Abstract: The present disclosure relates to image reconstruction with favorable properties in terms of noise reduction, spatial resolution, detail preservation and computational complexity. The disclosed techniques may include some or all of: a first-pass reconstruction, a simplified datafit term, and/or a deep learning denoiser. In various implementations, the disclosed technique is portable to different CT platforms, such as by incorporating a first-pass reconstruction step.

Abstract: An image generation device comprising: an image acquiring unit configured to acquire a set of a first non-defective-product image and a second non-defective-product image for the same article to be inspected; a first processing unit configured to change a pixel value of a first target pixel that is at least one pixel forming the first non-defective-product image, thereby generating a first virtual defective-product image that is the virtual defective-product image; and a second processing unit configured to change a pixel value of a second target pixel that corresponds to the first target pixel and is at least one pixel forming the second non-defective-product image, thereby generating a second virtual defective-product image that is the virtual defective-product image.

Abstract: A method for determining an apposition parameter indicative for the position and apposition of a tubular member, such as a stent graft, inserted in a lumen of an anatomical vessel/duct of a patient. The method includes providing a numerical three-dimensional patient model of at least a part of the vessel including the tubular member; determining a vessel morphology parameter from the patient model, the parameter indicative for the anatomy of a predetermined part of the vessel at or near the tubular member in said vessel with respect to said patient model; determining a tubular member positional parameter from the patient model, the parameter indicative for the position of a predetermined part of the tubular member in the patient model; and calculating, based on the determined vessel morphology parameter and tubular member positional parameter, the relative position of the tubular member with respect to the vessel as the apposition parameter.

Abstract: Systems and methods are provided for processing a set of multiple serially acquired magnetic resonance spectroscopy (MRS) free induction decay (FID) frames from a multi-frame MRS acquisition series from a region of interest (ROI) in a subject, and for providing a post-processed MRS spectrum. Processing parameters are dynamically varied while measuring results to determine the optimal post-processed results. Spectral regions opposite water from chemical regions of interest are evaluated and used in at least one processing operation. Frequency shift error is estimated via spectral correlation between free induction decay (FID) frames and a reference spectrum. Multiple groups of FID frames within the acquired set are identified to different phases corresponding with a phase step cycle of the acquisition. Baseline correction is also performed via rank order filter (ROF) estimate and a polynomial fit.

Abstract: A method of detecting whether or not a body chamber has an abnormal structure or function including: (a) providing a stack of images as input to a system comprising one or more hardware processors configured to obtain a stack of medical images comprising at least a representation of the body chamber inside the patient; to obtain a region of interest using a convolutional network trained to locate the body chamber, wherein the region of interest corresponds to the body chamber from each of the medical images; and to infer a shape of the body chamber using a stacked auto-encoder (AE) network trained to delineate the body chamber, wherein the AE network segments the body chamber; (b) operating the system to detect the body chamber in the images using deep convolutional networks trained to locate the body chamber, to infer a shape of the body chamber using a stacked auto-encoder trained to delineate the body chamber, and to incorporate the inferred shape into a deformable model for segmentation; and (c) detecting

Abstract: There is disclosed an image processing apparatus including a hardware processor which generates a highly resolved still image from a plurality of frame images obtained by continuously imaging a moving subject. The hardware processor analyzes each of the plurality of frame images to calculate a feature amount, and determines, on a basis of the calculated feature amount, a reference frame image which becomes a reference when generating the highly resolved still image from the plurality of frame images.

Abstract: A method of processing magnetic resonance (MR) data of a sample under investigation, includes the steps of providing the MR data being collected with an MRI scanner apparatus, and subjecting the MR data to a multi-parameter nonlinear regression procedure being based on a non-linear MR model and employing a set of input parameters, wherein the regression procedure results in creating a parameter map of model parameters of the sample, wherein the input parameters (initial values and possibly boundaries) of the regression procedure are estimated by a machine learning based estimation procedure applied to the MR data. The machine learning based estimation procedure preferably includes at least one of at least one neural network and a support vector machine. Furthermore, an MRI scanner apparatus is described.

Abstract: Among other things, computed tomography (CT) systems and/or techniques for generating projections images of an object(s) under examination via a CT system are provided. The projection images of the object may represent a projection of the entire object or merely a portion of the object, such as a slice of the object. A surface about which the projection image is focused is defined and data yielded from a plurality of views of the object is mapped to the surface. In some embodiments, such a mapping comprises mapping data corresponding to a first view and yielded from a first detector cell to a first point on the surface, mapping data corresponding to the first view and yielded from a second detector cell to a second point on the surface, and/or mapping data corresponding to a second view and yielded from the first detector cell to a third point on the surface.

Abstract: A system and method for generating a rib suppressed radiographic image using deep learning computation. The method includes using a convolutional neural network module trained with pairs of a chest x-ray image and its counterpart bone suppressed image. The bone suppressed image is obtained using a bone suppression algorithm applied to the chest x-ray image. The convolutional neural network module is then applied to a chest x-ray image or the bone suppressed image to generate an enhanced bone suppressed image.

Abstract: According to one embodiment, a photon-counting detector (PCD) includes a plurality of macro-pixels. The plurality of macro-pixels arranged on a semiconductor crystal has a first face and a second face. The first face and the second face are parallel. Each macro-pixel from the plurality of macro-pixels is configured to acquire projection data for generating a reconstructed image. The plurality of macro-pixels each includes at least one large micro-pixel is disposed within the each macro-pixel and at least two small micro-pixels is disposed within the each macro-pixel. Each of the at least two small micro-pixels has a surface area that is less than a surface area of the at least one large micro-pixel.

Abstract: An image grid line removing method is used for removing grid lines of an image and includes a Fourier transform step, a Gaussian-like masking step and an inverse Fourier transform step. The Fourier transform step is for providing a Fourier transform to process the image to generate a frequency domain image. The Gaussian-like masking step is for providing a Gaussian-like masking model to process the frequency domain image to generate a frequency domain masked image. The inverse Fourier transform step is for providing an inverse Fourier transform to process the frequency domain masked image to generate a grid line removing image.

Abstract: A radiation image display apparatus that constitutes a radiation imaging system includes a displayer and a hardware processor that acquires image data of a dynamic image constituted of a plurality of frame images, image data of an analysis dynamic image obtained by applying predetermined image processing to the image data of the dynamic image and image data of a related dynamic image which is related to the dynamic image or the analysis dynamic image respectively, and causes the displayer to display the related dynamic image together with the dynamic image and the analysis dynamic image.

Abstract: An image processing apparatus includes: an acquisition unit that acquires a plurality of radiographic images of the same breast which have captured in a plurality of different states related to compression of the breast; and a derivation unit that derives, on the basis of an amount of incident radiation derived from a value of a fat tissue pixel in a radiographic image in which the fat tissue pixel obtained by a portion of the breast which is estimated to be composed of only fat tissues is included in a breast image among the plurality of radiographic images acquired by the acquisition unit, a percentage of mammary glands of a breast image in a radiographic image different from the radiographic image used to derive the amount of incident radiation.

Abstract: Systems and methods according to one or more embodiments are provided for mapping and registration of synthetic aperture raw radar data to aid in SAR-based navigation. In one example, a SAR-based navigation system includes a memory including executable instructions and a processor adapted to receive phase history data associated with observation views of a scene. The processor further converts the received phase history data associated with the observation views to a range profile of the scene. The range profile is compared to a range profile template of the scene to estimate a geometric transformation of the scene encoded in the received phase history data with respect to a reference template.

Abstract: An image registration method, an image registration device, and a storage medium. The image registration method includes: causing a display device to display at least one spot array; obtaining a feature image, and performing a feature-based image registration operation on the feature image to obtain at least one transformed image; and obtaining a mapping model based on the at least one transformed image. The feature image is an image which is shown on the display device and displays the at least one spot array.

Abstract: An X-ray imaging apparatus includes a table, an imager configured to capture a plurality of X-ray images, a rotating mechanism, a moving mechanism, and an image processor. The image processor is configured to generate a long image by performing processing of varying magnifications of the plurality of X-ray images based on an amount of relative movement of the table and the imager and splicing the plurality of X-ray images when imaging is performed at a plurality of imaging positions in a state in which an optical axis of X-rays radiated from an X-ray irradiator is inclined with respect to the table.

Abstract: Methods and systems for characterizing tissue of a subject include acquiring and receiving data for a plurality of time series of fluorescence images, identifying one or more attributes of the data relevant to a clinical characterization of the tissue, and categorizing the data into clusters based on the attributes such that the data in the same cluster are more similar to each other than the data in different clusters, wherein the clusters characterize the tissue. The methods and systems further include receiving data for a subject time series of fluorescence images, associating a respective cluster with each of a plurality of subregions in the subject time series of fluorescence images, and generating a subject spatial map based on the clusters for the plurality of subregions in the subject time series of fluorescence images. The generated spatial maps may then be used as input for tissue diagnostics using supervised machine learning.

Abstract: With regard to a setting reference for X-ray irradiation range and image generation range, which differs by hospital or technician, a structure to automatically set a desired X-ray irradiation range and an image generation range infallibly, is provided. In an X-ray CT apparatus, a scan range automatic setting unit extracts an inspection target as an arbitrary body part designated by an operator before inspection from a positioning image, and generates an extraction region range including it. The operator sets an arbitrary margin value by line operation or numerical input using a GUI with respect to the extraction region range (S104). The scan range automatic setting unit generates and stores a range setting pattern in which the inspection target and the margin value are made to correspond to each other (S105), and links the range setting pattern to an inspection protocol (S106).

Abstract: Methods and systems for medical imaging including synthesizing virtual projections from acquired real projections and generating reconstruction models and images based on the synthesized virtual projections and acquired real projections. For example, first x-ray imaging data is generated from a detected first x-ray emission at a first angular location and second x-ray imaging data is generated from a detected second x-ray emission at a second angular location. Based on at least the first x-ray imaging data and the second x-ray imaging data, third x-ray imaging data for a third angular location relative to the breast may be synthesized. An image of the breast may be displayed or generated from the third x-ray imaging data.

Abstract: A method for facial analytics includes capturing a series of images of individuals from a camera into a circular buffer and selecting a plurality of images from the buffer for analysis in response to a trigger event, wherein the plurality of images are chronologically proximate before and/or after the trigger event in time. The method includes analyzing the plurality of images to determine image quality and selecting one of the plurality of images based on image quality to form a cropped facial image most likely to result in positive facial recognition matching. Methods of signaling to control the pedestrian traffic flow can maximize the individuals' facial alignment to the capturing camera's field of view. Non-relevant facial images associated with individuals outside a given region of interest can be discarded. Facial recognition is run on the resultant cropped facial image. Output can be displayed with information from the facial recognition.

Abstract: Systems and methods for identifying fields in an electronic document using classification and scale invariant template matching. The method includes receiving an electronic document having fields and processing the electronic document into digital pages. The method also includes determining, for each of the digital pages, a corresponding document type. The method further includes identifying at least one of the digital pages containing a structured field based on the document type. The method also includes extracting a structured template from a database corresponding to the document type and identifying an optimal match between the structured field and the structured template using scale invariant template matching. The method further includes determining, in response to identifying the optimal match, coordinates corresponding to the structured field.

Abstract: A detection unit of a CPU of a console detects the position of an electronic cassette and the position of an irradiation field on the basis of a camera image output from a camera that is attached to an X-ray source and captures an image of at least the electronic cassette. The image processing unit performs image processing for an X-ray image detected by the electronic cassette on the basis of information of the position of the electronic cassette and information of the position of the irradiation field.

Abstract: A computer-implemented image analysis method and system. The method comprises: quantifying one or more features segmented and identified from a medical image of a subject; extracting clinically relevant features from non-image data pertaining to the subject; assessing the features segmented from the medical image and the features extracted from the non-image data with a trained machine learning model; and outputting one or more results of the assessing of the features.

Abstract: A system and method is provided for creating motion-adjusted or motion-compensated images of a patient to guide an interventional medical procedure. The method includes displaying a static roadmap and a plurality of dynamic images to show the interventional medical device aligned on the static roadmap using a motion transformation. Alignment of the interventional medical device on the static roadmap is based on a user selection of one of motion compensation of the interventional medical device relative to the static roadmap to produce a plurality of images that do not show patient motion or motion adjustment of the static roadmap relative to the interventional medical device to produce a plurality of images that show patient motion.

Abstract: The present invention seeks to provide a method of analyzing medical image, the method comprises receiving a medical image; applying a model stored in a memory; analyzing the medical image based on the model; determining the medical image including a presence of fracture; and, transmitting an indication indicative of the determination.

Abstract: The present invention relates to an apparatus for the detection of opacities in X-ray images. It is described to provide (210) an analysis X-ray image of a region of interest of an analyzed body part. A model of a normal region of interest is provided (220), wherein the model is based on a plurality of X-ray images of the region of interest. At least one abnormality is detected (230) in the region of interest of the analyzed body part, the detection comprising comparing the analysis X-ray image of the region of interest and the model of the normal region of interest. Information is output (240) on the at least one abnormality.

Abstract: A method is for operating an x-ray device for recording a series of images, in particular for fluoroscopic monitoring of a recording region of a patient. The method includes acquiring fluoroscopy images of a patient with a recording rate and a recording dose; and displaying the fluoroscopy images acquired to a user on a display device at a frame rate. The recording dose is selected automatically as a function of a change in image contents between consecutive fluoroscopy images acquired.

Abstract: A radiographic apparatus, comprises a generating unit that generates a composite image using a plurality of radiographic images that have been obtained by a plurality of radiation detecting apparatuses through single radiation irradiation by a radiation generating unit, a determining unit that determines a region to be analyzed so as to eliminate an overlap in an overlapping portion arising from a spatial placement of the plurality of radiation detecting apparatuses, and an obtaining unit that obtains an area dose for the composite image by obtaining an area dose for the region to be analyzed determined by the determining unit.

Abstract: The present invention relates to a device for displaying image information, the device comprising: a detection unit (10), which is configured to identify a plurality of admissible display orientations of multiple data sets; a restriction unit (20), which is configured to restrict the plurality of admissible display orientations of at least one of the multiple data sets to a set of admissible display orientations in common for all the multiple data sets; and/or to restrict a plurality of admissible scrolling directions of at least one of the multiple data sets to a set of admissible scrolling directions that are normal to the restricted admissible display orientations; and a display unit (30), which is configured to display the multiple data sets using the set of the restricted display orientations and/or the set of restricted scrolling directions.

Abstract: This X-ray fluoroscopic imaging apparatus is provided with an image processing unit that corrects magnification of a plurality of X-ray images based on first height information and generates a first long image by stitching the images together. The image processing unit is configured to generate a second long image in which the magnification of the plurality of X-ray images is corrected based on second height information upon acceptance of an input of second height information after generating the first long image.

Abstract: An imaging system includes an x-ray assembly having one or more x-ray sources configured to be energized at multiple positions. A control program energizes the one or more x-ray sources in a programmed sequence and controls the timing of the sequence.

Abstract: A system and a method for training and utilizing deep convolutional neural networks to perform diagnostic and image enhancement operations on images of dentition uses digital images and other auxiliary parameters as inputs for a convolutional neural network. The neural network can output a tooth segmentation map, tooth identifiers, a probability map indicating the presence of caries, cavities or other dental anomalies/conditions, and recommended parameters for use in image enhancement algorithms.

Abstract: Computed tomography (CT) screening, diagnosis, or another image analysis tasks are performed using one or more networks and/or algorithms to either integrate complementary tomographic image reconstructions and radiomics or map tomographic raw data directly to diagnostic findings in the machine learning framework. One or more reconstruction networks are trained to reconstruct tomographic images from a training set of CT projection data. One or more radiomics networks are trained to extract features from the tomographic images and associated training diagnostic data. The networks/algorithms are integrated into an end-to-end network and trained. A set of tomographic data, e.g., CT projection data, and other relevant information from an individual is input to the end-to-end network, and a potential diagnosis for the individual based on the features extracted by the end-to-end network is produced.

Abstract: The disclosure features methods and systems that include: obtaining an input image of an imaging subject, where the input image is a color image featuring, in each of multiple color channels, a first set of pixel intensity values; for each one of the multiple color channels, determining a measured contrast value and a measured brightness value from the first set of pixel intensity values for the color channel, determining a contrast ratio for the color channel based on a target contrast value for the color channel and the measured contrast value for the color channel, and generating a second set of pixel intensity values for the color channel; and generating an output image of the imaging subject based on the second sets of pixel intensity values for each of the multiple color channels.

Abstract: Identifying a local coordinate system is described for gesture recognition. In one example, a method includes receiving a gesture from a user across a horizontal axis at a depth camera, determining a horizontal vector for the user based on the received user gesture, determining a vertical vector; and determining a rotation matrix to convert positions of user gestures received by the camera to a frame of reference of the user.

Abstract: In an aspect, an image processing device includes: first specification means for specifying an abnormal pixel from a plurality of pixels according to a first method; and second specification means for specifying an abnormal pixel, from the plurality of pixels excluding the abnormal pixel specified by the first specification means, according to a second method different from the first method.

Abstract: A method including selecting, in a server, a first image portion from an image is provided. The method also includes identifying one or more known similar images associated with the first image portion, and determining a first score for enhancing the first image portion based on the known similar image(s). The method includes increasing a pixel resolution in the first image portion according to the scale to form an enhanced image portion. The method also includes identifying a synthetic value for the enhanced image portion and storing the enhanced image portion in a database when the synthetic value is below a tolerance value.

Abstract: An integrated circuit for an imaging system is disclosed. In one aspect, an integrated circuit has an array of optical sensors, an array of optical filters integrated with the sensors and configured to pass a band of wavelengths onto one or more of the sensors, and read out circuitry to read out pixel values from the sensors to represent an image. Different ones of the optical filters are configured to have a different thickness, to pass different bands of wavelengths by means of interference, and to allow detection of a spectrum of wavelengths. The read out circuitry can enable multiple pixels under one optical filter to be read out in parallel. The thicknesses may vary non-monotonically across the array. The read out, or later image processing, may involve selection or interpolation between wavelengths, to carry out spectral sampling or shifting, to compensate for thickness errors.

Abstract: A system and methods is provided for performing, by a processor, an initial tone mapping function on a first image to produce a second image. The first and second images are of different dynamic ranges. The method also includes applying, by the processor, a second tone mapping function to the second image when it contains any saturated portions. The second tone mapping function lowers luminance by a first fraction. The overall luminance of the second image is also determined and a fine tuning filter is applied when at least portions of said second image contain areas darker than an amount.

Abstract: An apparatus and method for providing additional information for region of interest. The apparatus includes a region of interest extractor configured to extract regions of interest from a first medical image and at least one second medical image, a region of interest merger configured to merge a region of interest of the at least one second medical image into the first medical image, an additional information determiner configured to determine additional information required for each region of interest, and an additional information provider configured to provide the determined additional information for the each region of interest.

Abstract: An image processing device capable of high-accuracy foreign object inspection is provided. The image processing device include a background value setting section configured to (i) obtain a value for use as a background value on a basis of a first pixel value of at least one reference pixel present in the vicinity of a target pixel and having a predetermined positional relationship with the target pixel, and (ii) set the background value of the target pixel to the value obtained.

Abstract: A method is for visualizing an image data set, the image data set displaying a three-dimensional arrangement including at least a first object and a second object. The method includes providing a three dimensional image data set including first voxels assigned to the first object and second voxels assigned to the second object; identifying first voxels of the three-dimensional image data set; determining a set of parameters for volume rendering, the set of parameters determined including a subset of parameters and a focusing parameter; identifying primary rays impacting on the first object and identifying secondary rays missing the first object; and performing the volume rendering using the subset of parameters determined, for visualizing the first object and the second object. The focusing parameter used for the primary rays in the volume rendering is different from the focusing parameter used for the secondary rays in the volume rendering.

Abstract: A LED controller for an LED pixel array includes a switch K1 activated in response to a row and column select signal; a switch K2 activated in response to a pulse width modulation duty cycle; and a switch K3 providing a current source from Vbias. Pixel activation is determined at least in part by state of switch K1 and K2. In operation, the LED pixel in the LED pixel array is selected by switch K1 and a fault determination for the LED pixel is made based on determined Vf on a Vf bus.

Abstract: A method is for producing an identification unit for identifying image artifacts automatically. In an embodiment, the method includes providing a learning processing apparatus; providing an initial identification unit; providing a first image data library including artifact reference acquisitions containing image artifacts; and training the identification unit using the image artifacts. An identification method is for identifying image artifacts automatically in an image acquisition. In an embodiment, the identification method includes: providing a trained identification unit; providing an image acquisition produced via a medical imaging system; inspecting the image acquisition for image artifacts by the identification unit; and labeling the ascertained image artifacts.

Abstract: While a user holds a camera positioned relative to an object, a first image of the object and a second image of the object, as captured by the camera, may be obtained. Intensity variations between a first intensity map of the first image and a combination intensity map obtained from the first intensity map and a second intensity map of the second image may be compared. Then, a shadow may be identified within the first image, based on the intensity variations.

Abstract: A system and method are provided for enabling a user to annotate a medical image. A collection of key-value pairs is provided, in which a key represents an image-observable quantity and a value represents the value of the image-observable quantity. A collection of structured finding objects is provided, wherein each structured finding object represents a set of key-value pairs, each set of key-value pairs representing a different annotation of the medical image. The user is enabled to select one or more of the collection of key-value pairs, thereby obtaining a user-selected structured finding object which represents a preliminary annotation of the medical image by the user. At least one recommended structured finding object is selected by using the user-selected structured finding object as input to a probabilistic recommendation algorithm. Feedback is provided to the user on the basis of the recommended structured finding object. The annotation is well suited for, e.g.

Abstract: In positron emission tomography (PET) imaging, PET imaging data (22) having TOF localization is reconstructed. TOF image reconstruction (30) is performed on the PET imaging data to produce a TOF reconstructed image (32). The TOF image reconstruction utilizes the TOF localization of the PET imaging data. Non-TOF image reconstruction (40) is also performed on the PET imaging data to produce a non-TOF reconstructed image (42). The non-TOF image reconstruction does not utilize the TOF localization of the PET imaging data. A comparison image (50) is computed which is indicative of differences between the TOF reconstructed image and the non TOF reconstructed image. An adjustment (54) is determined for the TOF image reconstruction based on the comparison image, such as alignment correction of an attenuation map (18), and the TOF image reconstruction is repeated on the PET imaging data with the determined adjustment to produce an adjusted TOF reconstructed image.

Abstract: In accordance with some embodiments, systems, methods and media for generating a bone age assessment. In some embodiments, a method comprises: receiving an x-ray image of a subject's left hand and wrist; converting the image to a predetermined size; identifying, without user intervention, a first portion of the image corresponding to the hand and wrist; processing the first portion of the image to increase contrast between bones and non-bones to generate a processed image; causing a trained convolution neural network to determine a bone age based on the processed image; receiving an indication of the bone age; causing the bone age to be presented to a user as the result of a bone age assessment; and causing the bone age and the image to be stored in an electronic medical record associated with the subject.

Abstract: Apparatus and methods automate selection of patient interface(s) according to their size, such as with processing in a processor(s) or in a server(s). Image data captured by an image sensor may be received. The captured image data may contain facial feature(s) of an intended user of the patient interface. The facial features may be captured in association with a predetermined reference feature of known dimension(s). The user's facial feature(s) and the reference feature may be detected in the captured image data. Image pixel data of the image may be processed to measure an aspect of the detected facial feature(s) based on the reference feature. A patient interface size may be detected from standard patient interface sizes based on a comparison between the measured aspect of the facial feature(s) and a data record relating sizing information of the standard patient interface sizes and the measured aspect of the facial feature(s).

Abstract: An X-ray fluoroscopy imaging apparatus that corrects to precisely remove a banding artifact in an X-ray image, includes an image processing unit that corrects an X-ray image by processing the image to remove the banding artifact (AF) from the X-ray image based on the average difference brightness value (DLa) relative to a plurality of pixels included in an array in an artifact extending direction (A-direction).