Abstract: Systems and methods are disclosed for receiving a target image corresponding to a target specimen, the target specimen comprising a tissue sample of a patient, applying a machine learning model, which may also be known as a machine learning system, to the target image to determine at least one characteristic of the target specimen and/or at least one characteristic of the target image, the machine learning model having been generated by processing a plurality of training images to predict at least one characteristic, the training images comprising images of human tissue and/or images that are algorithmically generated, and outputting the at least one characteristic of the target specimen and/or the at least one characteristic of the target image.

Abstract: The present application relates generally to identifying regions of interest in images, including but not limited to whole slide image region of interest identification, prioritization, de-duplication, and normalization via interpretable rules, nuclear region counting, point set registration, and histogram specification color normalization. This disclosure describes systems and methods for analyzing and extracting regions of interest from images, for example biomedical images depicting a tissue sample from biopsy or ectomy. Techniques directed to quality control estimation, granular classification, and coarse classification of regions of biomedical images are described herein. Using the described techniques, patches of images corresponding to regions of interest can be extracted and analyzed individually or in parallel to determine pixels correspond to features of interest and pixels that do not.

Abstract: Systems and methods are disclosed for receiving a target electronic image corresponding to a target specimen, the target specimen comprising a tissue sample of a patient, applying a machine learning system to the target electronic image to identify a region of interest of the target specimen and determine an expression level of, category of, and/or presence of a biomarker in the region of interest, the biomarker comprising at least one from among an epithelial growth factor receptor (EGFR) biomarker and/or a DNA mismatch repair (MMR) deficiency biomarker, the machine learning system having been generated by processing a plurality of training images to predict whether a region of interest is present in the target electronic image, the training images comprising images of human tissue and/or images that are algorithmically generated, and outputting the determined expression level of, category of, and/or presence of the biomarker in the region of interest.

Abstract: Systems and methods are disclosed for processing an electronic image corresponding to a specimen. One method for processing the electronic image includes: receiving a target electronic image of a slide corresponding to a target specimen, the target specimen including a tissue sample from a patient, applying a machine learning system to the target electronic image to determine deficiencies associated with the target specimen, the machine learning system having been generated by processing a plurality of training images to predict stain deficiencies and/or predict a needed recut, the training images including images of human tissue and/or images that are algorithmically generated; and based on the deficiencies associated with the target specimen, determining to automatically order an additional slide to be prepared.

Abstract: The present application relates generally to identifying regions of interest in images, including but not limited to whole slide image region of interest identification, prioritization, de-duplication, and normalization via interpretable rules, nuclear region counting, point set registration, and histogram specification color normalization. This disclosure describes systems and methods for analyzing and extracting regions of interest from images, for example biomedical images depicting a tissue sample from biopsy or ectomy. Techniques directed to quality control estimation, granular classification, and coarse classification of regions of biomedical images are described herein. Using the described techniques, patches of images corresponding to regions of interest can be extracted and analyzed individually or in parallel to determine pixels correspond to features of interest and pixels that do not.

Abstract: The present disclosure is directed to systems and methods for classifying biomedical images. A feature classifier may generate a plurality of tiles from a biomedical image. Each tile may correspond to a portion of the biomedical image. The feature classifier may select a subset of tiles from the plurality of tiles by applying an inference model. The subset of tiles may have highest scores. Each score may indicate a likelihood that the corresponding tile includes a feature indicative of the presence of the condition. The feature classifier may determine a classification result for the biomedical image by applying an aggregation model. The classification result may indicate whether the biomedical includes the presence or lack of the condition.

Abstract: Systems and methods are disclosed for receiving a target image corresponding to a target specimen, the target specimen comprising a tissue sample of a patient, applying a machine learning model to the target image to determine at least one characteristic of the target specimen and/or at least one characteristic of the target image, the machine learning model having been generated by processing a plurality of training images to predict at least one characteristic, the training images comprising images of human tissue and/or images that are algorithmically generated, and outputting the at least one characteristic of the target specimen and/or the at least one characteristic of the target image.

Abstract: The present disclosure discusses systems and methods to detect blur in digital images. The solution can be incorporated into the quality control systems of pathology and other slide scanners or can be a stand-alone solution. The solution can identify scanned images that include blur and cause the scanner to automatically rescan the blurry image. The solution can also identify regions of the scanned image that include blur. The solution can generate blur maps for each of the scanned images that identify regions of the scanned image that include blur.

Abstract: Systems and methods are disclosed for processing an electronic image corresponding to a specimen and automatically prioritizing processing of the electronic image. One method includes receiving a target electronic image of a slide corresponding to a target specimen, the target specimen including a tissue sample of a patient; computing, using a machine learning system, a prioritization value of the target electronic image, the machine learning system having been generated by processing a plurality of training images, each training image comprising an image of human tissue and a label characterizing at least one of a slide morphology, a diagnostic value, a pathologist review outcome, and/or an analytic difficulty; and outputting a sequence of digitized pathology images, wherein a placement of the target electronic image in the sequence is based on the prioritization value of the target electronic image.

Abstract: Systems and methods are disclosed for processing an electronic image corresponding to a specimen. One method for processing the electronic image includes: receiving a target electronic image of a slide corresponding to a target specimen, the target specimen including a tissue sample from a patient, applying a machine learning system to the target electronic image to determine deficiencies associated with the target specimen, the machine learning system having been generated by processing a plurality of training images to predict stain deficiencies and/or predict a needed recut, the training images including images of human tissue and/or images that are algorithmically generated; and based on the deficiencies associated with the target specimen, determining to automatically order an additional slide to be prepared.

Abstract: Systems and methods are disclosed for receiving a target image corresponding to a target specimen, the target specimen comprising a tissue sample of a patient, applying a machine learning model to the target image to determine at least one characteristic of the target specimen and/or at least one characteristic of the target image, the machine learning model having been generated by processing a plurality of training images to predict at least one characteristic, the training images comprising images of human tissue and/or images that are algorithmically generated, and outputting the at least one characteristic of the target specimen and/or the at least one characteristic of the target image.

Abstract: Embodiments relate to a high-pressure fuel pump having a pump piston which, during operation, moves in translation between a pressure chamber and a leakage chamber. The leakage chamber has a leakage collecting region and an equalizing region. A low-pressure damper having a bellows-shaped corrugated damper plate is arranged in the equalizing region.

Abstract: A fuel filler device that includes a flow conduction device arranged in a filler line and configured such that during a filling, an outlet pipe of a pump nozzle is guided and supported therein, and an attachment connected to the flow conduction device. The attachment includes a first attachment end, a second attachment end, and a constriction extending between the first attachment end and the second attachment end such that the attachment tapers from the first attachment end to the second attachment end via the constriction. At least one first gap is formed between the first attachment end and the flow conduction device so that during a filling sequence, fuel vapour introduced into the fuel filler device may flow through the at least one first gap into the filler line in a direction of a fuel tank connected to the filler line.

Abstract: The present disclosure is directed to systems and methods for classifying biomedical images. A feature classifier may generate a plurality of tiles from a biomedical image. Each tile may correspond to a portion of the biomedical image. The feature classifier may select a subset of tiles from the plurality of tiles by applying an inference model. The subset of tiles may have highest scores. Each score may indicate a likelihood that the corresponding tile includes a feature indicative of the presence of the condition. The feature classifier may determine a classification result for the biomedical image by applying an aggregation model. The classification result may indicate whether the biomedical includes the presence or lack of the condition.

Abstract: A method is disclosed for registration on setting an alignment of an instrument relative to an object during a processing or treatment of the object by the instrument. A working image is registered to a planning image. The working image is recorded in a viewing direction that is selected dependent upon relevant degrees of freedom of the instrument such that the relevant degrees of freedom are the degrees of freedom with the greater registration accuracy. In addition, a robot system is provided which is configured for carrying out the method.

Abstract: A nuclear facility includes a fuel element pool which is filled with a cooling liquid. A fuel element rack, which is disposed in the fuel element pool, includes compartments for receiving fuel elements. The fuel elements received in the compartments are in direct contact with the cooling liquid in the fuel element pool. At least one cooling element is disposed in one of the compartments instead of a fuel element. The cooling element acts as a heat exchanger through which a coolant can flow, the cooling element is connected into a cooling circuit and the cooling element is immersed in the cooling liquid.

Abstract: Various embodiments include a high-pressure fuel pump for a fuel injection system comprising: a housing defining a housing bore with a pressure chamber in a first end region and a leakage chamber in a second end region; a pump piston, during operation of the high-pressure fuel pump moved in translation between the pressure chamber and the leakage chamber along an axis; wherein the leakage chamber includes a leakage collecting region and an equalizing region arranged in circular annular fashion around the pump piston guiding section and extending parallel to the axis from the leakage collecting region toward the pressure chamber; and a low-pressure damper arranged in the equalizing region, the low-pressure damper comprising an annular piston damper and an annular piston guided to move along the axis within an annular bushing.

Abstract: Systems and methods for training and using an image classifier are provided. A plurality of points can be generated from respective patches of images annotated as either a first type or a second type. The points corresponding to the images of the second type can be clustered into two clusters. A first cluster of the two clusters can be identified as closer to the points corresponding to the images annotated as the first type. The points in the first cluster can be assigned to a class positive, the points in the second cluster can be assigned to a class negative, and the points corresponding to the images annotated as the first type can be assigned to an anchor class. A plurality of triplets can be generated based on the points in the various classes. Parameters of an image classifier can be adjusted based on a loss function of the triplets.

Abstract: A method, apparatus, and program product utilize a multi-step subsidence inversion to model lithospheric layer thickness through geological time for a rift basin in a subsurface formation.

Abstract: An electrical connecting device for a charging cable is for charging an electric vehicle. The electrical connecting device includes a network-side first connecting element for electrically connecting the connecting device to an electrical supply network and a charging-cable-side second connecting element for connecting the connecting device to a network-side connector of the charging cable. The first connecting element includes at least two contact elements, each connected in an electrically conductive manner to one of at least two contact elements of the second connecting element; and a first temperature sensor, used for temperature monitoring and which is electrically connected to the second connecting element via a communication cable. The second connecting element has a further contact, connectable to a corresponding further contact of the network-side connector of the charging cable to transmit a signal of the temperature sensor to the charging cable.