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: In a medical image processing apparatus, a medical image processing method, and a medical image processing program, in a case where there are a plurality of past brain images, it is possible to select a past brain image with which the atrophy rate of the brain can be accurately calculated. An image acquisition unit acquires a target brain image Bt as a diagnostic target and a plurality of past brain images Bpi, which have earlier imaging dates and times than the target brain image Bt, for the same subject. A similarity calculation unit calculates the similarity between each of the plurality of past brain images Bpi and a standard brain image Bs. A selection unit selects a reference brain image B0 serving as a reference for calculating the amount of change of the brain from the plurality of past brain images Bpi.

Abstract: In an approach to automatic detection of vertebral dislocations, training data is received, where the training data includes an ordered sequence of radiographic image patches of vertebrae and intervertebral spaces, and location data for each vertebra and each intervertebral space. Location deep learning models are trained to detect a location of each vertebra and each intervertebral space from the training data. Classification deep learning models are trained to classify an ordered sequence of image patches to identify vertebral anomalies of the vertebrae and the intervertebral spaces from the training data. Responsive to receiving radiographic image files, the location deep learning models and the classification deep learning models are applied to the radiographic image files to create a condition assessment.

Abstract: A method for determining part wear, such as using a wear metric, includes receiving, from a sensor, sensor data representing a surface of a wear part. The method further includes determining distances between measured points in the sensor data and points on one or more part models, which part models may include new part models and/or worn or wear limit part models. The method further includes using a bounding model that at least partially envelopes the part model(s) and the measured points to determine a direction along which the distances are measured. The method may also include quantifying wear using the measured distances.

Abstract: A system for illustrating the flight of a sports ball includes a radar, an imager, and a controller. The imager is configured to image a moving sports ball. The controller is configured to (i) receive, from the imager, an image including the moving sports ball, (ii) receive, from the radar, radar data associated with the moving sports ball, (iii) determine, from the radar data, a portion of a trajectory of the moving sports ball, (iv) alter the image to illustrate the portion of the trajectory relative to the moving sports ball, and (v) output the altered image.

Abstract: Provided is a tumor tracking method including: acquiring a detection image when a first ray source is located at a first detection point; determining, from a first reference image sequence in a preset image library, a first reference image corresponding to the detection image; acquiring, from a second reference image sequence corresponding to the first reference image sequence in the preset image library, a second reference image determined at the same time point as the first reference image; and determining a position of a tumor relative to a second ray source according to the second reference image.

Abstract: The brain appears to have organized cardiac frequency angiographic phenomena with such coherence as to qualify as vascular pulse waves. Separate arterial and venous vascular pulse waves may be resolved. This disclosure states the method of extracting a spatiotemporal reconstruction of the cardiac frequency phenomena present in an angiogram obtained at faster than cardiac frequency. A wavelet transform is applied to each of the pixel-wise time signals of the angiogram. If there is motion alias then instead a high frequency resolution wavelet transform of the overall angiographic time intensity curve is cross-correlated to high temporal resolution wavelet transforms of the pixel-wise time signals. The result is filtered for cardiac wavelet scale then pixel-wise inverse wavelet transformed. This gives a complex-valued spatiotemporal grid of cardiac frequency angiographic phenomena. It may be rendered with a brightness-hue color model or subjected to further analysis.

Abstract: Technologies for evaluating, scoring, and determining whether to present a caption of an image are provided. The disclosed techniques include receiving an image with associated metadata. Contextual data is identified from the image and the metadata. A generated caption for the image is received from an image caption generator. A first vector representation is generated based on the contextual image data and a second vector representation is generated based on the generated caption. A machine learned model generates a score for the generated caption using the first vector representation and the second vector representation. The score represents a confidence value defining how accurately the caption describes the image. Based on the score, the caption may be presented along with the image on a client device.

Abstract: A method, apparatus and system for enhanced welding visualization include splitting incoming light from the welding environment into at least a first optical path and a second optical path having different light levels using at least one beam splitter. Images of the split light having different light levels are captured using a respective imaging sensor. The images from the respective imaging sensors are fused to create a left-eye fused image and a right-eye fused image. The left-eye fused image is displayed on a display at a location of a left eye of a user and the right-eye fused image is displayed on a display at a location of a right eye of the user to provide a parallax-free, high dynamic range, representation of the welding environment.

Abstract: Embodiments discussed herein facilitate classification of vascular plaque. One example embodiment can: access vascular imaging data comprising one or more slices, wherein each slice comprises a plurality of A-lines of that slice; for each A-line of the plurality of A-lines of each slice of the one or more slices: extract one or more features for that A-line, wherein the one or more features for that A-line comprise at least one of: one or more features extracted from that A-line, one or more features extracted from the slice comprising that A-line, or one or more features extracted from the vascular imaging data; provide the one or more features for that A-line to at least one classifier; and generate a classification of that A-line via the at least one classifier, wherein the classification of that A-line is one of fibrocalcific, fibrolipidic, or other.

Abstract: Systems and methods for accurately and efficiently diagnosing, assessing, staging/grading/categorizing, and treating pressure ulcers, as well as preventing reverse staging of pressure ulcers, are disclosed. The system, in one embodiment, ensures that the rationale for the stage assigned to the patient will be in the patients' medical record. The system, in various embodiments, further suggests the pressure ulcer classification and allows the user to choose which classification terms should be used. In various embodiments, the system also allows for the different classification/staging system guidelines to be used, including the National Pressure Ulcer Advisory Panel (NPUAP) guidelines, the European Pressure Ulcer Advisory Panel Guidelines (EPUAP), the Pan Pacific Pressure Injury Alliance, CMS, WHO, and the MDS Guidelines.

Abstract: There is provided an imaging system. The imaging system comprising a multispectral camera configured to capture a multispectral image of an object, an RGB camera configured to capture a color image of the object, at least one storage device configured to store spectrum information for each of a plurality of labeled objects, and processing circuitry. The processing circuitry is configured to determine, based on the captured multispectral image, spectrum information associated with the object, associate, based at least in part, on the spectrum information associated with the object and the stored spectrum information for each of the plurality of objects, a label with the color image of the object, and store, on the at least one storage device, the color image and the associated label as training data.

Abstract: A system for non-contact imaging of corneal tissue stored in a viewing chamber using Gabor-domain optical coherence microscopy (GDOCM), wherein a 3D numerical flattening procedure is applied to the image data to produce an at least substantially artifact-free en face view of the endothelium.

Abstract: Disclosed is a fluorescence image analyzing apparatus including a light source that emits light to a sample including a plurality of cells labeled with a fluorescent dye at a target site, an imaging unit that captures a fluorescence image of each of the cells that emit fluorescence by being irradiated with the light, a fluorescence image of the cell, and a processing unit that processes the fluorescence image captured by the imaging unit to acquire a bright spot pattern of fluorescence in the fluorescence image. The processing unit selects a reference pattern corresponding to a measurement item of the sample from a plurality of reference patterns corresponding to a plurality of measurement items and generates information used for determination of the sample based on the bright spot pattern of fluorescence in the fluorescence image and the selected reference pattern.

Abstract: Systems and methods for estimating contact force on an anatomical structure during a surgical procedure are disclosed. A system may include at least one processor configured to receive, from at least one image sensor in an operating room, image data of a surgical procedure and analyze the received image data to determine an identity of an anatomical structure and to determine a condition of the anatomical structure as reflected in the image data. The processor may select a contact force threshold associated with the anatomical structure, the selected contact force threshold being based on the determined condition of the anatomical structure, receive an indication of actual contact force on the anatomical structure, and compare the indication of actual contact force with the selected contact force threshold. The processor may then output a notification based on a determination that the indication of actual contact force exceeds the selected contact force threshold.

Abstract: A method of grouping detection events in an imaging apparatus is described herein. The detection events can include primary detection events and secondary scattered events, which are frequently discarded due to the secondary scattered events, thus reducing sensitivity of the dataset for eventual image reconstruction. The method includes cell modules cascaded with identical parametrized cells, in a pipeline fashion, having the last cell in the chain circle back to the first cell. A rotating data pointer indicates the location of the first entry in the cell pipeline. The described method enables the grouping of multiple samples of detector data in real time with no loss of information, based on a time and location of the detected event. The method can be implemented in an FPGA as a hardware-based real time process.

Abstract: A component mounting machine including a camera configured to capture an image of a component held by a suction nozzle; and an image processing section configured to process the image captured by the camera, recognize the shape of the component, and measure shape data of the component; wherein, when the deviation amount of the measurement value of the shape data of the component exceeds the allowable value, the deviation amount of the measurement value of the shape data of the component is compared to a retry determination that is larger than the allowance value, and if the deviation amount of the measurement value of the shape data of the component exceeds the retry determination value, the component is determined to be abnormal and is discarded to a specified discard location.

Abstract: The present disclosure describes systems and processes, including processes in which first location data is received. Visual access to a first image corresponding to the first location data is provided, the first image including a roof structure of a building. A first computer input capable of signaling a designation from the user of a building roof structure location within the first image is provided. A designation of the building roof structure location within the first image is received. Responsive to receiving the designation of the building roof structure location, a second computer input capable of signaling user-acceptance of the building roof structure location within the first image is provided. Subsequent to receiving the user-acceptance confirming the designation of the building roof structure location, a report of the roof structure is provided.

Abstract: An image processing apparatus configured to acquire first registration information being registration information between a first image of interest, which is the first frame image in the frame image pair, and the first reference image; to acquire second registration information being registration information between a second image of interest, which is the second frame image in the frame image pair, and the second reference image; to acquire reference registration information being registration information between the first reference image and the second reference image; and to acquire third registration information being registration information between the first image of interest and the second image of interest, based on the first registration information, the second registration information and the reference registration information.

Abstract: A method of identifying a background type in a photograph includes extracting a background image from a photograph, feeding the background image into a first convolution neural network to obtain a first decision, extracting color features in the background image, transforming the color features into a two-dimensional color feature matrix, feeding the two-dimensional color feature matrix into a second convolution neural network to obtain a second decision by the one or more computer processors, extracting texture features in the background image, transforming the texture features into a two-dimensional texture feature matrix image by the one or more computer processors, feeding the two-dimensional texture feature matrix into a third convolution neural network to obtain a third decision, computing a hybrid decision based on the first decision, the second decision, and the third decision, and identifying a background type in the background image based on the hybrid decision.