Abstract: A method of analyzing an ultrasound image involves assessing the quality of the image in terms of which features of interest have been identified in the image and assessing a segmentation quality relating to the quality of a segmentation of the image. The two quality assessments are combined to derive and output an overall quality assessment for biometry measurements obtained from the image.

Abstract: A method for segmenting a target anatomy in ultrasound data. Scan-converted ultrasound data is obtained within a scan-converted space in the Cartesian coordinate system. The scan-converted ultrasound data is transformed to de-scanned ultrasound data within a de-scanned space in the Toroidal coordinate system. The de-scanned ultrasound data is an estimate of the ultrasound data as obtained by an original acquisition procedure. A segmentation of a target anatomy can thus be performed on the ultrasound data in the de-scanned space The resulting segmentation data can then be re-scanned back to the Cartesian coordinate system for display with the ultrasound data.

Abstract: The present invention relates to localizing stenoses. In order to provide improved and facilitated stenosis localization, a device (10) for localizing a stenosis in an angiogram is provided. The device comprises an image supply (12), a data processor (14) and an output (16). The image supply is configured to provide a first image (18) and a second image (20). The first image is an angiographic image that comprises image data representative of a region of interest of a vascular structure in a visible and distinct manner, wherein the vascular structure comprises at least one vessel with at least a part of a stenosis. The second image is a treatment X-ray image that comprises image data representative of at least a part of an interventional device arranged within the vascular structure in a state when the stenosis of the vascular structure is treated.

Abstract: The invention provides a method for determining a global confidence index for a 2D ultrasound image extracted from a 3D ultrasound volume, wherein the global confidence index indicates the suitability of the 2D ultrasound image for medical measure-ments. The method comprises obtaining a 3D ultrasound volume of a subject and extracting a set of at least one 2D ultrasound image from the 3D ultrasound volume. A set of geometrical indicators are then obtained with a first neural network, wherein each geometrical indicator indicates geometrical features of the anatomy of the subject. The set of 2D ultrasound images are then processed with a second neural network, wherein the output of the second neural network is a set of anatomical indicators and wherein the anatomical indicators indicate at least the presence of anatomical landmarks. A global confidence index is then determined for each one of the set of 2D ultrasound images based on the geometrical indicators and the anatomical indicators.

Abstract: The invention provides a method for performing an assessment of a placenta. The method includes obtaining a 3D ultrasound image of a uterus (210) and segmenting the placenta (220). A 3D rendering (200) of the uterus is then generated, wherein the generating includes: identifying a position of the placenta within the uterus with respect to an anatomical structure such as the cervix (250); obtaining anatomical reference data relating to a potential risk associated with the position of the placenta within the uterus; and comparing the position of the placenta and the anatomical reference data. A 3D rendering of the uterus is generated that comprises a 3D rendering of the placenta, marked with an indicator that is altered based on the comparison of the position of the placenta and the anatomical reference data. The appearance of the indicator may vary according to e.g. risk type/severity.

Abstract: A method, system and computer-program product for identifying neural network inputs for a neural network that may have been incorrectly processed by the neural network. A set of activation values (of a subset of neurons of a single layer) associated with a neural network input is obtained. A neural network output associated with the neural network input is also obtained. A determination is made as to whether a first and second neural network input share similar sets of activation values, but dissimilar neural network outputs or vice versa. In this way a prediction can be made as to whether one of the first and second neural network inputs has been incorrectly processed by the neural network.

Abstract: An ultrasound image processing apparatus (16) is disclosed comprising a processor arrangement (46, 50) adapted to receive a temporal sequence (15) of ultrasound images (150) of at least a chest region (151) of a fetal entity (62) from an ultrasound probe (14), said chest region including the fetal heart (171), said temporal sequence capturing at least part of a cardiac cycle of the fetal heart; identify the chest region of the fetal entity in one or more of the ultrasound images of said temporal sequence; identify a portion of the spine in the identified chest region; calculate an orientation axis (160) of the fetal chest from the identified chest region and the identified spine portion; identify the septum of the fetal heart as a linear structure which is temporally more stable than its surrounding structures in said temporal sequence of ultrasound images and which defines a region of convergence of the movements of the fetal heart during said cardiac cycle; calculate an orientation axis (170) of the fetal h

Abstract: A computer implemented method is provided for processing a 3D fetal ultrasound image. A 3D fetal ultrasound image is obtained (either acquired or received from memory), and the spine is detected within the image. This enables a first reference axis to be defined. A second reference axis is defined perpendicular to the first reference axis, and the 3D fetal ultrasound image is updated (e.g. rotated in 3D space) using the first and second reference axes and an up/down (elevation) orientation detection. This provides a normalization of the orientation of the image, so that a machine learning approach is better able to identify landmarks within new images.

Abstract: The present invention relates to a guidance for treatment of a chronic total occlusion. In order to provide improved guidance information for chronic total occlusion treatment, a device (10) for guidance for treatment of a chronic total occlusion is provided that comprises an image supply (12), a data processor (14) and an output (16). The image supply provides a sequence of angiographic images comprising a vascular structure. The data processor detects at least one portion of the vascular structure indicating a total occlusion of a vessel based on the sequence of angiographic images; and determines an image of the sequence of images that shows at least one segment of the vessel next to the total occlusion; and generates guidance image data based on the determined image. The output provides the generated guidance image data. Thus, additional information relating to spatial aspects is provided to the user based on 2D image data.

Abstract: The invention provides an ultrasound imaging method for determining complementary views of interest based on an anomalous feature identified in a region of interest of an ultrasound image. The method includes obtaining an ultrasound image of a region of interest of a subject and identifying an anomalous feature within said region. The identified anomalous feature may then be used to determine one or more available complementary ultrasound images of interest of the subject. The one or more available complementary ultrasound images may then be displayed to a user and the complementary ultrasound views to be reviewed may then be selected by the user from the displayed available complementary ultrasound images.

Abstract: The invention provides a method for guiding the acquisition of an ultrasound image. A 3D ultrasound image is acquired by an ultrasound probe at a first position and an anatomical structure is identified within the 3D ultrasound image. A target imaging plane is estimated based on the identified anatomical structure and it is determined whether the target imaging plane is present within the 3D ultrasound image. If the target imaging plane is present, a displacement between a central plane of the 3D ultrasound image and the target plane is determined. If the displacement is below a predetermined threshold, the target imaging plane is extracted and if the displacement is above the predetermined threshold, an instruction to acquire a 3D ultrasound image with the ultrasound probe at a second position, different from the first position, is generated based on the displacement. The invention further provides a method for estimating a target imaging plane.

Abstract: A method, system and computer-program product for identifying neural network inputs for a neural network that may have been incorrectly processed by the neural network. A set of activation values (of a subset of neurons of a single layer) associated with a neural network input is obtained. A neural network output associated with the neural network input is also obtained. A determination is made as to whether a first and second neural network input share similar sets of activation values, but dissimilar neural network outputs or vice versa. In this way a prediction can be made as to whether one of the first and second neural network inputs has been incorrectly processed by the neural network.

Abstract: A computer implemented method is provided for processing a 3D fetal ultrasound image. A 3D fetal ultrasound image is obtained (either acquired or received from memory), and the spine is detected within the image. This enables a first reference axis to be defined. A second reference axis is defined perpendicular to the first reference axis, and the 3D fetal ultrasound image is updated (e.g. rotated in 3D space) using the first and second reference axes and an up/down (elevation) orientation detection. This provides a normalization of the orientation of the image, so that a machine learning approach is better able to identify landmarks within new images.

Abstract: An ultrasound image processing apparatus (16) is disclosed comprising a processor arrangement (46, 50) adapted to receive a temporal sequence (15) of ultrasound images (150) of at least a chest region (151) of a fetal entity (62) from an ultrasound probe (14), said chest region including the fetal heart (171), said temporal sequence capturing at least part of a cardiac cycle of the fetal heart; identify the chest region of the fetal entity in one or more of the ultrasound images of said temporal sequence; identify a portion of the spine in the identified chest region; calculate an orientation axis (160) of the fetal chest from the identified chest region and the identified spine portion; identify the septum of the fetal heart as a linear structure which is temporally more stable than its surrounding structures in said temporal sequence of ultrasound images and which defines a region of convergence of the movements of the fetal heart during said cardiac cycle; calculate an orientation axis (170) of the fetal h