Abstract: A method and system for correcting a difference in contrast agent density in a sequence of contrast-enhanced image frames. A reference image frame is defined in the sequence of contrast-enhanced image frames, and segmentation is performed on the reference image frame to determine a location of a region of interest within the reference image frame. The region of interest is a region of the reference image frame that contains contrast agent. Other image frames in the sequence of contrast-enhanced images are corrected based on a difference in contrast agent density/image intensity in the region of interest relative to the region of interest in the reference image frame.

Abstract: The invention provides for a medical imaging system (100, 400) comprising a memory (110) storing machine executable instructions (120) and a configured artificial neural network (122). The medical imaging system further comprises a processor (104) configured for controlling the medical imaging system. Execution of the machine executable instructions causes the processor to receive (200) magnetic resonance imaging data (124), wherein the magnetic resonance imaging data is BOLD functional magnetic resonance imaging data descriptive of a time dependent BOLD signal (1100) for each of a set of voxels. Execution of the machine executable instructions further causes the processor to construct (202) a set of initial signals (126) by reconstructing the time dependent BOLD signal for each of the set of voxels using the magnetic resonance imaging data.

Abstract: A system and method for achieving more accurate results when applying an image processing task to a series of medical images of a patient, without significantly increasing processing resource. The proposed system and method is based on receiving a plurality of image sequences of a particular anatomical region, each capturing cyclical movement of an anatomical object. Each image sequence is supplied to a classifier module which employs use of one or more machine learning algorithms to derive at least one score for each image sequence indicative of predicted success or quality of a result of the image processing task if applied to the given image series. This permits an assessment to be made in advance of which of the plurality of image series is most likely to result in the best (e.g. highest quality, or greatest amount of information) results from the image processing task.

Abstract: A method is provided for generating an ultrasound image of an anatomical region having a volume. First image low resolution image data is enhanced by adapting a 3D anatomical model to the image data to generate a second, greater, quantity of ultrasound image data in respect of the anatomical region. The enhanced volumetric information is then displayed. An anatomical model is thus used to complete partial image data thereby increasing the image resolution, so that a high resolution volumetric image can be displayed with a reduced image capture time.

Abstract: A method is provided for generating an ultrasound image of an anatomical region having a volume. First image low resolution image data is enhanced by adapting a 3D anatomical model to the image data to generate a second, greater, quantity of ultrasound image data in respect of the anatomical region. The enhanced volumetric information is then displayed. An anatomical model is thus used to complete partial image data thereby increasing the image resolution, so that a high resolution volumetric image can be displayed with a reduced image capture time.

Abstract: The invention provides a method for determining a confidence value for an image segmentation. The method includes obtaining an image, wherein the image comprises a view of an anatomical structure and a model of the anatomical structure is obtained, wherein the model comprises a plurality of nodes. The image is processed to generate a plurality of image segmentation outputs, wherein each image segmentation output comprises a set of values for the view, wherein each value of the set of values is associated with a node of the plurality of nodes of the model. For each node of the model, a confidence value is determined based on the plurality of values corresponding to the node. A confidence map of the anatomical structure is generated based on the confidence value of each node.

Abstract: A mechanism for generating a rendering of a left atrial appendage of a patient. The potential position of one or more interventional devices within the left atrial appendage is determined from model data that contains an anatomical model of the left atrial appendage. A rendering of the left atrial appendage is generated, from image data, and subsequently displayed. Visual parameters of the displayed rendering of the left atrial appendage are responsive to the determined potential position(s) for the one or more interventional devices.

Abstract: The present invention relates to an image processing apparatus for deriving multi-dimensional images of an object and an according system and method. The image processing apparatus comprises an interface configured to provide 3D image data of an object and to provide a sequence of images of the object. The image processing apparatus further comprises a processing unit configured to obtain a personalized 3D model of the object by applying a model-based segmentation to the 3D image data of the object and to adapt the personalized 3D model based on at least a part of the images of the sequence of images of the object.

Abstract: An ultrasound imaging system for acquiring ultrasound images of an anatomical feature of interest in a subject, comprising a controller operable by a user and configured to: process input ultrasound images to extract anatomical data; determine a set of constraints to be applied to the ultrasound images, the constraints being spatial, temporal and/or of image quality, derived from the extracted anatomical data and/or on user input; monitor the ultrasound images, as they are received, for determining their compliance with the determined constraints; and output an indication based on the determined compliance. The user can adapt the imaging process using the feedback of these indications, and can decide to stop the process based on satisfactory indications.

Abstract: A system (100) and computer-implemented method are provided for data collection for distributed machine learning of a machine learnable model. A privacy policy data (050) is provided defining computer-readable criteria for limiting a selection of medical image data (030) to a subset of the medical image data to obfuscate an identity of the at least one patient. The medical image data is selected based on the computer-readable criteria to obtain privacy policy-compliant training data (060) for transmission to another entity. The system and method enable medical data collection at clinical sites without requiring manual oversight, and enables such selections to be made automatically, e.g., based on a request for medical image data which may be received from outside of the clinical site.

Abstract: A mechanism for determining a score indicative of a success of a segmentation of a 3D image, i.e. a success score. The mechanism proposes to obtain one or more 2D images of different target views of a target object in the 3D image, by processing a segmentation result of the 3D image. (A view of) each 2D image is classified using an automated classifier. The classification results are used to determine a success score, which may indicate, for example, whether, or how closely, the 3D segmentation result represents a ground truth segmentation result with sufficient accuracy, e.g. for clinical decision making.

Abstract: An ultrasound imaging system comprises a display for displaying a received ultrasound image. A user interface is provided for receiving user commands for controlling the ultrasound imaging process, and it receives a user input which identifies a point or region of the displayed ultrasound image. An image depth is determined which is associated with the identified point or region and the imaging process is controlled to tailor the imaging to the identified point or region.

Abstract: A method (10) that encodes electrode locations to a mean scalp mesh for adaptation to subsequent image scans.

Abstract: The invention provides a method for refining a mapped surface mesh of a cardiac chamber. The method includes obtaining a mapped surface mesh of the cardiac chamber anatomy, wherein the mapped surface mesh comprises a central region representing a cardiac chamber and an outer region representing a peripheral cardiac structure connected to the cardiac chamber, and wherein the mapped surface mesh comprises a first view of an anatomical landmark within the cardiac chamber, and obtaining image data of a cardiac chamber anatomy of a subject. The central region of the mapped surface mesh is deformed based on a first segmentation algorithm configured according to one or more predetermined shape- constraints and the outer region of the mapped surface mesh is deformed based on a second segmentation algorithm configured according to the image data, thereby generating a deformed outer region. The deformed central region and the deformed outer region are then combined, thereby generating a refined mapped surface mesh.

Abstract: A mechanism for creating/synthesizing realistic training data, for training a machine-learning model, using anatomical knowledge. An anatomical model can be obtained. Information from annotated training data entries (i.e. “ground truth” information), can be used to model the anatomical variation, from the obtained model, in the population of the training data. This anatomical model can then be modified, e.g. incorporating some random factors, in order to generate one or more augmented models of realistic anatomies. The augmented anatomy is then transferred from the model domain to the data entry domain to thereby generate a new data entry or data entries for training a machine-learning model. This latter process can be achieved in various ways, e.g. using GANs, such as CycleGANs and label images, or deformation vector fields.

Abstract: An ultrasound image processing apparatus (10) is disclosed comprising a processor arrangement (16) adapted to map a model (1) of an anatomical feature of interest onto an ultrasound image showing at least a section of said anatomical feature of interest and to segment said ultrasound image in accordance with the mapped model; and a touchscreen display (18, 19) adapted to display said ultrasound image including the mapped anatomical model. The processor arrangement is responsive to the touchscreen display and adapted to recognize a type of a user touch motion (3) provided through the touchscreen display (18, 19), each type of user touch motion being associated with a particular type of alteration of said mapping and alter said mapping in accordance with the recognized type of user touch motion. Also disclosed are an ultrasound imaging system, a computer-implemented method and a computer program product.

Abstract: The present invention relates to a system (10) for functional magnetic resonance image data acquisition. The system comprises an input unit (20), a magnetic resonance imaging “MRI” device (30), an electroencephalography “EEG” data acquisition device (40), and a processing unit (50). The input unit is configured to provide task based information to a patient, wherein the task based information extends over a period of time. The MRI device is configured to acquire functional magnetic resonance imaging “fMRI” data relating to brain activity of the patient, wherein the fMRI data extends over the period of time. The EEG device is configured to acquire EEG data relating to electrical activity of the brain of the patient, wherein the EEG data extends over the period of time. The processing unit is configured to utilize the task based information that extends over the period of time and the EEG data that extends over the period of time to determine at least one first sub-set period of time over the period of time.

Abstract: Provided is a method (200) for generating a combined anatomical model of a heart. The method comprises receiving (220) a non-contrast agent-enhanced ultrasound image of a left ventricular region of the heart and receiving (240) a contrast agent-enhanced ultrasound image of the left ventricular region of the heart. Image registration (260) is performed on the respective non-contrast agent-enhanced and contrast agent-enhanced ultrasound images, such that the respective images are aligned. Combined segmentation (270) of the aligned non-contrast agent-enhanced and contrast agent-enhanced ultrasound images is then carried out to generate the combined anatomical model. The combined segmentation (270) uses features of both of the aligned non-contrast agent-enhanced and contrast agent-enhanced ultrasound images as target points. Further provided is a processor arrangement adapted to implement the method and an ultrasound system comprising the processor arrangement.

Abstract: A system (SYS) for supporting a medical procedure, comprising an interface (IN) for receiving at least one medical input signal that describes a state of a target anatomy. A signal analyzer (SA) is configured to analyze the medical input signal to determine a time window for deployment of a cardio-vascular device (CL) to be deployed by a deployment.

Abstract: The present disclosure relates to a medical imaging method, comprising: receiving (201) a set of subject parameters descriptive of a subject; in response to inputting (203) the set of subject parameters into a trained deep neural network, DNN, receiving (205) from the trained DNN a predicted task; presenting the task to the subject; controlling (207) an MRI system (700) for acquiring fMRI data from the subject in response to the predicted task performed by the subject during the acquisition