an endocavity object of interest. The needle may include a distinct radiation signature to facilitate imaging thereof.

Abstract: A method for locating a vessel, the method comprising illuminating at least a portion of the vessel with a background light having a substantially high susceptibility to absorption by particles in said portion of the vessel; detecting backscattered light from said illuminated portion of the vessel; reproducing an image from said backscattered light; and identifying dark regions within said reproduced image.