Abstract: A computer-implemented method comprises: receiving a measurement data set, the measurement data set including energy resolved data based on a computed tomography scan of the patient; reconstructing a morphology preserving image data set based on a first photon-energy band or a first combination of photon-energy bands described by the measurement data set; segmenting a blood pool within a myocardium in the morphology preserving image data set; reconstructing a contrast agent map based on a second photon-energy band or a second combination of photon-energy bands described by the measurement data set; determining a reference value based on at least one pixel or voxel of the contrast agent map within the segmented blood pool; and determining a respective myocardial extracellular volume fraction depending on the reference value and a value given for at least one respective pixel or voxel outside the segmented blood pool by the contrast agent map.

Abstract: A computer-implemented method is for evaluating a CT data set of a coronary region of a patient regarding perivascular tissue of at least one target blood vessel. In an embodiment, the computer-implemented method automatically determines a centerline of at least the at least one target blood vessel in the CT data set; defines a region of interest as including at least one defined outer region radius around an extension interval of the centerline, the outer region radius being relatively larger than a radius of the at least one target blood vessel; and calculates at least one quantitative value from CT data in the region of interest.

Abstract: A computer-implemented method is for evaluating a CT data set of a coronary region of a patient regarding perivascular tissue of at least one target blood vessel. In an embodiment, the computer-implemented method automatically determines a centerline of at least the at least one target blood vessel in the CT data set; defines a region of interest as including at least one defined outer region radius around an extension interval of the centerline, the outer region radius being relatively larger than a radius of the at least one target blood vessel; and calculates at least one quantitative value from CT data in the region of interest.

Abstract: Systems and methods for automated assessment of a vessel are provided. One or more input medical images of a vessel of a patient are received. A plurality of vessel assessment tasks for assessing the vessel is performed using a machine learning based model trained using multi-task learning. The plurality of vessel assessment tasks comprises segmentation of reference walls of the vessel from the one or more input medical images and segmentation of lumen of the vessel from the one or more input medical images. Results of the plurality of vessel assessment tasks are output.

Abstract: Systems and methods for automated assessment of a vessel are provided. One or more input medical images of a vessel of a patient are received. A plurality of vessel assessment tasks for assessing the vessel is performed using a machine learning based model trained using multi-task learning. The plurality of vessel assessment tasks are performed by the machine learning based model based on shared features extracted from the one or more input medical images. Results of the plurality of vessel assessment tasks or a combination of the results of the plurality of vessel assessment tasks are output.

Abstract: A computer-implemented method for performing at least one measurement in an anatomical vessel structure in an imaging region, the vessel structure comprising multiple vessels of interest for the measurement, the method comprises receiving a three-dimensional image data set of the imaging region; determining a two-dimensional unfolded image of the vessel structure from the image data set; displaying the unfolded image to the user; determining at least one landmark in the vessel structure and visualizing the at least one landmark at a corresponding landmark position in the unfolded image; performing the at least one measurement based on the at least one landmark and the three-dimensional image data set; and displaying the result of the at least one measurement in the unfolded image in a user presentation or together with the unfolded image in the user presentation.

Abstract: A method is for providing an aggregate algorithm for processing medical data. In an embodiment, a multitude of local algorithms are trained by machine learning. The training of each respective local algorithm is performed on a respective local system using respective local training data. A respective algorithm dataset concerning the respective local algorithm is transferred to an aggregating system that generates the aggregate algorithm based on the algorithm datasets.

Abstract: At least one example embodiment provides a computer-implemented method for evaluating at least one image data set of an imaging region of a patient, wherein at least one evaluation information describing at least one medical condition in an anatomical structure of the imaging region is determined.

Abstract: At least one example embodiment provides an improved handling of image data sets of patients.

Abstract: Systems and methods for automated assessment of a vessel are provided. One or more input medical images of a vessel of a patient are received. A plurality of vessel assessment tasks for assessing the vessel is performed using a machine learning based model trained using multi-task learning. The plurality of vessel assessment tasks are performed by the machine learning based model based on shared features extracted from the one or more input medical images. Results of the plurality of vessel assessment tasks or a combination of the results of the plurality of vessel assessment tasks are output.

Abstract: A method, preferably a computer implemented method, and system are for providing output data associated with a medical imaging dataset of a patient, the medical imaging dataset including image data of a region of an anatomy of a patient including a plurality of coronary arteries. The output data is a significance score associated with a medical imaging data set of a patient. The method, in the most general terms, includes receiving input data, e.g. via a first interface, generating output data by applying algorithmic operations to the input data, and providing the output data, e.g. via a second interface.

Abstract: A computer-implemented method is for providing a two-dimensional unfolded image of at least one tubular structure. In an embodiment, the method includes receiving three-dimensional image data of an examination region including the at least one tubular structure; selecting a set of input points in the three-dimensional image data; determining a projection surface with respect to the three-dimensional image data; calculating a set of surface points of the projection surface; calculating a deformed projection surface by applying a deformation algorithm onto the projection surface; calculating a set of voxel positions with respect to the three-dimensional image data based on the deformed projection surface; and calculating the two-dimensional unfolded image of the at least one tubular structure based on the three-dimensional image data and the set of voxel positions.

Abstract: In hemodynamic determination in medical imaging, the classifier is trained from synthetic data rather than relying on training data from other patients. A computer model (in silico) may be perturbed in many different ways to generate many different examples. The flow is calculated for each resulting example. A bench model (in vitro) may similarly be altered in many different ways. The flow is measured for each resulting example. The machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data. Perturbations or alterations may account for therapy so that the machine-trained classifier may estimate the results of therapeutically altering a patient-specific input feature. Uncertainty may be handled by training the classifier to predict a distribution of possibilities given uncertain input distribution.

Abstract: A computer-implemented method is for providing a two-dimensional unfolded image of at least one tubular structure. In an embodiment, the method includes receiving three-dimensional image data of an examination region including the at least one tubular structure; selecting a set of input points in the three-dimensional image data; determining a projection surface with respect to the three-dimensional image data; calculating a set of surface points of the projection surface; calculating a deformed projection surface by applying a deformation algorithm onto the projection surface; calculating a set of voxel positions with respect to the three-dimensional image data based on the deformed projection surface; and calculating the two-dimensional unfolded image of the at least one tubular structure based on the three-dimensional image data and the set of voxel positions.

Abstract: A computer-implemented method is for evaluating a CT data set of a coronary region of a patient regarding perivascular tissue of at least one target blood vessel. In an embodiment, the computer-implemented method automatically determines a centerline of at least the at least one target blood vessel in the CT data set; defines a region of interest as including at least one defined outer region radius around an extension interval of the centerline, the outer region radius being relatively larger than a radius of the at least one target blood vessel; and calculates at least one quantitative value from CT data in the region of interest.

Abstract: In hemodynamic determination in medical imaging, the classifier is trained from synthetic data rather than relying on training data from other patients. A computer model (in silico) may be perturbed in many different ways to generate many different examples. The flow is calculated for each resulting example. A bench model (in vitro) may similarly be altered in many different ways. The flow is measured for each resulting example. The machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data. Perturbations or alterations may account for therapy so that the machine-trained classifier may estimate the results of therapeutically altering a patient-specific input feature. Uncertainty may be handled by training the classifier to predict a distribution of possibilities given uncertain input distribution.

Abstract: A method, for two-dimensional mapping of anatomical structures of a patient, includes acquiring three-dimensional image data of anatomical structures of a patient; adapting a virtual network structure to a spatial course of the anatomical structures; defining a user-defined map projection for projection of two-dimensional pixel positions of an image to be output onto a geometric figure around a center of the anatomical structures for which mapping onto a two-dimensional space is defined; ascertaining points of intersection of radially extending half lines assigned to the two-dimensional pixel positions of the image to be output with the virtual network structure; and ascertaining the image to be output based upon image intensity values assigned to the points of intersection ascertained. A method for two-dimensional mapping of the tree-like elongated structure of the patient; a method for simultaneous mapping of a tree-like elongated structure; and corresponding apparatuses are also described.

Abstract: A method is for providing an aggregate algorithm for processing medical data. In an embodiment, a multitude of local algorithms are trained by machine learning. The training of each respective local algorithm is performed on a respective local system using respective local training data. A respective algorithm dataset concerning the respective local algorithm is transferred to an aggregating system that generates the aggregate algorithm based on the algorithm datasets.

Abstract: A method and apparatus for deep learning based automatic bone removal in medical images, such as computed tomography angiography (CTA) volumes, is disclosed. Bone structures are segmented in a 3D medical image of a patient by classifying voxels of the 3D medical image as bone or non-bone voxels using a deep neural network trained for bone segmentation. A 3D visualization of non-bone structures in the 3D medical image is generated by removing voxels classified as bone voxels from a 3D visualization of the 3D medical image.

Abstract: A method and system for determining hemodynamic indices, such as fractional flow reserve (FFR), for a location of interest in a coronary artery of a patient is disclosed. Medical image data of a patient is received. Patient-specific coronary arterial tree geometry of the patient is extracted from the medical image data. Geometric features are extracted from the patient-specific coronary arterial tree geometry of the patient. A hemodynamic index, such as FFR, is computed for a location of interest in the patient-specific coronary arterial tree based on the extracted geometric features using a trained machine-learning based surrogate model. The machine-learning based surrogate model is trained based on geometric features extracted from synthetically generated coronary arterial tree geometries.