Abstract: Machine learning is used to train a network to estimate a three-dimensional (3D) body surface and body regions of a patient from surface images of the patient. The estimated 3D body surface of the patient is used to determine an isocenter of the patient. The estimated body regions are used to generate heatmaps representing visible body region boundaries and unseen body region boundaries of the patient. The estimation of 3D body surfaces, the determined patient isocenter, and the estimated body region boundaries may assist in planning a medical scan, including automatic patient positioning.

Abstract: A method of determining a 3D center location of a specimen container on a track. The method includes providing a calibration object on the track; providing an initially calibrated image capture device adjacent to the track; moving the calibration object to at least two different longitudinal positions along the track; capturing a first image with the calibration object located at the first longitudinal position; capturing a second image with the calibration object located at the second longitudinal position; and determining a three-dimensional path trajectory of a center location along the track based at least upon the first image and the second image. The method can be used to determine a 3D center location of a specimen container imaged anywhere within a viewing area. Characterization apparatus and specimen testing apparatus adapted to carry out the methods are described, as are other aspects.

Abstract: A method of aligning a component to a structure in a diagnostic laboratory system. The method includes aligning a position sensor to the structure; sensing a position of the component using the position sensor; and calculating the position of the component relative to the structure based at least in part on the sensing. Other methods, apparatus, and systems are disclosed.

Abstract: Apparatus for robotic arm alignment in an automated sample analysis system includes a robotic arm, a sample tube carrier, a plurality of optical components (including, e.g., one or more cameras), and a controller. The controller is operative to process images received from the optical components to determine a first set of coordinates of a first marker relative to the sample tube carrier and determine a second set of coordinates of a second marker relative to the robotic arm. The controller is further operative to adjust the position of the robotic arm and/or the sample tube carrier in response to an excessive offset between the first and second sets of coordinates. In some embodiments, a positioning tool includes the first and second markers thereon. Methods of robotic arm alignment with a sample tube carrier in an automated sample analysis system are also provided, as are other aspects.

Abstract: Methods of predicting a fault in a diagnostic laboratory system include providing one or more sensors; generating data using the one or more sensors; inputting the data into an artificial intelligence algorithm, the artificial intelligence algorithm configured to predict at least one fault in the diagnostic laboratory system in response to the data; and predicting at least one fault in the diagnostic laboratory system using the artificial intelligence algorithm. Other methods, systems, and apparatus are also disclosed.

Abstract: A system for holding and controlling medical instruments during procedures includes an end effector configured to hold a medical instrument and a rotational and translational (RT) mechanism configured to rotate and translate the medical instrument along an insertion axis. The system further includes a platform coupled to the RT mechanism and a pair of parallel five-bar planar linkages configured to translate, pitch, and yaw the platform with respect to a principal axis that is parallel to the insertion axis.

Abstract: Methods of identifying a defect in a machine vision system. Embodiments of the method include providing a first imaging device having a first field of view; moving a reflective tool through the first field of view; capturing a plurality of images of the reflective tool at different locations in the first field of view using the first imaging device; and analyzing at least one of the plurality of images to identify one or more defects in the machine vision system. Systems and apparatus configured to carry out the methods are provided, as are other aspects.

Abstract: A method of characterizing a serum or plasma portion of a specimen in a specimen container provides an HILN (hemolysis, icterus, lipemia, normal) determination. Pixel data of an input image of the specimen container is processed by a classification network to identify whether the specimen contains plasma or serum. Pixel data representing a plasma sample are forwarded to a segmentation/classification/regression network trained with plasma samples for HILN determination. Pixel data representing a serum sample are forwarded to a transformation network, wherein the serum sample pixel data is transformed into pixel data that matches pixel data of a corresponding previously-collected plasma sample by changing sample color, contrast, intensity, and/or brightness. The transformed serum sample pixel data are forwarded to the segmentation/classification/regression network for HILN determination. Quality check modules and testing apparatus configured to carry out the method are also described, as are other aspects.

Abstract: A generative adversarial network (GAN) (21, 24), or any other generative modeling technique, is used to learn (12) how to generate (68) an optimal robotic system given performance, operation, safety, or any other specifications. For instance, the specifications may be modeled (65) relative to anatomy to confirm satisfaction of anatomy-based or another task specific constraint. A machine-learning system, for instance neural network, is trained (12) to translate given specifications to a robotic configuration. The network may convert task-specific specifications into one or more configurations of robot modules into a robotic system. The user may enter (67) changes to performance in order for the network to estimate (62) appropriate configurations. The configurations may be converted (64) to estimated performance by another machine-learning system, for instance neural network, allowing modeling (65) of operation relative to the anatomy, such as anatomy based on medical imaging.

Abstract: For quantification of blood flow by an ultrasound system, B-mode images generated with a multi-transmit, coherent image formation produce swirling or other speckle patterns in the blood regions. These patterns, as represented in specially formed B-mode images, are tracked over time to indicate two or three-dimensional velocity vectors of the blood at a B-mode resolution. Various visualizations may be provided at the same resolution, including the velocity flow field, flow direction, vorticity, vortex size, vortex shape, and/or divergence.

Abstract: For training a machine learning system for representing a patient body a plurality of stored medical imaging data sets each representing at least a part of a respective patient are obtained. A first one of the plurality of stored medical imaging data sets represents a different part of the patient body than a second one of the plurality of stored medical imaging data sets. A plurality of landmarks in the stored medical imaging data sets are estimated, and each of the stored medical imaging data sets are aligned to a predefined pose using the plurality of landmarks. A plurality of points in the aligned medical imaging data sets are sampled, and the machine learning system is trained based on at least the plurality of points. The learned parameters of the machine learning system are then stored and used in a method for inferring a body representation.

Abstract: For robotically operating a catheter, translation and/or rotation manipulation is provided along the shaft or away from the handle, such as near a point of access to the patient. A worm drive arrangement may allow for both translation and rotation of the shaft. Some control may be provided by robotic manipulation of the handle, while other control (e.g., fine adjustments) are made by robotic manipulation of the shaft.

Abstract: Machine learning is used to train a network to estimate a three-dimensional (3D) body surface and body regions of a patient from surface images of the patient. The estimated 3D body surface of the patient is used to determine an isocenter of the patient. The estimated body regions are used to generate heatmaps representing visible body region boundaries and unseen body region boundaries of the patient. The estimation of 3D body surfaces, the determined patient isocenter, and the estimated body region boundaries may assist in planning a medical scan, including automatic patient positioning.

Abstract: Object specific in-homogeneities in an MRI system are corrected. Prescan information available at the MR imaging system is determined. The prescan information includes at least object specific information of an object located in the MR imaging system from which an MR image is to be generated. The prescan information does not include a B1 map of the MRI system with the object being present in the MR imaging system. The prescan information is applied to a trained machine learning module provided at the MRI system. The trained machine learning module determines and generates shimming information as output. The shimming information is applied to a shimming module of the MR imaging system, wherein the shimming module uses the shimming information to generate a corrected magnetic field B0.

Abstract: For quantification of blood flow by an ultrasound system, B-mode images generated with a multi-transmit, coherent image formation produce swirling or other speckle patterns in the blood regions. These patterns, as represented in specially formed B-mode images, are tracked over time to indicate two or three-dimensional velocity vectors of the blood at a B-mode resolution. Various visualizations may be provided at the same resolution, including the velocity flow field, flow direction, vorticity, vortex size, vortex shape, and/or divergence.

Abstract: Machine learning is used to train a network to estimate a three-dimensional (3D) body surface and body regions of a patient from surface images of the patient. The estimated 3D body surface of the patient is used to determine an isocenter of the patient. The estimated body regions are used to generate heatmaps representing visible body region boundaries and unseen body region boundaries of the patient. The estimation of 3D body surfaces, the determined patient isocenter, and the estimated body region boundaries may assist in planning a medical scan, including automatic patient positioning.

Abstract: Patient biographic data may be estimated by receiving patient image data, applying the patient image data to a machine learned model, the machine learned model trained on second patient data and trained to map the second patient data to associated biographic data using machine learned features, generating the patient biographic data based on the applying and the machine learned features, and outputting the patient biographic data. The patient biographic data may include a patient weight, a patient height, a patient gender, and a patient age.

Abstract: Camera-based respiratory triggered medical scanning is provided. A camara captures an image or images of a patient. A processor detects breathing from the camera image or images. Detected breathing is used to automatically trigger the medical scan. An extra breathing sensor is not needed. Manual monitoring is not relied upon.

Abstract: Systems and methods for determining an assessment of a patient for a medical condition are provided. Input medical data of a patient is received. A vector representing a state of the patient is generated based on the input medical data. An assessment of the patient for a medical condition is determined using a machine learning based network based on the vector. The assessment of the patient is output.

Abstract: Systems and methods for determining an assessment of a patient for a medical condition are provided. Input medical data of a patient is received. A knowledge graph is computed based on the input medical data. A vector representing a state of the patient is generated based on the knowledge graph. An assessment of the patient for a medical condition is determined using a machine learning based network based on the vector. The assessment of the patient is output.