Abstract: A medical imaging and segmentation method comprising utilizing segmentation results obtained for 3D frames earlier in a same imaging session to initialize a segmentation model for subsequent 3D frames. This accelerates and stabilizes segmentation results, particularly in the context of a scanning procedure in which segmentation is performed in real time (on-the-fly) for each acquired frame.

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: A method and system for providing saliency maps for a deep learning model. The method comprises inputting an input image into the deep learning model trained to output a metric score, from a plurality of metric scores, for the input image. A supportive saliency map is generated for the input image, from the deep learning model, corresponding to a first range of the metric scores for the image, thereby providing one or more supportive regions of the image indicative of the first range of metric scores. A distractive saliency map is also generated for the image, from the deep learning model, corresponding to a second range of the metric scores for the image, thereby providing one or more distractive regions of the image indicative of the second range of metric scores.

Abstract: The invention concerns a device, a method, and an X-ray-system comprising such a device, for assisting in positioning at least one body part of a patient for an X-ray acquisition by an X-ray system, comprising a display for displaying the body part to a user, a first camera on a first side of the display, arranged and configured to monitor the body part, wherein the body part is monitored from a viewing perspective of the device, and a processing unit. The processing unit is configured to estimate an actual bone position of the body part based on one or more images captured by the first camera, determine a target bone position, calculate a difference between the estimated actual bone position and the target bone position. The device is configured to display by the display at least one of the target bone position, the estimated actual bone position, and the calculated difference between the estimated actual bone position and the target bone position overlaid over at least one image of the body part.

Abstract: A computer-implemented method of providing pose information for X-ray projection images, is provided. The method includes segmenting an X-ray projection image (120) to identify a plurality of projected sub-regions (1501 . . . m) of an anatomical structure, generating a pose metric for the X-ray projection image (120) based on a relative size of two or more of the projected sub-regions (1501 . . . m) in the segmented X-ray projection image (120), and outputting the pose metric to provide the pose information for the X-ray projection image (120).

Abstract: A method is provided for adapting a 3D field of view (FOV) in ultrasound data acquisition so as to minimize the FOV volume in a manner that is controlled and precise. The method comprises defining a volumetric region across which 3D ultrasound data is desired, and then adapting the data acquisition field of view (FOV) in dependence upon the defined volumetric region, to encompass the region. This is achieved based on adapting a scan line length (or scan depth) of each individual scan line based on the defined volumetric region. In some embodiments, the volumetric region may be defined based on anatomical segmentation of a reference ultrasound dataset acquired in an initial step, and setting the volumetric region in dependence upon boundaries of an identified object of interest. The volumetric region may in a subset of embodiments be set as the region occupied by a detected anatomical object of interest.

Abstract: A method and system for automatically detecting within an input 3D ultrasound image one or more suspected disease features and automatically computing an optimum one or more planes through the 3D field of view for acquiring imagery that would best assist in confirming or further analyzing the suspected disease features. The determined optimum one or more planes are used to control acquisition by an ultrasound acquisition system of new 2D images which correspond to said determined optimum planes.

Abstract: Systems, apparatuses and methods provide technology to automatically evaluate diagnostic images, including receiving a diagnostic image relating to a condition of a patient, performing a registration of the diagnostic image with reference to an anatomical structure, identifying one or more ROIs from the registered image, generating a feature distribution based on the one or more ROIs, analyzing the feature distribution to determine a quantification, the quantification reflecting the condition of the patient, and providing a diagnostic output based on the quantification. In embodiments, identifying a ROI includes identifying a field of interest in the registered image, the field of interest encompassing the one or more regions of interest, and dividing the field of interest into a plurality of sub-regions. In embodiments, generating a feature distribution includes generating an intensity histogram for each ROI.

Abstract: The invention relates to detecting anatomical abnormalities in medical images. In order to detect anatomical abnormalities, a computer-implemented method (100) and system are disclosed that detect 2D contours (130) of anatomical features in a medical image and compares these contours with predicted 2D contours (140) based on a 3D reference model in order to detect (150) anatomical abnormalities. This approach may improve accuracy of anatomical abnormality detection, thereby cutting time in a medical facility and potentially improving operator experiences and patient outcomes.

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 computer implemented method of making a measurement associated with a feature of interest in an image. The method comprises using (302) a model trained using a machine learning process to take the image as input and predict a pair of points between which to make the measurement of the feature of interest in the image. The method then comprises determining (304) the measurement, based on the predicted pair of points.

Abstract: A computer-implemented method for positioning a subject in medical imaging, comprising: receiving a first image (20) of a region of interest (14, 16) of the subject (S10); determining first positioning data based on the first image (20), wherein the first positioning data indicates an alignment of the region of interest (14, 16) relative to a first image acquisition unit used to acquire the first image (20) (S20); determining guidance data based on the first positioning data, wherein the guidance data comprises a guidance for an alignment of the region of interest (14, 16) relative to a second image acquisition unit used to acquire a second image (60) from a current alignment to a target alignment, wherein the target alignment is to correspond to that derived from the first positioning data (S30); providing the guidance data for acquiring the second image (60) (S40).

Abstract: The present invention relates to a method and system for predicting X-ray degradation, the system comprising; a generator (10) configured to generate a deployment fingerprint data set for recording cumulative radiation exposure of a currently deployed X-ray tube; a database (20) configured to provide a training data set comprising multiple tube fingerprint data sets for recording cumulative radiation exposure of previously deployed X-ray tubes correlated with failures of the previously deployed X-ray tubes; and a neural network (30) configured to be trained using the training data set and configured to predict at least one parameter of the currently deployed X-ray tube based on the training.

Abstract: A computer-implemented method of compensating for differences in medical images, is provided. The method includes receiving (S110) image data comprising a temporal series of medical images (1101. . .i). The temporal series includes one or more medical images generated by a first type of imaging modality (120), and one or more medical images generated by a second type of imaging modality (130, 130?). The first type of imaging modality is different to the second type of imaging modality. In one aspect, the method includes generating (S120a. S120b), from the temporal series of medical images (1101. .i), a normalised temporal series of medical images (1401. .i), and outputting (S130a. S130a?. S130b) the normalised temporal series of medical images (1401. . i) and/or one or more measurement values derived therefrom. In another aspect, the method includes generating (S120a. S120b), from the temporal series of medical images (1101 . .i), one or more normalised measurement values (1501. . .

Abstract: The present invention relates to a computer-implemented method for rendering soft tissue into an X-ray image. The method comprises the step of providing an articulated three-dimensional anatomical model of at least one joint of a body, wherein the model comprises a rigid structure and at least one type of soft tissue, and wherein the rigid structure comprises at least two bones connected by the joint. The method comprises further the steps of providing an X-ray image of a joint of a patient, wherein the joint of the patient corresponds to the joint of the anatomical model, and registering the anatomical model to the X-ray image. The method comprises further the steps of projecting the at least one type of soft tissue into the image domain of the X-ray image, and visualizing the at least one type of soft tissue in the X-ray image.

Abstract: The invention provides a method of imaging the heart. An ultrasound probe is controlled to receive first reflected ultrasound echo signals from the heart transmitted using first transmit parameters and an ultrasound image of the heart is created from the first reflected ultrasound echo signals using first echo signal processing parameters. Model-based segmentation is performed of the ultrasound image to identify anatomical structures of the heart, and, for at least one anatomical structure which has areas of dropout, the segmentation is used to extrapolate from the identified anatomical structures to identify the location within the image of the areas of dropout.

Abstract: Disclosed is a method for modelling a joint, the method comprising, processing first 3D surface image data of a body part in a first pose by means of an automatic pose retrieval method so as to obtain first articulation parameters representative of the first pose, wherein the body part comprises a first anatomical structure and a second anatomical structure connected by a joint; performing image registration between first medical image data of the body part, the first medical image data acquired simultaneously with the first 3D surface image data and depicting the first anatomical structure and the second anatomical structure, and second medical image data of the body part in a second pose, wherein the image registration is performed individually for each of the first anatomical structure and the second anatomical structure; determining transformation data representing one or more first transformations required to register the first anatomical structure in the first medical image data to the first anatomical

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: The present invention relates to a system and a method for detecting pain experienced by a patient in relation to a pose of the patient. The system comprises a pose estimation unit configured to estimate the pose of the patient and a pain detection unit configured to detect pain experienced by the patient. The system further comprises a processing unit configured to determine a correlation between the detected pain experienced by the patient and the estimated pose of the patient. The determined correlation can be displayed on a display unit to a physician.

Abstract: The present invention relates to medical imaging. In order to reduce repeat images, it is proposed to enable automated prediction of quality metrics prior to image formation by exploiting data from sensors. This may greatly improve the quality of medical image data acquired in the actual imaging examination, thereby leading to fewer retakes, less delayed treatment to patients, shortened workflow, and higher patient rate. In X-ray and CT exams, fewer retakes may also reduce radiation doses for patients.