Abstract: A system and method for managing medical image data items. A large image manager is used to store medical image data items external to a core PACS. Representative objects are generated and provided to the PACS to be incorporated into the core PACS workflows. The representative objects can be generated by extracted pixel data and metadata from the medical image data items. The representative objects are generated in a format compatible with the protocol used by the PACS workflows. Requests sent to the PACS for medical images can be re-routed to the large image manager to provide the requested images.

Abstract: Systems and methods for integrating a plurality of healthcare software applications. A user initiates one or more software applications required to perform different parts of a healthcare task. The software applications include a local application installed on the user's device and a web-based application accessed through a browser. A host application is launched in order to facilitate local two-way communication between the local application and the web-based application. The host application generates a local communication server on the user device through which the local application and web application communicate. This allows a user to easily and efficiently perform multiple parts of the healthcare tasks. This also allows different healthcare software applications to be integrated without requiring any plug-ins or other integration components to be installed on the user's device.

Abstract: Method of segmenting anatomical structures such as organs in 3D scans in an architecture that combines U-net, time-distributed convolutions and bidirectional convolutional LSTM.

Abstract: A neural network, trained for the task of deriving the attribution of image regions that significantly influence classification in a tool for pathology classification, comprising (i) a contracting branch, (ii) an attenuation module, (iii) an interconnected upsampling branch, and (iv) a final mapping module.

Abstract: A method for finding image regions that significantly influence classification in a tool for pathology classification in a medical image wherein image regions that influence classification are inpainted, by replacing the pixels in these regions by representations of heathy tissue, resulting in an image with a healthy classification-score in the classification tool.

Abstract: A computer-implemented method which, given a set of procedure definitions in a first radiology information system generates the best match for a procedure definition defined in a second system on the basis of a multidimensional vector representation of procedure definitions and a matching algorithm based on vector cosine similarity.

Abstract: A method and system for parallel processing of data messages in a healthcare communication network for coordinating concurrent processing of messages between computer systems over a network. The method and system include determining if a precondition for immediate processing of a message for a clinical workflow type exists, and whether or not the precondition is fulfilled, by looking up a message type and a workflow type of the message in a preconditions table database.

Abstract: A method for training an artificial neural network on an additional untrained segmentation task prevents the loss of previously acquired segmentation skills on originally trained segmentation tasks.

Abstract: A pipe-line method for multi-label segmentation of anatomic structures in a medical image using a convolutional neural network trained with a weighted loss function takes into account under—representation of at least one anatomical structure in a ground-truth mask relative to other anatomical structures. Different architectures for the convolutional neural network are described.

Abstract: A method and system to correct for alignment errors between assumed and actual geometric parameters of an acquisition geometry during image reconstruction in a chest tomosynthesis application includes receiving at least 2 raw projection images acquired on at least 2 different positions in a known acquisition geometry, determining an actual geometric parameter value by determining the minimum of a redundant planes cost function which is calculated for a varying range of the geometric parameter values, and which is determined by: a) at least one plane which intersects an X-ray source trajectory with at least two points, b) an intersection between the planes and a detector surface for which points the source positions are determined, and c) for which the parameters determining the intersection (?, ?, l) are used for the construction of the cost function, applying the calculated actual geometric parameter value of the acquisition geometry for the image reconstruction of the plurality of images, characterized in t

Abstract: A system and method for compiling a clinically logical medical dossier for a patient. A list of medical conditions can be determined for the patient. A plurality of medical imaging records for the patient can be identified, and each record can be assigned to one of the conditions. A timeline of condition-specific imaging records can then be generated for each condition. A condition can be selected and the timeline of condition-specific imaging records for the selected condition can then be displayed.

Abstract: A system for creating a semantic data warehouse including a convergence service configured to execute queries to connected data sources, to convert data from source to domain semantics, and to aggregate converted data. The convergence service is configured to invoke by an entity graph service that, on demand, defines a semantic entity representation, the needed queries and data sources to be queried; and projects and makes available the resulting data in the semantic entity representation.

Abstract: On the basis of user input a set of contour points of a 3D object is detected in a number of 2D slice images representing the 3D object. Next a 2D object is segmented in each of the slice images by the set of contour points so as to obtain segmentation masks. Finally, by interpolation between computed segmentation masks, the 3D object is segmented.

Abstract: A radiation image capturing system includes a processing unit that determines at least three distances between at least one first distance sensor provided at a radiation generation unit and at least three second distance sensors provided at a detection unit based on one or more signals emitted by the first distance sensor, and that determines an orientation of the radiation generation unit and the detection unit relative to each other based on inclination information provided by a first sensor unit provided at the radiation generation unit and a second sensor unit provided at the detection unit. Alternatively, the processing unit determines distances between at least three first distance sensors provided at the radiation generation unit and at least three second distance sensors provided at the detection unit based on signals emitted by the at least three first distance sensors to determine an orientation of the radiation generation unit and the detection unit relative to each other.

Abstract: A method and system for automatically detecting systemic arteries in arbitrary field-of-view computed tomography angiography (CTA) includes fully-automatically analyzing a medical image represented by a digital image representation.

Abstract: A system and method for collecting medical image data items. A central processor identifies a new medical image data file on a remote image storage memory. The central processor determines that the new medical image data file is a completed file and copies the completed file to a central storage memory. The central processor determines an expected set of files corresponding to the medical image data file that defines a medical image data item. The central processor determines that each of the medical image data files in the expected set have been copied to the central storage memory. The central processor then generates an indicator that the medical image date item is available on the central storage memory.

Abstract: A digital encoding and decoding method of high bit-depth gray scale medical images allows standard 3-channel color image compression algorithms to be used to compress and de-compress such encoded high bit-depth gray scale images without significant image quality loss. The digital encoding and decoding method may be used to improve the network transmission, storage and rendering of such gray scale images in a standard web browser.

Abstract: A method, and an according apparatus and system, for analyzing medical images of blood vessels includes the steps of a) classifying a surrounding of at least one vessel represented in at least one medical image by applying a first classifier to the medical image such that the surrounding of the vessel is assigned to one of at least two surrounding classes, and b) segmentation of the at least one vessel dependent on the surrounding class to which the surrounding of the vessel has been assigned. The invention allows for a reliable segmentation and/or shape detection, in particular bifurcation detection, of blood vessels represented in medical images.

Abstract: A system and method for managing medical image data items. Pixel data and metadata are identified in the medical image data items. A plurality of pixel objects are generated using the pixel data. The plurality of pixel objects are stored in a first storage memory. A plurality of representative objects are generated using the metadata. The representative objects are stored in a second storage memory. The representative objects may include overview objects and representative metadata objects. The representative objects can be generated in a DICOM-compatible format suitable for PACS workflows.

Abstract: A system and method for managing medical image data items. Pixel data and metadata are identified in the medical image data items. A plurality of pixel objects are generated using the pixel data. The plurality of pixel objects are stored in a first storage memory. A plurality of representative objects are generated using the metadata. The representative objects are stored in a second storage memory. The representative objects may include overview objects and representative metadata objects. The representative objects can be generated in a DICOM-compatible format suitable for PACS workflows.